Щоб переглянути інші типи публікацій з цієї теми, перейдіть за посиланням: Models of neural elements.
Статті в журналах з теми "Models of neural elements"
Оформте джерело за APA, MLA, Chicago, Harvard та іншими стилями
Ознайомтеся з топ-50 статей у журналах для дослідження на тему "Models of neural elements".
Біля кожної праці в переліку літератури доступна кнопка «Додати до бібліографії». Скористайтеся нею – і ми автоматично оформимо бібліографічне посилання на обрану працю в потрібному вам стилі цитування: APA, MLA, «Гарвард», «Чикаго», «Ванкувер» тощо.
Також ви можете завантажити повний текст наукової публікації у форматі «.pdf» та прочитати онлайн анотацію до роботи, якщо відповідні параметри наявні в метаданих.
Переглядайте статті в журналах для різних дисциплін та оформлюйте правильно вашу бібліографію.
1
Bainbridge, William Sims. "Neural Network Models of Religious Belief." Sociological Perspectives 38, no. 4 (December 1995): 483–95. http://dx.doi.org/10.2307/1389269.
Повний текст джерелаАнотація:
This paper applies neural network technology, a standard approach in computer science that has been unaccountably ignored by sociologists, to the problem of developing rigorous sociological theories. A simulation program employing a “varimax” model of human learning and decision-making models central elements of the Stark-Bainbridge theory of religion. Individuals in a micro-society of 24 simulated people learn which categories of potential exchange partners to seek for each of four material rewards which in fact can be provided by other actors in the society. However, when they seek eternal life, they are unable to find suitable human exchange partners who can provide it to them, so they postulate the existence of supernatural exchange partners as substitutes. The explanation of how the particular neural net works, including reference to modulo arithmetic, introduces some aspects of this new technology to sociology, and this paper invites readers to explore the wide range of other neural net techniques that may be of value for social scientists
2
Yaish, Ofir, and Yaron Orenstein. "Computational modeling of mRNA degradation dynamics using deep neural networks." Bioinformatics 38, no. 4 (November 26, 2021): 1087–101. http://dx.doi.org/10.1093/bioinformatics/btab800.
Повний текст джерелаАнотація:
Abstract Motivation messenger RNA (mRNA) degradation plays critical roles in post-transcriptional gene regulation. A major component of mRNA degradation is determined by 3′-UTR elements. Hence, researchers are interested in studying mRNA dynamics as a function of 3′-UTR elements. A recent study measured the mRNA degradation dynamics of tens of thousands of 3′-UTR sequences using a massively parallel reporter assay. However, the computational approach used to model mRNA degradation was based on a simplifying assumption of a linear degradation rate. Consequently, the underlying mechanism of 3′-UTR elements is still not fully understood. Results Here, we developed deep neural networks to predict mRNA degradation dynamics and interpreted the networks to identify regulatory elements in the 3′-UTR and their positional effect. Given an input of a 110 nt-long 3′-UTR sequence and an initial mRNA level, the model predicts mRNA levels of eight consecutive time points. Our deep neural networks significantly improved prediction performance of mRNA degradation dynamics compared with extant methods for the task. Moreover, we demonstrated that models predicting the dynamics of two identical 3′-UTR sequences, differing by their poly(A) tail, performed better than single-task models. On the interpretability front, by using Integrated Gradients, our convolutional neural networks (CNNs) models identified known and novel cis-regulatory sequence elements of mRNA degradation. By applying a novel systematic evaluation of model interpretability, we demonstrated that the recurrent neural network models are inferior to the CNN models in terms of interpretability and that random initialization ensemble improves both prediction and interoperability performance. Moreover, using a mutagenesis analysis, we newly discovered the positional effect of various 3′-UTR elements. Availability and implementation All the code developed through this study is available at github.com/OrensteinLab/DeepUTR/. Supplementary information Supplementary data are available at Bioinformatics online.
3
Seeliger, K., L. Ambrogioni, Y. Güçlütürk, L. M. van den Bulk, U. Güçlü, and M. A. J. van Gerven. "End-to-end neural system identification with neural information flow." PLOS Computational Biology 17, no. 2 (February 4, 2021): e1008558. http://dx.doi.org/10.1371/journal.pcbi.1008558.
Повний текст джерелаАнотація:
Neural information flow (NIF) provides a novel approach for system identification in neuroscience. It models the neural computations in multiple brain regions and can be trained end-to-end via stochastic gradient descent from noninvasive data. NIF models represent neural information processing via a network of coupled tensors, each encoding the representation of the sensory input contained in a brain region. The elements of these tensors can be interpreted as cortical columns whose activity encodes the presence of a specific feature in a spatiotemporal location. Each tensor is coupled to the measured data specific to a brain region via low-rank observation models that can be decomposed into the spatial, temporal and feature receptive fields of a localized neuronal population. Both these observation models and the convolutional weights defining the information processing within regions are learned end-to-end by predicting the neural signal during sensory stimulation. We trained a NIF model on the activity of early visual areas using a large-scale fMRI dataset recorded in a single participant. We show that we can recover plausible visual representations and population receptive fields that are consistent with empirical findings.
4
Wang, Zhaojun, Jiangning Wang, Congtian Lin, Yan Han, Zhaosheng Wang, and Liqiang Ji. "Identifying Habitat Elements from Bird Images Using Deep Convolutional Neural Networks." Animals 11, no. 5 (April 27, 2021): 1263. http://dx.doi.org/10.3390/ani11051263.
Повний текст джерелаАнотація:
With the rapid development of digital technology, bird images have become an important part of ornithology research data. However, due to the rapid growth of bird image data, it has become a major challenge to effectively process such a large amount of data. In recent years, deep convolutional neural networks (DCNNs) have shown great potential and effectiveness in a variety of tasks regarding the automatic processing of bird images. However, no research has been conducted on the recognition of habitat elements in bird images, which is of great help when extracting habitat information from bird images. Here, we demonstrate the recognition of habitat elements using four DCNN models trained end-to-end directly based on images. To carry out this research, an image database called Habitat Elements of Bird Images (HEOBs-10) and composed of 10 categories of habitat elements was built, making future benchmarks and evaluations possible. Experiments showed that good results can be obtained by all the tested models. ResNet-152-based models yielded the best test accuracy rate (95.52%); the AlexNet-based model yielded the lowest test accuracy rate (89.48%). We conclude that DCNNs could be efficient and useful for automatically identifying habitat elements from bird images, and we believe that the practical application of this technology will be helpful for studying the relationships between birds and habitat elements.
5
Boriskov, Petr, and Andrei Velichko. "Switch Elements with S-Shaped Current-Voltage Characteristic in Models of Neural Oscillators." Electronics 8, no. 9 (August 22, 2019): 922. http://dx.doi.org/10.3390/electronics8090922.
Повний текст джерелаАнотація:
In this paper, we present circuit solutions based on a switch element with the S-type I–V characteristic implemented using the classic FitzHugh–Nagumo and FitzHugh–Rinzel models. Using the proposed simplified electrical circuits allows the modeling of the integrate-and-fire neuron and burst oscillation modes with the emulation of the mammalian cold receptor patterns. The circuits were studied using the experimental I–V characteristic of an NbO2 switch with a stable section of negative differential resistance (NDR) and a VO2 switch with an unstable NDR, considering the temperature dependences of the threshold characteristics. The results are relevant for modern neuroelectronics and have practical significance for the introduction of the neurodynamic models in circuit design and the brain–machine interface. The proposed systems of differential equations with the piecewise linear approximation of the S-type I–V characteristic may be of scientific interest for further analytical and numerical research and development of neural networks with artificial intelligence.
