Relevant bibliographies by topics / Generalization performance evaluation

Academic literature on the topic 'Generalization performance evaluation'

Author: Grafiati
Published: 10 December 2022
Last updated: 28 January 2023

Create a spot-on reference in APA, MLA, Chicago, Harvard, and other styles

Select a source type:

Contents

Consult the lists of relevant articles, books, theses, conference reports, and other scholarly sources on the topic 'Generalization performance evaluation.'

Next to every source in the list of references, there is an 'Add to bibliography' button. Press on it, and we will generate automatically the bibliographic reference to the chosen work in the citation style you need: APA, MLA, Harvard, Chicago, Vancouver, etc.

You can also download the full text of the academic publication as pdf and read online its abstract whenever available in the metadata.

Journal articles on the topic "Generalization performance evaluation"

1

Shi, Wenzhong, and ChuiKwan Cheung. "Performance Evaluation of Line Simplification Algorithms for Vector Generalization." Cartographic Journal 43, no. 1 (March 1, 2006): 27–44. http://dx.doi.org/10.1179/000870406x93490.

Full text
APA, Harvard, Vancouver, ISO, and other styles
2

Alwakeel, Ahmed, Mohammed Alwakeel, Mohammad Hijji, Tausifa Jan Saleem, and Syed Rameem Zahra. "Performance Evaluation of Different Decision Fusion Approaches for Image Classification." Applied Sciences 13, no. 2 (January 15, 2023): 1168. http://dx.doi.org/10.3390/app13021168.

Full text
Abstract:
Image classification is one of the major data mining tasks in smart city applications. However, deploying classification models that have good generalization accuracy is highly crucial for reliable decision-making in such applications. One of the ways to achieve good generalization accuracy is through the use of multiple classifiers and the fusion of their decisions. This approach is known as “decision fusion”. The requirement for achieving good results with decision fusion is that there should be dissimilarity between the outputs of the classifiers. This paper proposes and evaluates two ways of attaining the aforementioned dissimilarity. One is using dissimilar classifiers with different architectures, and the other is using similar classifiers with similar architectures but trained with different batch sizes. The paper also compares a number of decision fusion strategies.
APA, Harvard, Vancouver, ISO, and other styles
3

Alexander, Melina, Ben Lignugaris/Kraft, and David Forbush. "Online Mathematics Methods Course Evaluation: Student Outcomes, Generalization, and Pupil Performance." Teacher Education and Special Education: The Journal of the Teacher Education Division of the Council for Exceptional Children 30, no. 4 (October 2007): 199–216. http://dx.doi.org/10.1177/088840640703000401.

Full text
APA, Harvard, Vancouver, ISO, and other styles
4

Emmert-Streib, Frank, and Matthias Dehmer. "Evaluation of Regression Models: Model Assessment, Model Selection and Generalization Error." Machine Learning and Knowledge Extraction 1, no. 1 (March 22, 2019): 521–51. http://dx.doi.org/10.3390/make1010032.

Full text
Abstract:
When performing a regression or classification analysis, one needs to specify a statistical model. This model should avoid the overfitting and underfitting of data, and achieve a low generalization error that characterizes its prediction performance. In order to identify such a model, one needs to decide which model to select from candidate model families based on performance evaluations. In this paper, we review the theoretical framework of model selection and model assessment, including error-complexity curves, the bias-variance tradeoff, and learning curves for evaluating statistical models. We discuss criterion-based, step-wise selection procedures and resampling methods for model selection, whereas cross-validation provides the most simple and generic means for computationally estimating all required entities. To make the theoretical concepts transparent, we present worked examples for linear regression models. However, our conceptual presentation is extensible to more general models, as well as classification problems.
APA, Harvard, Vancouver, ISO, and other styles
5

Gülci, Sercan, Hafiz Hulusi Acar, Abdullah E. Akay, and Neşe Gülci. "Evaluation of Automatic Prediction of Small Horizontal Curve Attributes of Mountain Roads in GIS Environments." ISPRS International Journal of Geo-Information 11, no. 11 (November 9, 2022): 560. http://dx.doi.org/10.3390/ijgi11110560.