6
Marchesin, Stefano, Alberto Purpura, and Gianmaria Silvello. "Focal elements of neural information retrieval models. An outlook through a reproducibility study." Information Processing & Management 57, no. 6 (November 2020): 102109. http://dx.doi.org/10.1016/j.ipm.2019.102109.
Повний текст джерела
7
De Wolf, E. D., and L. J. Franel. "Neural Networks That Distinguish Infection Periods of Wheat Tan Spot in an Outdoor Environment." Phytopathology® 87, no. 1 (January 1997): 83–87. http://dx.doi.org/10.1094/phyto.1997.87.1.83.
Повний текст джерелаАнотація:
Tan spot of wheat, caused by Pyrenophora tritici-repentis, provided a model system for testing disease forecasts based on an artificial neural network. Infection periods for P. tritici-repentis on susceptible wheat cultivars were identified from a bioassay system that correlated tan spot incidence with crop growth stage and 24-h summaries of environmental data, including temperature, relative humidity, wind speed, wind direction, solar radiation, precipitation, and flat-plate resistance-type wetness sensors. The resulting data set consisted of 97 discrete periods, of which 32 were reserved for validation analysis. Neural networks with zero to nine processing elements were evaluated 20 times each to identify the model that most accurately predicted an infection event. The 200 models averaged 74 to 77% accuracy, depending on the number of processing elements and random initialization of coefficients. The most accurate model had five processing elements and correctly predicted 87% of the infection periods in the validation set. In comparison, stepwise logistic regression correctly predicted 69% of the validation cases, and multivariate discriminant analysis distinguished 50% of the validation cases. When wetness-sensor inputs were withheld from the models, both the neural network and logistic regression models declined 6% in prediction accuracy. Thus, neural networks were more accurate than statistical procedures, both with and without wetness-sensor inputs. These results demonstrate the applicability of neural networks to plant disease forecasting.
8
Cid, Juan M., Jesús García, Javier Monge, and Juan Zapata. "Design of microwave devices by segmentation, finite elements, reduced-order models, and neural networks." Microwave and Optical Technology Letters 49, no. 3 (January 26, 2007): 655–59. http://dx.doi.org/10.1002/mop.22248.
Повний текст джерела
9
Yuille, Alan L. "Generalized Deformable Models, Statistical Physics, and Matching Problems." Neural Computation 2, no. 1 (March 1990): 1–24. http://dx.doi.org/10.1162/neco.1990.2.1.1.
Повний текст джерелаАнотація:
We describe how to formulate matching and combinatorial problems of vision and neural network theory by generalizing elastic and deformable templates models to include binary matching elements. Techniques from statistical physics, which can be interpreted as computing marginal probability distributions, are then used to analyze these models and are shown to (1) relate them to existing theories and (2) give insight into the relations between, and relative effectivenesses of, existing theories. In particular we exploit the power of statistical techniques to put global constraints on the set of allowable states of the binary matching elements. The binary elements can then be removed analytically before minimization. This is demonstrated to be preferable to existing methods of imposing such constraints by adding bias terms in the energy functions. We give applications to winner-take-all networks, correspondence for stereo and long-range motion, the traveling salesman problem, deformable template matching, learning, content addressable memories, and models of brain development. The biological plausibility of these networks is briefly discussed.
10
Fujiwara, Yusuke, Yoichi Miyawaki, and Yukiyasu Kamitani. "Modular Encoding and Decoding Models Derived from Bayesian Canonical Correlation Analysis." Neural Computation 25, no. 4 (April 2013): 979–1005. http://dx.doi.org/10.1162/neco_a_00423.
Повний текст джерелаАнотація:
Neural encoding and decoding provide perspectives for understanding neural representations of sensory inputs. Recent functional magnetic resonance imaging (fMRI) studies have succeeded in building prediction models for encoding and decoding numerous stimuli by representing a complex stimulus as a combination of simple elements. While arbitrary visual images were reconstructed using a modular model that combined the outputs of decoder modules for multiscale local image bases (elements), the shapes of the image bases were heuristically determined. In this work, we propose a method to establish mappings between the stimulus and the brain by automatically extracting modules from measured data. We develop a model based on Bayesian canonical correlation analysis, in which each module is modeled by a latent variable that relates a set of pixels in a visual image to a set of voxels in an fMRI activity pattern. The estimated mapping from a latent variable to pixels can be regarded as an image basis. We show that the model estimates a modular representation with spatially localized multiscale image bases. Further, using the estimated mappings, we derive encoding and decoding models that produce accurate predictions for brain activity and stimulus images. Our approach thus provides a novel means of revealing neural representations of stimuli by automatically extracting modules, which can be used to generate effective prediction models for encoding and decoding.
11
Fischer, M. M. "Computational Neural Networks: A New Paradigm for Spatial Analysis." Environment and Planning A: Economy and Space 30, no. 10 (October 1998): 1873–91. http://dx.doi.org/10.1068/a301873.
Повний текст джерелаАнотація:
In this paper a systematic introduction to computational neural network models is given in order to help spatial analysts learn about this exciting new field. The power of computational neural networks viz-à-viz conventional modelling is illustrated for an application field with noisy data of limited record length: spatial interaction modelling of telecommunication data in Austria. The computational appeal of neural networks for solving some fundamental spatial analysis problems is summarized and a definition of computational neural network models in mathematical terms is given. Three definitional components of a computational neural network—properties of the processing elements, network topology and learning—are discussed and a taxonomy of computational neural networks is presented, breaking neural networks down according to the topology and type of interconnections and the learning paradigm adopted. The attractiveness of computational neural network models compared with the conventional modelling approach of the gravity type for spatial interaction modelling is illustrated before some conclusions and an outlook are given.
12
Tunakova, Yulia, Svetlana Novikova, Aligejdar Ragimov, Rashat Faizullin, and Vsevolod Valiev. "A Method for Assessing the Retention of Trace Elements in Human Body Using Neural Network Technology." Journal of Healthcare Engineering 2017 (2017): 1–7. http://dx.doi.org/10.1155/2017/3471616.
Повний текст джерелаАнотація:
Models that describe the trace element status formation in the human organism are essential for a correction of micromineral (trace elements) deficiency. A direct trace element retention assessment in the body is difficult due to the many internal mechanisms. The trace element retention is determined by the amount and the ratio of incoming and excreted substance. So, the concentration of trace elements in drinking water characterizes the intake, whereas the element concentration in urine characterizes the excretion. This system can be interpreted as three interrelated elements that are in equilibrium. Since many relationships in the system are not known, the use of standard mathematical models is difficult. The artificial neural network use is suitable for constructing a model in the best way because it can take into account all dependencies in the system implicitly and process inaccurate and incomplete data. We created several neural network models to describe the retentions of trace elements in the human body. On the model basis, we can calculate the microelement levels in the body, knowing the trace element levels in drinking water and urine. These results can be used in health care to provide the population with safe drinking water.
13
KRASILENKO, VLADIMIR, NATALIYA YURCHUK, and Diana NIKITOVICH. "DESIGN AND SIMULATION OF NEURON-EQUIVALENTORS ARRAY FOR CREATION OF SELF-LEARNING EQUIVALENT-CONVOLUTIONAL NEURAL STRUCTURES (SLECNS)." HERALD OF KHMELNYTSKYI NATIONAL UNIVERSITY 297, no. 3 (July 2, 2021): 58–69. http://dx.doi.org/10.31891/2307-5732-2021-297-3-58-69.