Full text
Abstract:
Road curve attributes can be determined by using Geographic Information System (GIS) to be used in road vehicle traffic safety and planning studies. This study involves analyzing the GIS-based estimation accuracy in the length, radius and the number of small horizontal road curves on a two-lane rural road and a forest road. The prediction success of horizontal curve attributes was investigated using digitized raw and generalized/simplified road segments. Two different roads were examined, involving 20 test groups and two control groups, using 22 datasets obtained from digitized and surveyed roads based on satellite imagery, GIS estimates, and field measurements. Confusion matrix tables were also used to evaluate the prediction accuracy of horizontal curve geometry. F-score, Mathews Correlation Coefficient, Bookmaker Informedness and Balanced Accuracy were used to investigate the performance of test groups. The Kruskal–Wallis test was used to analyze the statistical relationships between the data. Compared to the Bezier generalization algorithm, the Douglas–Peucker algorithm showed the most accurate horizontal curve predictions at generalization tolerances of 0.8 m and 1 m. The results show that the generalization tolerance level contributes to the prediction accuracy of the number, curve radius, and length of the horizontal curves, which vary with the tolerance value. Thus, this study underlined the importance of calculating generalizations and tolerances following a manual road digitization.
APA, Harvard, Vancouver, ISO, and other styles
6

Ferreira, Diogo Cunha, and Rui Cunha Marques. "Malmquist and Hicks–Moorsteen Productivity Indexes for Clusters Performance Evaluation." International Journal of Information Technology & Decision Making 15, no. 05 (September 2016): 1015–53. http://dx.doi.org/10.1142/s0219622016500243.

Full text
Abstract:
Measuring the performance of clusters characterized by the unbalancedeness and units with no correspondence in other clusters (“uncorrespondencedeness”) has not achieved the desired attention in the literature. Particularly, the operational research has been almost exclusively focused on performance evolution over time, where clusters are generally balanced and the units repeat themselves over these groups. Such analysis has been based on the Malmquist and the Hicks–Moorsteen indexes (MI and HMI), which are solely based on Shephard’s radial distance functions and do not account for all inefficiency sources. Making use of the so-called geometric distance functions (GDFs) and the GDF-based MI, we propose a generalization of the Hicks–Moorsteen index (HMI), based on targets instead of distances to the efficient frontier, allowing the introduction of all inefficiency sources in the productivity model. Moreover, we propose a Monte Carlo-based framework to achieve the pseudo-corresponding units for general cluster performance analysis. This framework is then a generalization of the conventional performance evolution over time. Then, we show that the HMI can be decomposed into economically meaningful indexes and can be rewritten as the geometric mean of the input and the output-oriented MIs. Given these conclusions and our proposed framework, the employment of the HMI to the general clusters analysis is straightforward. Other economically meaningful conclusions are also obtained in this paper.
APA, Harvard, Vancouver, ISO, and other styles
7

Huang, Ke Wang. "Experimental Study of FPCA on its Generalization Performance in Image Classification." Applied Mechanics and Materials 496-500 (January 2014): 2299–302. http://dx.doi.org/10.4028/www.scientific.net/amm.496-500.2299.

Full text
Abstract:
The theoretical study of FPCA shows that FPCA algorithm has better generalization performance than existing PCA and its extended algorithms. But this theoretic conclusion was not confirmed by existing experimental results because of the problems of evaluation criterion. Introducing the idea of clustering performance criterion of LDA, we proposed a general performance metrics for PCA and performed numbers of experimental studies to compare FPCA with existing PCA and its extended algorithms by using our metrics. We found in the feature extraction of image samples that FPCA really has better generalization performance than existing PCA and its extended algorithms under the condition of large sample size. The results confirmed theoretical conclusion of FPCA and improved relevant experimental study.
APA, Harvard, Vancouver, ISO, and other styles
8

Ahmad, Muhammad, Manuel Mazzara, and Salvatore Distefano. "Regularized CNN Feature Hierarchy for Hyperspectral Image Classification." Remote Sensing 13, no. 12 (June 10, 2021): 2275. http://dx.doi.org/10.3390/rs13122275.

Full text
Abstract:
Convolutional Neural Networks (CNN) have been rigorously studied for Hyperspectral Image Classification (HSIC) and are known to be effective in exploiting joint spatial-spectral information with the expense of lower generalization performance and learning speed due to the hard labels and non-uniform distribution over labels. Therefore, this paper proposed an idea to enhance the generalization performance of CNN for HSIC using soft labels that are a weighted average of the hard labels and uniform distribution over ground labels. The proposed method helps to prevent CNN from becoming over-confident. We empirically show that, in improving generalization performance, regularization also improves model calibration, which significantly improves beam-search. Several publicly available Hyperspectral datasets are used to validate the experimental evaluation, which reveals improved performance as compared to the state-of-the-art models with overall 99.29%, 99.97%, and 100.0% accuracy for Indiana Pines, Pavia University, and Salinas dataset, respectively.
APA, Harvard, Vancouver, ISO, and other styles
9

Zhang, Dong Sheng. "Generalization Privacy Protection Method for Alarm Data." Applied Mechanics and Materials 543-547 (March 2014): 3646–49. http://dx.doi.org/10.4028/www.scientific.net/amm.543-547.3646.

Full text
Abstract:
To resolve conflicts between share and collaborative analysis requirements of security alarm and alert data holders worries about privacy, it firstly probes into the anonymized protection method Incognito. Based on that, it improves the algorithm to solve existing problems by extending common data like privacy protection targets to alert data. The generalized anonymous processing model for alert data is developed and the quantitative evaluation is realized between the level of alert datas secret protection and data quality. With authoritative data set of intrusion detection attack scenario as test data, the experiment validates efficiency and effectiveness of the proposed method on the part of performance and security.
APA, Harvard, Vancouver, ISO, and other styles
10

Huang, Felix C., James L. Patton, and Ferdinando A. Mussa-Ivaldi. "Manual Skill Generalization Enhanced by Negative Viscosity." Journal of Neurophysiology 104, no. 4 (October 2010): 2008–19. http://dx.doi.org/10.1152/jn.00433.2009.

Full text
Abstract:
Recent human-machine interaction studies have suggested that movement augmented with negative viscosity can enhance performance and can even promote better motor learning. To test this, we investigated how negative viscosity influences motor adaptation to an environment where forces acted only in one axis of motion. Using a force-feedback device, subjects performed free exploratory movements with a purely inertia generating forces proportional to hand acceleration, negative viscosity generating destabilizing forces proportional to hand velocity, or a combination of the acceleration and velocity fields. After training, we evaluated each subject's ability to perform circular movements in only the inertial field. Combined training resulted in lowest error and revealed similar responses as inertia training in catch trials. These findings are remarkable because negative viscosity, available only during training, evidently enhanced learning when combined with inertia. This success in generalization is consistent with the ability of the nervous system to decompose the perturbing forces into velocity and acceleration dependent components. Compared with inertia, the combined group exhibited a broader range of speeds along the direction of maximal perturbing force. Broader exploration was also correlated with better performance in subsequent evaluation trials; this suggests that negative viscosity improved performance by enhancing identification of each force field. These findings shed light on a new way to enhance sensorimotor adaptation through robot-applied augmentation of mechanics.
APA, Harvard, Vancouver, ISO, and other styles
More sources

Book chapters on the topic "Generalization performance evaluation"

1

More, Shammi, Simon B. Eickhoff, Julian Caspers, and Kaustubh R. Patil. "Confound Removal and Normalization in Practice: A Neuroimaging Based Sex Prediction Case Study." In Machine Learning and Knowledge Discovery in Databases. Applied Data Science and Demo Track, 3–18. Cham: Springer International Publishing, 2021. http://dx.doi.org/10.1007/978-3-030-67670-4_1.