Повний текст джерелаАнотація:
In the paper, we consider the urgent need to create highly efficient hardware accelerators for machine learning algorithms, including convolutional and deep neural networks (CNN and DNNS), for associative memory models, clustering, and pattern recognition. We show a brief overview of our related works the advantages of the equivalent models (EM) for describing and designing bio-inspired systems. The capacity of NN on the basis of EM and of its modifications is in several times quantity of neurons. Such neural paradigms are very perspective for processing, clustering, recognition, storing large size, strongly correlated, highly noised images and creating of uncontrolled learning machine. And since the basic operational functional nodes of EM are such vector-matrix or matrix-tensor procedures with continuous-logical operations as: normalized vector operations “equivalence”, “nonequivalence”, and etc. , we consider in this paper new conceptual approaches to the design of full-scale arrays of such neuron-equivalentors (NEs) with extended functionality, including different activation functions. Our approach is based on the use of analog and mixed (with special coding) methods for implementing the required operations, building NEs (with number of synapsis from 8 up to 128 and more) and their base cells, nodes based on photosensitive elements and CMOS current mirrors. Simulation results show that the efficiency of NEs relative to the energy intensity is estimated at a value of not less than 1012 an. op. / sec on W and can be increased. The results confirm the correctness of the concept and the possibility of creating NE and MIMO structures on their basis.
14
Ćirić, Tomislav, Rohan Dhuri, Zlatica Marinković, Olivera Pronić-Rančić, Vera Marković, and Larissa Vietzorreck. "Neural Based Lumped Element Model of Capacitive RF MEMS Switches." Frequenz 72, no. 11-12 (November 27, 2018): 539–46. http://dx.doi.org/10.1515/freq-2018-0023.
Повний текст джерелаАнотація:
Abstract In this paper a lumped element model of RF MEMS capacitive switches which is scalable with the lateral dimensions of the bridge is proposed. The dependence of the elements of the model on the bridge dimensions is introduced by using one or more artificial neural networks to model the relationship between the bridge dimensions and the inductive and resistive elements of the lumped element model. The achieved results show that the developed models have a good accuracy over the whole considered range of the bridge dimension values.
15
Zahran, B. "Using Neural Networks to Predict the Hardness of Aluminum Alloys." Engineering, Technology & Applied Science Research 5, no. 1 (February 8, 2015): 757–59. http://dx.doi.org/10.48084/etasr.529.
Повний текст джерелаАнотація:
Aluminum alloys have gained significant industrial importance being involved in many of the light and heavy industries and especially in aerospace engineering. The mechanical properties of aluminum alloys are defined by a number of principal microstructural features. Conventional mathematical models of these properties are sometimes very complex to be analytically calculated. In this paper, a neural network model is used to predict the correlations between the hardness of aluminum alloys in relation to certain alloying elements. A backpropagation neural network is trained using a thorough dataset. The impact of certain elements is documented and an optimum structure is proposed
16
Ahmad, Afaq, Vagelis Plevris, and Qaiser-uz-Zaman Khan. "Prediction of Properties of FRP-Confined Concrete Cylinders Based on Artificial Neural Networks." Crystals 10, no. 9 (September 14, 2020): 811. http://dx.doi.org/10.3390/cryst10090811.
Повний текст джерелаАнотація:
Recently, the use of fiber-reinforced polymers (FRP)-confinement has increased due to its various favorable effects on concrete structures, such as an increase in strength and ductility. Therefore, researchers have been attracted to exploring the behavior and efficiency of FRP-confinement for concrete structural elements further. The current study investigates improved strength and strain models for FRP confined concrete cylindrical elements. Two new physical methods are proposed for use on a large preliminary evaluated database of 708 specimens for strength and 572 specimens for strain from previous experiments. The first approach is employing artificial neural networks (ANNs), and the second is using the general regression analysis technique for both axial strength and strain of FRP-confined concrete. The accuracy of the newly proposed strain models is quite satisfactory in comparison with previous experimental results. Moreover, the predictions of the proposed ANN models are better than the predictions of previously proposed models based on various statistical indices, such as the correlation coefficient (R) and mean square error (MSE), and can be used to assess the members at the ultimate limit state.
17
Chapeau-Blondeau, François, and Nicolas Chambet. "Synapse Models for Neural Networks: From Ion Channel Kinetics to Multiplicative Coefficient wij." Neural Computation 7, no. 4 (July 1995): 713–34. http://dx.doi.org/10.1162/neco.1995.7.4.713.
Повний текст джерелаАнотація:
This paper relates different levels at which the modeling of synaptic transmission can be grounded in neural networks: the level of ion channel kinetics, the level of synaptic conductance dynamics, and the level of a scalar synaptic coefficient. The important assumptions to reduce a synapse model from one level to the next are explicitly exhibited. This coherent progression provides control on what is discarded and what is retained in the modeling process, and is useful to appreciate the significance and limitations of the resulting neural networks. This methodic simplification terminates with a scalar synaptic efficacy as it is very often used in neural networks, but here its conditions of validity are explicitly displayed. This scalar synapse also comes with an expression that directly relates it to basic quantities of synaptic functioning, and it can be endowed with meaningful physical units and realistic numerical values. In addition, it is shown that the scalar synapse does not receive the same expression in neural networks operating with spikes or with firing rates. These coherent modeling elements can help to improve, adjust, and refine the investigation of neural systems and their remarkable collective properties for information processing.
18
MARWALA, T., and H. E. M. HUNT. "FAULT IDENTIFICATION USING FINITE ELEMENT MODELS AND NEURAL NETWORKS." Mechanical Systems and Signal Processing 13, no. 3 (May 1999): 475–90. http://dx.doi.org/10.1006/mssp.1998.1218.
Повний текст джерела
19
Kusdarwati, Heni, and Samingun Handoyo. "System for Prediction of Non Stationary Time Series based on the Wavelet Radial Bases Function Neural Network Model." International Journal of Electrical and Computer Engineering (IJECE) 8, no. 4 (August 1, 2018): 2327. http://dx.doi.org/10.11591/ijece.v8i4.pp2327-2337.
Повний текст джерелаАнотація:
This paper proposes and examines the performance of a hybrid model called the wavelet radial bases function neural networks (WRBFNN). The model will be compared its performance with the wavelet feed forward neural networks (WFFN model by developing a prediction or forecasting system that considers two types of input formats: input9 and input17, and also considers 4 types of non-stationary time series data. The MODWT transform is used to generate wavelet and smooth coefficients, in which several elements of both coefficients are chosen in a particular way to serve as inputs to the NN model in both RBFNN and FFNN models. The performance of both WRBFNN and WFFNN models is evaluated by using MAPE and MSE value indicators, while the computation process of the two models is compared using two indicators, many epoch, and length of training. In stationary benchmark data, all models have a performance with very high accuracy. The WRBFNN9 model is the most superior model in nonstationary data containing linear trend elements, while the WFFNN17 model performs best on non-stationary data with the non-linear trend and seasonal elements. In terms of speed in computing, the WRBFNN model is superior with a much smaller number of epochs and much shorter training time.
20
Kumar, Vinod, Parveen Sihag, Ali Keshavarzi, Shevita Pandita, and Andrés Rodríguez-Seijo. "Soft Computing Techniques for Appraisal of Potentially Toxic Elements from Jalandhar (Punjab), India." Applied Sciences 11, no. 18 (September 9, 2021): 8362. http://dx.doi.org/10.3390/app11188362.
Повний текст джерелаАнотація:
The contamination of potentially toxic elements (PTEs) in agricultural soils is a serious concern around the globe, and modelling approaches is imperative in order to determine the possible hazards linked with PTEs. These techniques accurately assess the PTEs in soil, which play a pivotal role in eliminating the weaknesses in determining PTEs in soils. This paper aims to predict the concentration of Cu, Co and Pb using neural networks (NNs) based on multilayer perceptron (MLP) and boosted regression trees (BT). Statistical performance estimation factors were rummage-sale to measure the performance of developed models. Comparison of the coefficient of correlation and root mean squared error suggest that MLP-established models perform better than BT-based models for predicting the concentration of Cu and Pb, whereas BT models perform better than MLP established models at predicting the concentration of Co.
21
Kim, Mansu, Sungwon Jung, and Joo-won Kang. "Artificial Neural Network-Based Residential Energy Consumption Prediction Models Considering Residential Building Information and User Features in South Korea." Sustainability 12, no. 1 (December 22, 2019): 109. http://dx.doi.org/10.3390/su12010109.
Повний текст джерелаАнотація:
When researching the energy consumption of residential buildings, it is becoming increasingly important to consider how residents use energy. With the advancement of computing power and data analysis techniques, it is now possible to analyze user information using big data techniques. Here, we endeavored to integrate user information with the physical characteristics of residential buildings to analyze how these elements impact energy consumption. Regression analysis was conducted to accurately identify the impact of each element on energy consumption. It was found that six elements were influential in all seasons: the number of exterior walls, housing direction, housing area, number of years occupied, number of household members, and the occupation of the household head. The elements that had an impact in each period were then derived. Based on the results of the regression analysis, input variables for the training of an artificial neural network (ANN) model were selected for each period, and residential energy consumption prediction models were implemented based on actual consumption. The elements identified as those affecting energy consumption, through regression analysis, can be used for implementing prediction models with advanced forms. This study is significant in that we derived influential elements from an integrative perspective.
22
Makarov, Valeri A., Yongli Song, Manuel G. Velarde, David Hübner, and Holk Cruse. "Elements for a general memory structure: properties of recurrent neural networks used to form situation models." Biological Cybernetics 98, no. 5 (March 19, 2008): 371–95. http://dx.doi.org/10.1007/s00422-008-0221-5.
Повний текст джерела
23
Fan, Angela, Jack Urbanek, Pratik Ringshia, Emily Dinan, Emma Qian, Siddharth Karamcheti, Shrimai Prabhumoye, et al. "Generating Interactive Worlds with Text." Proceedings of the AAAI Conference on Artificial Intelligence 34, no. 02 (April 3, 2020): 1693–700. http://dx.doi.org/10.1609/aaai.v34i02.5532.
Повний текст джерелаАнотація:
Procedurally generating cohesive and interesting game environments is challenging and time-consuming. In order for the relationships between the game elements to be natural, common-sense has to be encoded into arrangement of the elements. In this work, we investigate a machine learning approach for world creation using content from the multi-player text adventure game environment LIGHT (Urbanek et al. 2019). We introduce neural network based models to compositionally arrange locations, characters, and objects into a coherent whole. In addition to creating worlds based on existing elements, our models can generate new game content. Humans can also leverage our models to interactively aid in worldbuilding. We show that the game environments created with our approach are cohesive, diverse, and preferred by human evaluators compared to other machine learning based world construction algorithms.
24
CARD, HOWARD. "ARTIFICIAL NEURAL COMPUTATIONS IN DIGITAL ARRAYS." Journal of Circuits, Systems and Computers 08, no. 05n06 (October 1998): 525–39. http://dx.doi.org/10.1142/s021812669800033x.
Повний текст джерелаАнотація:
In this paper the properties of artificial neural network computations by digital VLSI systems are discussed. We also comment on artificial computational models, learning algorithms, and digital implementations of ANNs in general. The analysis applies to regular arrays or processing elements performing binary integer arithmetic at various bit precisions. Computation rates are limited by power dissipation which is dependent upon required precision and packaging constraints such as pinout. They also depend strongly on the minimum feature size of the CMOS technology. Custom digital implementations with low bit precision are emphasized, because these circuits require less power and silicon area. This may be achieved using stochastic arithmetic, with pseudorandom number generation using cellular automata.
25
Xue, Lanqing, Xiaopeng Li, and Nevin L. Zhang. "Not All Attention Is Needed: Gated Attention Network for Sequence Data." Proceedings of the AAAI Conference on Artificial Intelligence 34, no. 04 (April 3, 2020): 6550–57. http://dx.doi.org/10.1609/aaai.v34i04.6129.
Повний текст джерелаАнотація:
Although deep neural networks generally have fixed network structures, the concept of dynamic mechanism has drawn more and more attention in recent years. Attention mechanisms compute input-dependent dynamic attention weights for aggregating a sequence of hidden states. Dynamic network configuration in convolutional neural networks (CNNs) selectively activates only part of the network at a time for different inputs. In this paper, we combine the two dynamic mechanisms for text classification tasks. Traditional attention mechanisms attend to the whole sequence of hidden states for an input sentence, while in most cases not all attention is needed especially for long sequences. We propose a novel method called Gated Attention Network (GA-Net) to dynamically select a subset of elements to attend to using an auxiliary network, and compute attention weights to aggregate the selected elements. It avoids a significant amount of unnecessary computation on unattended elements, and allows the model to pay attention to important parts of the sequence. Experiments in various datasets show that the proposed method achieves better performance compared with all baseline models with global or local attention while requiring less computation and achieving better interpretability. It is also promising to extend the idea to more complex attention-based models, such as transformers and seq-to-seq models.
26
Chen, Z. X., J. W. Shuai, R. T. Liu, and B. X. Wu. "The stability of the 2n-element number neural network models." Physica A: Statistical Mechanics and its Applications 218, no. 3-4 (September 1995): 291–97. http://dx.doi.org/10.1016/0378-4371(95)00128-t.
Повний текст джерела
27
Botov, D. S., J. D. Klenin, and I. E. Nikolaev. "Information extraction using neural language models for the case of online job listings analysis." Yugra State University Bulletin 14, no. 3 (December 15, 2018): 37–48. http://dx.doi.org/10.17816/byusu2018037-48.
Повний текст джерелаАнотація:
In this article we discuss the approach to information extraction (IE) using neural language models. We provide a detailed overview of modern IE methods: both supervised and unsupervised. The proposed method allows to achieve a high quality solution to the problem of analyzing the relevant labor market requirements without the need for a time-consuming labelling procedure. In this experiment, professional standards act as a knowledge base of the labor domain. Comparing the descriptions of work actions and requirements from professional standards with the elements of job listings, we extract four entity types. The approach is based on the classification of vector representations of texts, generated using various neural language models: averaged word2vec, SIF-weighted averaged word2vec, TF-IDF-weighted averaged word2vec, paragraph2vec. Experimentally, the best quality was shown by the averaged word2vec (CBOW) model.
28
Woo, Yunhee, Dongyoung Kim, Jaemin Jeong, Young-Woong Ko, and Jeong-Gun Lee. "Zero-Keep Filter Pruning for Energy/Power Efficient Deep Neural Networks." Electronics 10, no. 11 (May 22, 2021): 1238. http://dx.doi.org/10.3390/electronics10111238.