Full text
Abstract:
AbstractMachine learning (ML) methods are increasingly being used to predict pathologies and biological traits using neuroimaging data. Here controlling for confounds is essential to get unbiased estimates of generalization performance and to identify the features driving predictions. However, a systematic evaluation of the advantages and disadvantages of available alternatives is lacking. This makes it difficult to compare results across studies and to build deployment quality models. Here, we evaluated two commonly used confound removal schemes–whole data confound regression (WDCR) and cross-validated confound regression (CVCR)–to understand their effectiveness and biases induced in generalization performance estimation. Additionally, we study the interaction of the confound removal schemes with Z-score normalization, a common practice in ML modelling. We applied eight combinations of confound removal schemes and normalization (pipelines) to decode sex from resting-state functional MRI (rfMRI) data while controlling for two confounds, brain size and age. We show that both schemes effectively remove linear univariate and multivariate confounding effects resulting in reduced model performance with CVCR providing better generalization estimates, i.e., closer to out-of-sample performance than WDCR. We found no effect of normalizing before or after confound removal. In the presence of dataset and confound shift, four tested confound removal procedures yielded mixed results, raising new questions. We conclude that CVCR is a better method to control for confounding effects in neuroimaging studies. We believe that our in-depth analyses shed light on choices associated with confound removal and hope that it generates more interest in this problem instrumental to numerous applications.
APA, Harvard, Vancouver, ISO, and other styles
2

Theis, Julian, Ilia Mokhtarian, and Houshang Darabi. "On the Performance Analysis of the Adversarial System Variant Approximation Method to Quantify Process Model Generalization." In Lecture Notes in Business Information Processing, 281–93. Cham: Springer International Publishing, 2022. http://dx.doi.org/10.1007/978-3-030-98581-3_21.

Full text
Abstract:
AbstractProcess mining algorithms discover a process model from an event log. The resulting process model is supposed to describe all possible event sequences of the underlying system. Generalization is a process model quality dimension of interest. A generalization metric should quantify the extent to which a process model represents the observed event sequences contained in the event log and the unobserved event sequences of the system. Most of the available metrics in the literature cannot properly quantify the generalization of a process model. A recently published method called Adversarial System Variant Approximation leverages Generative Adversarial Networks to approximate the underlying event sequence distribution of a system from an event log. While this method demonstrated performance gains over existing methods in measuring the generalization of process models, its experimental evaluations have been performed under ideal conditions. This paper experimentally investigates the performance of Adversarial System Variant Approximation under non-ideal conditions such as biased and limited event logs. Moreover, experiments are performed to investigate the originally proposed sampling parameter value of the method on its performance to measure the generalization. The results confirm the need to raise awareness about the working conditions of the Adversarial System Variant Approximation method and serve to initiate future research directions.
APA, Harvard, Vancouver, ISO, and other styles
3

Li, Zhuowei, Amitabha Das, and Jianying Zhou. "Evaluating the Effects of Model Generalization on Intrusion Detection Performance." In New Approaches for Security, Privacy and Trust in Complex Environments, 421–32. Boston, MA: Springer US, 2007. http://dx.doi.org/10.1007/978-0-387-72367-9_36.

Full text
APA, Harvard, Vancouver, ISO, and other styles
4

Sokolova, Natalia, Klaus Schoeffmann, Mario Taschwer, Doris Putzgruber-Adamitsch, and Yosuf El-Shabrawi. "Evaluating the Generalization Performance of Instrument Classification in Cataract Surgery Videos." In MultiMedia Modeling, 626–36. Cham: Springer International Publishing, 2019. http://dx.doi.org/10.1007/978-3-030-37734-2_51.

Full text
APA, Harvard, Vancouver, ISO, and other styles
5

"A Generalization of a TCP Model: Multiple Source-Destination Case with Arbitrary LAN as the Access Network." In System Performance Evaluation, 55–66. CRC Press, 2000. http://dx.doi.org/10.1201/9781482274530-8.

Full text
APA, Harvard, Vancouver, ISO, and other styles
6

Antonanzas-Torres, Fernando, Andres Sanz-Garcia, Javier Antonanzas-Torres, Oscar Perpiñán-Lamiguero, and Francisco Javier Martínez-de-Pisón-Ascacibar. "Current Status and Future Trends of the Evaluation of Solar Global Irradiation using Soft-Computing-Based Models." In Advances in Environmental Engineering and Green Technologies, 1–22. IGI Global, 2015. http://dx.doi.org/10.4018/978-1-4666-6631-3.ch001.