Повний текст джерелаАнотація:
Recent deep learning models succeed in achieving high accuracy and fast inference time, but they require high-performance computing resources because they have a large number of parameters. However, not all systems have high-performance hardware. Sometimes, a deep learning model needs to be run on edge devices such as IoT devices or smartphones. On edge devices, however, limited computing resources are available and the amount of computation must be reduced to launch the deep learning models. Pruning is one of the well-known approaches for deriving light-weight models by eliminating weights, channels or filters. In this work, we propose “zero-keep filter pruning” for energy-efficient deep neural networks. The proposed method maximizes the number of zero elements in filters by replacing small values with zero and pruning the filter that has the lowest number of zeros. In the conventional approach, the filters that have the highest number of zeros are generally pruned. As a result, through this zero-keep filter pruning, we can have the filters that have many zeros in a model. We compared the results of the proposed method with the random filter pruning and proved that our method shows better performance with many fewer non-zero elements with a marginal drop in accuracy. Finally, we discuss a possible multiplier architecture, zero-skip multiplier circuit, which skips the multiplications with zero to accelerate and reduce energy consumption.
29
Li, Pengpeng, An Luo, Jiping Liu, Yong Wang, Jun Zhu, Yue Deng, and Junjie Zhang. "Bidirectional Gated Recurrent Unit Neural Network for Chinese Address Element Segmentation." ISPRS International Journal of Geo-Information 9, no. 11 (October 26, 2020): 635. http://dx.doi.org/10.3390/ijgi9110635.
Повний текст джерелаАнотація:
Chinese address element segmentation is a basic and key step in geocoding technology, and the segmentation results directly affect the accuracy and certainty of geocoding. However, due to the lack of obvious word boundaries in Chinese text, the grammatical and semantic features of Chinese text are complicated. Coupled with the diversity and complexity in Chinese address expressions, the segmentation of Chinese address elements is a substantial challenge. Therefore, this paper proposes a method of Chinese address element segmentation based on a bidirectional gated recurrent unit (Bi-GRU) neural network. This method uses the Bi-GRU neural network to generate tag features based on Chinese word segmentation and then uses the Viterbi algorithm to perform tag inference to achieve the segmentation of Chinese address elements. The neural network model is trained and verified based on the point of interest (POI) address data and partial directory data from the Baidu map of Beijing. The results show that the method is superior to previous neural network models in terms of segmentation performance and efficiency.
30
Pang, Xiaojia. "Intelligent Psychology Teaching System Based on Adaptive Neural Network." Applied Bionics and Biomechanics 2022 (April 4, 2022): 1–11. http://dx.doi.org/10.1155/2022/6248095.
Повний текст джерелаАнотація:
In order to study the intelligent psychology system, this paper proposes the role of adaptive neural network based on it and uses the ICAP learning method to compare with it. Firstly, the basic structure of the neural network in the teaching system is introduced, the psychological teaching algorithm based on the adaptive neural network is introduced, the ideas are formulated, and the four learning methods and the design elements of the adaptive neural network are described. The corresponding relationship between the four learning methods and the adaptive neural network is explained. The most popular and advanced adaptive neural network module usage statistics are made. The network model on the right is more advanced than the left, and the classification accuracy is higher. The interactive learning elements used by the network model from left to right gradually increase, and the performances of the network model are gradually enhanced. Among them, the number of interactive learning elements inception modules used by the network models GoogLeNet, Inception-v2, Inception-v4, and Inception-ResNet-v2 are 9, 10, 14, and 20, respectively. Inception-v4 also employs 2 interactive learning element reduction modules. Inception-ResNet-v2 uses 2 interactive learning element reduction modules and 20 residual modules. The ICAP classification method is experimentally studied. The design of the experiment adopts passive method (P), active method (A), constructive method (C), and interactive method (I), respectively, to learn a short text in materials science. By analyzing the learning effect and comparing the data before and after the test, it can be concluded that the learning performance of the four learning methods gradually increased by 8%-10%, and the learning effect increased significantly. With the gradual increase of educational psychological learning elements in the adaptive neural network, the network learning level is continuously improved, and the classification accuracy is gradually improved.
31
Tarelko, Wieslaw, and Krzysztof Rudzki. "Applying artificial neural networks for modelling ship speed and fuel consumption." Neural Computing and Applications 32, no. 23 (June 16, 2020): 17379–95. http://dx.doi.org/10.1007/s00521-020-05111-2.
Повний текст джерелаАнотація:
AbstractThis paper deals with modelling ship speed and fuel consumption using artificial neural network (ANN) techniques. These tools allowed us to develop ANN models that can be used for predicting both the fuel consumption and the travel time to the destination for commanded outputs (the ship driveline shaft speed and the propeller pitch) selected by the ship operator. In these cases, due to variable environmental conditions, making decisions regarding setting the proper commanded outputs to is extraordinarily difficult. To support such decisions, we have developed a decision support system. Its main elements are the ANN models enabling ship fuel consumption and speed prediction. To collect data needed for building ANN models, sea trials were conducted. In this paper, the decision support system concept, input and variables of the ship driveline system models, and data acquisition methods are presented. Based on them, we developed appropriate ANN models. Subsequently, we performed a quality assessment of the collected data set, data normalization and division of the data set, selection of an ANN model architecture and assessment of their quality.
32
CORINTO, FERNANDO, and MARCO GILLI. "ON STABILITY OF CELLULAR NEURAL NETWORKS WITH POLYNOMIAL INTERACTIONS." International Journal of Neural Systems 13, no. 06 (December 2003): 379–85. http://dx.doi.org/10.1142/s0129065703001704.
Повний текст джерелаАнотація:
Cellular neural/nonlinear networks (CNNs) are analog dynamic processor arrays, that present local interconnections. CNN models with polynomial interactions among the cells (Polynomial type CNNs) have been recently introduced. They are useful for solving some complex computational problems and for real-time implementation of PDE-based algorithms. This manuscript provides some simple and rigorous sufficient conditions for stability of polynomial type CNNs. A particular emphasis is given to conditions that can be expressed in terms of template elements, since they can be exploited for design purposes.
33
Shanbeh, Mohsen, Hossein Hasani, and Somayeh Akhavan Tabatabaei. "Modelling and Predicting the Breaking Strength and Mass Irregularity of Cotton Rotor-Spun Yarns Containing Cotton Fiber Recovered from Ginning Process by Using Artificial Neural Network Algorithm." Modelling and Simulation in Engineering 2011 (2011): 1–8. http://dx.doi.org/10.1155/2011/591905.
Повний текст джерелаАнотація:
One of the main methods to reduce the production costs is waste recycling which is the most important challenge for the future. Cotton wastes collected from ginning process have desirable properties which could be used during spinning process. The purpose of this study was to develop predictive models of breaking strength and mass irregularity (%) of cotton waste rotor-spun yarns containing cotton waste collected from ginning process by using the artificial neural network trained with backpropagation algorithm. Artificial neural network models have been developed based on rotor diameter, rotor speed, navel type, opener roller speed, ginning waste proportion and yarn linear density as input parameters. The parameters of artificial neural network model, namely, learning, and momentum rate, number of hidden layers and number of hidden processing elements (neurons) were optimized to get the best predictive models. The findings showed that the breaking strength and mass irregularity of rotor spun yarns could be predicted satisfactorily by artificial neural network. The maximum error in predicting the breaking strength and mass irregularity of testing data was 8.34% and 6.65%, respectively.
34
Inyang, Udoinyang G., Samuel S. Udoh, and Oluwole C. Akinyokun. "Comparative Analysis of Neural Network Models for Petroleum Products Pipeline Monitoring." Studies in Engineering and Technology 4, no. 1 (April 6, 2017): 53. http://dx.doi.org/10.11114/set.v4i1.2340.
Повний текст джерелаАнотація:
In recent years, Neural Network (NN) has gained popularity in proffering solution to complex nonlinear problems. Monitoring of variations in Petroleum Products Pipeline (PPP) attributes (flow rate, pressure, temperature, viscosity, density, inlet and outlet volume) which changes with time is complex due to existence of non linear interaction amongst the attributes. The existing works on PPP monitoring are limited by lack of capabilities for pattern recognition and learning from previous data. In this paper, NN models with pattern recognition and learning capabilities are compared with a view of selecting the best model for monitoring PPP. Data was collected from Pipelines and Products Marketing Company (PPMC), Port Harcourt, Nigeria. The data was used for NN training, validation and testing with different NN models such as Multilayer Perceptron (MLP), Radial Basis Function (RBF), Generalized Feed Forward (GFF), Support Vector Machine (SVM), Time Delay Network (TDN) and Recurrent Neural Network (RNN). Neuro Solutions 6.0 was used as the front-end-engine for NN training, validation and testing while My Structured Query Language (MySQL) database served as the back-end-engine. Performance of NN models was measured using Mean Squared Error (MSE), Mean Absolute Error (MAE), Correlation Coefficient (r), Akaike Information Criteria (AIC) and Minimum Descriptive Length (MDL). MLP with one hidden layer and three processing elements performed better than other NN models in terms of MSE, MAE, AIC, MDL and r values between the computed and the desired output.
35
Badea, Francisco, Jesus Angel Perez, and Jose Luis Olazagoitia. "Detailed Study on the Behavior of Improved Beam T-Junctions Modeling for the Characterization of Tubular Structures, Based on Artificial Neural Networks Trained with Finite Element Models." Mathematics 9, no. 9 (April 23, 2021): 943. http://dx.doi.org/10.3390/math9090943.
Повний текст джерелаАнотація:
The actual behavior of welded T-junctions in tubular structures depends strongly on the topology of the junction at the joint level. In finite element analysis, beam-type elements are usually employed due to their simplicity and low computational cost, even though they cannot reproduce the joints topologies and characteristics. To adjust their behavior to a more realistic situation, elastic elements can be introduced at the joint level, whose characteristics must be determined through costly validations. This paper studies the optimization and implementation of the validation data, through the creation of an optimal surrogate model based on neural networks, leading to a model that predicts the stiffness of elastic elements, introduced at the joint level based on available data. The paper focuses on how the neural network should be chosen, when training data is very limited and, more importantly, which of the available data should be used for training and which for verification. The methodology used is based on a Monte Carlo analysis that allows an exhaustive study of both the network parameters and the distribution and choice of the limited data in the training set to optimize its performance. The results obtained indicate that the use of neural networks without a careful methodology in this type of problems could lead to inaccurate results. It is also shown that a conscientious choice of training data, among the data available in the problem of choice of elastic parameters for T-junctions in finite elements, is fundamental to achieve functional surrogate models.
36
Li, Ling Yun, Yi Miao Lin, and Ji Wei Hu. "A Study on Pathway and QSPR Models for Debromination of PBDEs with Pseudopotential Method." Advanced Materials Research 997 (August 2014): 25–32. http://dx.doi.org/10.4028/www.scientific.net/amr.997.25.
Повний текст джерелаАнотація:
Neutral PBDEs congeners and their corresponding radical anions were studied with the pseudopotential method of stuttgart group (SDD) effective-core potentials basis set for the bromine atoms and the all-electron basis set for all other atoms. The pseudopotential method can be used for compounds containing heavy elements with relativistic effects and can reduce the computational time. The quantitative structure property relationship (QSPR) study was also performed in this work to develop models to predict the normolized reaction rate constants for the reductive debromination of polybrominated diphenyl ethers (PBDEs) by zero-valent iron (ZVI). The partial least squares regression (PLSR), principal component analysis-multiple linear regression analysis (PCA-MLR), and back propagation artificial neural network (BP-ANN) approaches were employed for the QSPR study between the molecular descriptors and the logarithm of normalized reaction rate constants of fourteen selected BDE congeners. The results show that the ANN models could be more satisfactorily to predict the rate constants than the PLSR and PCA-MLR models.
37
Tang, Yehui, Yunhe Wang, Yixing Xu, Boxin Shi, Chao Xu, Chunjing Xu, and Chang Xu. "Beyond Dropout: Feature Map Distortion to Regularize Deep Neural Networks." Proceedings of the AAAI Conference on Artificial Intelligence 34, no. 04 (April 3, 2020): 5964–71. http://dx.doi.org/10.1609/aaai.v34i04.6057.
Повний текст джерелаАнотація:
Deep neural networks often consist of a great number of trainable parameters for extracting powerful features from given datasets. One one hand, massive trainable parameters significantly enhance the performance of these deep networks. One the other hand, they bring the problem of over-fitting. To this end, dropout based methods disable some elements in the output feature maps during the training phase for reducing the co-adaptation of neurons. Although the generalization ability of the resulting models can be enhanced by these approaches, the conventional binary dropout is not the optimal solution. Therefore, we investigate the empirical Rademacher complexity related to intermediate layers of deep neural networks and propose a feature distortion method for addressing the aforementioned problem. In the training period, randomly selected elements in the feature maps will be replaced with specific values by exploiting the generalization error bound. The superiority of the proposed feature map distortion for producing deep neural network with higher testing performance is analyzed and demonstrated on several benchmark image datasets.
38
Abdelkader, Eslam Mohammed, Abobakr Al-Sakkaf, Nehal Elshaboury, and Ghasan Alfalah. "Hybrid Grey Wolf Optimization-Based Gaussian Process Regression Model for Simulating Deterioration Behavior of Highway Tunnel Components." Processes 10, no. 1 (December 24, 2021): 36. http://dx.doi.org/10.3390/pr10010036.
Повний текст джерелаАнотація:
Highway tunnels are one of the paramount infrastructure systems that affect the welfare of communities. They are vulnerable to higher limits of deterioration, yet there are limited available funds for maintenance and rehabilitation. This state of circumstances entails the development of a deterioration model to forecast the performance condition behavior of critical tunnel elements. Accordingly, this research paper proposes an integrated deterioration prediction model for five highway tunnel elements, namely, cast-in-place tunnel liners, concrete interior walls, concrete portal, concrete ceiling slab, and concrete slab on grade. The developed deterioration model is envisioned in two fundamental components, which are model calibration and model assessment. In the first component, an integrated model of Gaussian process regression and a grey wolf optimization algorithm (GWO-GPR) is introduced for deterioration behavior prediction of highway tunnel elements. In this regard, the grey wolf optimizer is exploited to improve the prediction accuracies of the Gaussian process through optimal estimation of its hyper parameters and to automatically interpret the significant deterioration factors. The second component involves three tiers of performance evaluation comparison, statistical significance comparisons, and consolidated ranking to assess the prediction accuracies of the developed GWO-GPR model. In this regard, the developed model is validated against six widely acknowledged machine learning models, which are back-propagation artificial neural network, Elman neural network, cascade forward neural network, generalized regression neural network, support vector machines, and regression tree. Results demonstrate that the developed GWO-GPR model significantly outperformed other deterioration prediction models in the five tunnel elements. In cast-in-place tunnel liners it accomplished a mean absolute percentage error, mean absolute error, root mean square percentage error, root relative squared error, and relative absolute error of 1.65%, 0.018, 0.21%, 0.018, and 0.147, respectively. In this context, it was inferred that the developed GWO-GPR model managed to reduce the prediction errors of the back-propagation artificial neural network, Elman neural network, and support vector machines by 84.71%, 76.91%, and 69.6%, respectively. It can be concluded that the developed deterioration model can assist transportation agencies in creating timely and cost-efficient maintenance schedules of highway tunnels.
39
van der Wolk, Pieter J., Jiajun Wang, Jilt Sietsma, and Sybrand van der Zwaag. "Modelling the continuous cooling transformation diagram of engineering steels using neural networks." International Journal of Materials Research 93, no. 12 (December 1, 2002): 1208–16. http://dx.doi.org/10.1515/ijmr-2002-0209.
Повний текст джерелаАнотація:
Abstract The neural network model of Van der Wolk et al. [1] describes the effect of composition on the phase regions of the continuous cooling transformation (CCT) diagram, yet does not consider the fractions of microstructural components and the hardness data that are often quoted in CCT diagrams. In the present paper, the construction of two more neural network models, one for the fractions of ferrite, pearlite, bainite and martensite in the microstructure, and one for the hardness after cooling, using the data of 338 and 412 diagrams, respectively. The accuracy of each model was found to be similar to the expected experimental error; moreover, the models were found to be mutually consistent, although they have been constructed independently. Furthermore, the trends in these properties for alloying elements can be quantified with the models, and are largely in line with metallurgical expectations.
40
LEWIS, JOHN E., and LEON GLASS. "STEADY STATES, LIMIT CYCLES, AND CHAOS IN MODELS OF COMPLEX BIOLOGICAL NETWORKS." International Journal of Bifurcation and Chaos 01, no. 02 (June 1991): 477–83. http://dx.doi.org/10.1142/s0218127491000373.
Повний текст джерелаАнотація:
Theoretical models of neural and genetic control networks consisting of N interacting elements are cast in the form of an N-dimensional system of piecewise linear (PL) ordinary differential equations. The state transition diagram of this system, which represents transitions between distinct volumes in the N-dimensional phase space, is given as a directed graph on an N-dimensional hypercube in which each edge has only one orientation. Analytical results establish steady-states and limit cycles in these systems, and numerical results have identified chaotic dynamics for N ≥ 6.
41
Rezaeva, M. A., and R. Y. Semendyaev. "Development and Application of Convolutional Neural Network for the Recognition of Objects in the Scheme of Electric Grid." Journal of Physics: Conference Series 2096, no. 1 (November 1, 2021): 012020. http://dx.doi.org/10.1088/1742-6596/2096/1/012020.
Повний текст джерелаАнотація:
Abstract One of the current design problems in the electric power industry is the labor intensity of synthesizing mathematical models to calculate the electrical modes of the network. It takes a lot of time to compose a detailed model of a large power system based on circuit diagram data. To simplify, speed up, and automate the data input, a convolutional neural network is proposed. In this paper the definition of convolutional neural network is given, its elements are described, the architecture of neural network is developed, the accuracy of its work on the schematic diagrams of various power systems is 0.84.
42
Smuga-Kogut, Małgorzata, Tomasz Kogut, Roksana Markiewicz, and Adam Słowik. "Use of Machine Learning Methods for Predicting Amount of Bioethanol Obtained from Lignocellulosic Biomass with the Use of Ionic Liquids for Pretreatment." Energies 14, no. 1 (January 5, 2021): 243. http://dx.doi.org/10.3390/en14010243.
Повний текст джерелаАнотація:
The study objective was to model and predict the bioethanol production process from lignocellulosic biomass based on an example of empirical study results. Two types of algorithms were used in machine learning: artificial neural network (ANN) and random forest algorithm (RF). Data for the model included results of studying bioethanol production with the use of ionic liquids (ILs) and different enzymatic preparations from the following biomass types: buckwheat straw and biomass from four wastelands, including a mixture of various plants: stems of giant miscanthus, common nettle, goldenrod, common broom, fireweed, and hay (a mix of grasses). The input variables consisted of different ionic liquids (imidazolium and ammonium), enzymatic preparations, enzyme doses, time and temperature of pretreatment, and type of yeast for alcoholic fermentation. The output value was the bioethanol concentration. The multilayer perceptron (MLP) was used in the artificial neural networks. Two model types were created; the training dataset comprised 120 vectors (14 elements for Model 1 and 11 elements for Model 2). Assessment of the optimum random forest was carried out using the same division of experimental points (two random datasets, containing 2/3 for training and 1/3 for testing) and the same criteria used for the artificial neural network models. Data for mugwort and hemp were used for validation. In both models, the coefficient of determination for neural networks was <0.9, while for RF it oscillated around 0.95. Considering the fairly large spread of the determination coefficient, two hybrid models were generated. The use of the hybrid approach in creating models describing the present bioethanol production process resulted in an increase in the fit of the model to R2 = 0.961. The hybrid model can be used for the initial classification of plants without the necessity to perform lengthy and expensive research related to IL-based pretreatment and further hydrolysis; only their lignocellulosic composition results are needed.
43
Abdel-Salam, Emad A. B., Mohamed I. Nouh, Yosry A. Azzam, and M. S. Jazmati. "Conformable Fractional Models of the Stellar Helium Burning via Artificial Neural Networks." Advances in Astronomy 2021 (March 16, 2021): 1–18. http://dx.doi.org/10.1155/2021/6662217.
Повний текст джерелаАнотація:
The helium burning phase represents the second stage that the star used to consume nuclear fuel in its interior. In this stage, the three elements, carbon, oxygen, and neon, are synthesized. The present paper is twofold: firstly, it develops an analytical solution to the system of the conformable fractional differential equations of the helium burning network, where we used, for this purpose, the series expansion method and obtained recurrence relations for the product abundances, that is, helium, carbon, oxygen, and neon. Using four different initial abundances, we calculated 44 gas models covering the range of the fractional parameterα=0.5−1with stepΔα=0.05. We found that the effects of the fractional parameter on the product abundances are small which coincides with the results obtained by a previous study. Secondly, we introduced the mathematical model of the neural network (NN) and developed a neural network algorithm to simulate the helium burning network using a feed-forward process. A comparison between the NN and the analytical models revealed very good agreement for all gas models. We found that NN could be considered as a powerful tool to solve and model nuclear burning networks and could be applied to the other nuclear stellar burning networks.
44
Mukhin, Dmitry, Evgeny Loskutov, Anna Mukhina, Alexander Feigin, Ilia Zaliapin, and Michael Ghil. "Predicting Critical Transitions in ENSO Models. Part I: Methodology and Simple Models with Memory." Journal of Climate 28, no. 5 (February 26, 2015): 1940–61. http://dx.doi.org/10.1175/jcli-d-14-00239.1.
Повний текст джерелаАнотація:
Abstract A new empirical approach is proposed for predicting critical transitions in the climate system based on a time series alone. This approach relies on nonlinear stochastic modeling of the system’s time-dependent evolution operator by the analysis of observed behavior. Empirical models that take the form of a discrete random dynamical system are constructed using artificial neural networks; these models include state-dependent stochastic components. To demonstrate the usefulness of such models in predicting critical climate transitions, they are applied here to time series generated by a number of delay-differential equation (DDE) models of sea surface temperature anomalies. These DDE models take into account the main conceptual elements responsible for the El Niño–Southern Oscillation phenomenon. The DDE models used here have been modified to include slow trends in the control parameters in such a way that critical transitions occur beyond the learning interval in the time series. Numerical results suggest that the empirical models proposed herein are able to forecast sequences of critical transitions that manifest themselves in future abrupt changes of the climate system’s statistics.
45
Vankov, Ivan I., and Jeffrey S. Bowers. "Training neural networks to encode symbols enables combinatorial generalization." Philosophical Transactions of the Royal Society B: Biological Sciences 375, no. 1791 (December 16, 2019): 20190309. http://dx.doi.org/10.1098/rstb.2019.0309.
Повний текст джерелаАнотація:
Combinatorial generalization—the ability to understand and produce novel combinations of already familiar elements—is considered to be a core capacity of the human mind and a major challenge to neural network models. A significant body of research suggests that conventional neural networks cannot solve this problem unless they are endowed with mechanisms specifically engineered for the purpose of representing symbols. In this paper, we introduce a novel way of representing symbolic structures in connectionist terms—the vectors approach to representing symbols (VARS), which allows training standard neural architectures to encode symbolic knowledge explicitly at their output layers. In two simulations, we show that neural networks not only can learn to produce VARS representations, but in doing so they achieve combinatorial generalization in their symbolic and non-symbolic output. This adds to other recent work that has shown improved combinatorial generalization under some training conditions, and raises the question of whether specific mechanisms or training routines are needed to support symbolic processing. This article is part of the theme issue ‘Towards mechanistic models of meaning composition’.
46
Ip, Y. T., M. Levine, and E. Bier. "Neurogenic expression of snail is controlled by separable CNS and PNS promoter elements." Development 120, no. 1 (January 1, 1994): 199–207. http://dx.doi.org/10.1242/dev.120.1.199.
Повний текст джерелаАнотація:
The Drosophila snail (sna) gene is first expressed in cells giving rise to mesoderm and is required for mesoderm formation. sna is subsequently expressed in the developing nervous system. sna expression during neurogenesis evolves from segmentally repeated neuroectodermal domains to a pan-neural pattern. We have identified a 2.8 kb regulatory region of the sna promoter that drives LacZ expression in a faithful neuronal pattern. Deletion analysis of this region indicates that the pan-neural element is composed of separable CNS and PNS components. This finding is unexpected since all known genes controlling early neurogenesis, including the proneural genes (i.e. da and AS-C), are expressed in both the CNS and PNS. We also show that expression of sna during neurogenesis is largely independent of the proneural genes da and AS-C. The separate control of CNS and PNS sna expression and independence of proneural gene regulation add to a growing body of evidence that current genetic models of neurogenesis are substantially incomplete.
47
Lei, Ao, Chuan-xue Song, Yu-long Lei, Yao Fu, and Shang Zheng. "Research on the Models of Coupling Dynamics and Damage Classification for Vehicle-Engine Vibration." Mathematical Problems in Engineering 2020 (March 31, 2020): 1–14. http://dx.doi.org/10.1155/2020/5907613.
Повний текст джерелаАнотація:
Many researchers have designed the dynamic models to study the vehicle-engine vibration. However, the existing mechanical models are relatively simple, and the analysis of engine vibration damage is discussed rarely. In this paper, we proposed the models of coupling dynamics and damage classification of vehicle-engine vibration. The key advantages of these proposed models are (1) the finite elements method is adopted for the rotor and casing system, and the complex structure with multirotor and multicasing is modeled by defining support system and linking methods; (2) the hybrid numerical integral method is used to obtain the inherent frequency of the nonlinear dynamic system; and (3) the algorithms based on backpropagation (BP) neural network and radial basis function (RBF) neural network are chosen to construct the damage classification model of rotors. Experimental results based on the engine rotor tester prove that the proposed models are not only more robust than the existing works but also show that the classification algorithms can support engine damage analysis effectively.
48
Liu, Jianli, Edwin Lughofer, and Xianyi Zeng. "Toward Model Building for Visual Aesthetic Perception." Computational Intelligence and Neuroscience 2017 (2017): 1–13. http://dx.doi.org/10.1155/2017/1292801.
Повний текст джерелаАнотація:
Several models of visual aesthetic perception have been proposed in recent years. Such models have drawn on investigations into the neural underpinnings of visual aesthetics, utilizing neurophysiological techniques and brain imaging techniques including functional magnetic resonance imaging, magnetoencephalography, and electroencephalography. The neural mechanisms underlying the aesthetic perception of the visual arts have been explained from the perspectives of neuropsychology, brain and cognitive science, informatics, and statistics. Although corresponding models have been constructed, the majority of these models contain elements that are difficult to be simulated or quantified using simple mathematical functions. In this review, we discuss the hypotheses, conceptions, and structures of six typical models for human aesthetic appreciation in the visual domain: the neuropsychological, information processing, mirror, quartet, and two hierarchical feed-forward layered models. Additionally, the neural foundation of aesthetic perception, appreciation, or judgement for each model is summarized. The development of a unified framework for the neurobiological mechanisms underlying the aesthetic perception of visual art and the validation of this framework via mathematical simulation is an interesting challenge in neuroaesthetics research. This review aims to provide information regarding the most promising proposals for bridging the gap between visual information processing and brain activity involved in aesthetic appreciation.
49
Wai Yong, Ching, Kareen Teo, Belinda Pingguan Murphy, Yan Chai Hum, and Khin Wee Lai. "CORSegNet: Deep Neural Network for Core Object Segmentation on Medical Images." Journal of Medical Imaging and Health Informatics 11, no. 5 (May 1, 2021): 1364–71. http://dx.doi.org/10.1166/jmihi.2021.3380.
Повний текст джерелаАнотація:
In recent decades, convolutional neural networks (CNNs) have delivered promising results in vision-related tasks across different domains. Previous studies have introduced deeper network architectures to further improve the performances of object classification, localization, and segmentation. However, this induces the complexity in mapping network’s layer to the processing elements in the ventral visual pathway. Although CORnet models are not precisely biomimetic, they are closer approximations to the anatomy of ventral visual pathway compared with other deep neural networks. The uniqueness of this architecture inspires us to extend it into a core object segmentation network, CORSegnet-Z. This architecture utilizes CORnet-Z building blocks as the encoding elements. We train and evaluate the proposed model using two large datasets. Our proposed model shows significant improvements on the segmentation metrics in delineating cartilage tissues from knee magnetic resonance (MR) images and segmenting lesion boundary from dermoscopic images.
50
Roemer, M. J., C. Hong, and S. H. Hesler. "Machine Health Monitoring and Life Management Using Finite-Element-Based Neural Networks." Journal of Engineering for Gas Turbines and Power 118, no. 4 (October 1, 1996): 830–35. http://dx.doi.org/10.1115/1.2817002.
Повний текст джерелаАнотація:
This paper demonstrates a novel approach to condition-based health monitoring for rotating machinery using recent advances in neural network technology and rotordynamic, finite-element modeling. A desktop rotor demonstration rig was used as a proof of concept tool. The approach integrates machinery sensor measurements with detailed, rotordynamic, finite-element models through a neural network that is specifically trained to respond to the machine being monitored. The advantage of this approach over current methods lies in the use of an advanced neural network. The neural network is trained to contain the knowledge of a detailed finite-element model whose results are integrated with system measurements to produce accurate machine fault diagnostics and component stress predictions. This technique takes advantage of recent advances in neural network technology that enable real-time machinery diagnostics and component stress prediction to be performed on a PC with the accuracy of finite-element analysis. The availability of the real-time, finite-element-based knowledge on rotating elements allows for real-time component life prediction as well as accurate and fast fault diagnosis.