Full text
Abstract:
Most of the research on estimating Solar Global Irradiation (SGI) is based on the development of parametric models. However, the use of methods based on the use of statistics and machine-learning theories can provide a significant improvement in reducing the prediction errors. The chapter evaluates the performance of different Soft Computing (SC) methods, such as support vector regression and artificial neural networks-multilayer perceptron, in SGI modeling against classical parametric and lineal models. SC methods demonstrate a higher generalization capacity applied to SGI modeling than classic parametric models. As a result, SC models suppose an alternative to satellite-derived models to estimate SGI in near-to-present time in areas in which no pyranometers are installed nearby.
APA, Harvard, Vancouver, ISO, and other styles
7

Nayak, Sarat Chandra, Bijan Bihari Misra, and Himansu Sekhar Behera. "On Developing and Performance Evaluation of Adaptive Second Order Neural Network With GA-Based Training (ASONN-GA) for Financial Time Series Prediction." In Advancements in Applied Metaheuristic Computing, 231–63. IGI Global, 2018. http://dx.doi.org/10.4018/978-1-5225-4151-6.ch010.

Full text
Abstract:
Financial time series forecasting has been regarded as a challenging issue because of successful prediction could yield significant profit, hence require an efficient prediction system. Conventional ANN based models are not competent systems. Higher order neural networks have several advantages over traditional neural networks such as stronger approximation, higher fault tolerance capacity and faster convergence. With the aim of achieving improved forecasting accuracy, this article develops and evaluates the performance of an adaptive single layer second order neural network with GA based training (ASONN-GA). The global search ability of GA has been incorporated with the better generalization ability of a second order neural network and the model is found quite capable in handling the uncertainties and nonlinearities associated with the financial time series. The model takes minimal input data and considered the partially optimized weight set from previous training, hence a significant reduction in training time. The efficiency of the model has been evaluated by forecasting one-step-ahead closing prices and exchange rates of five real stock markets and it is revealed that the ASONN-GA model achieves better forecasting accuracy over other state of the art models.
APA, Harvard, Vancouver, ISO, and other styles
8

Yauri, José, Aura Hernández-Sabaté, Paul Folch, and Débora Gil. "Mental Workload Detection Based on EEG Analysis." In Frontiers in Artificial Intelligence and Applications. IOS Press, 2021. http://dx.doi.org/10.3233/faia210144.

Full text
Abstract:
The study of mental workload becomes essential for human work efficiency, health conditions and to avoid accidents, since workload compromises both performance and awareness. Although workload has been widely studied using several physiological measures, minimising the sensor network as much as possible remains both a challenge and a requirement. Electroencephalogram (EEG) signals have shown a high correlation to specific cognitive and mental states like workload. However, there is not enough evidence in the literature to validate how well models generalize in case of new subjects performing tasks of a workload similar to the ones included during model’s training. In this paper we propose a binary neural network to classify EEG features across different mental workloads. Two workloads, low and medium, are induced using two variants of the N-Back Test. The proposed model was validated in a dataset collected from 16 subjects and shown a high level of generalization capability: model reported an average recall of 81.81% in a leave-one-out subject evaluation.
APA, Harvard, Vancouver, ISO, and other styles
9

Yauri, José, Aura Hernández-Sabaté, Paul Folch, and Débora Gil. "Mental Workload Detection Based on EEG Analysis." In Frontiers in Artificial Intelligence and Applications. IOS Press, 2021. http://dx.doi.org/10.3233/faia210144.

Full text
Abstract:
The study of mental workload becomes essential for human work efficiency, health conditions and to avoid accidents, since workload compromises both performance and awareness. Although workload has been widely studied using several physiological measures, minimising the sensor network as much as possible remains both a challenge and a requirement. Electroencephalogram (EEG) signals have shown a high correlation to specific cognitive and mental states like workload. However, there is not enough evidence in the literature to validate how well models generalize in case of new subjects performing tasks of a workload similar to the ones included during model’s training. In this paper we propose a binary neural network to classify EEG features across different mental workloads. Two workloads, low and medium, are induced using two variants of the N-Back Test. The proposed model was validated in a dataset collected from 16 subjects and shown a high level of generalization capability: model reported an average recall of 81.81% in a leave-one-out subject evaluation.
APA, Harvard, Vancouver, ISO, and other styles
10

Das, Raja, and M. K. Pradhan. "Artificial Neural Network Modeling for Electrical Discharge Machining Parameters." In Advances in Secure Computing, Internet Services, and Applications, 281–302. IGI Global, 2014. http://dx.doi.org/10.4018/978-1-4666-4940-8.ch014.

Full text
Abstract:
The objective of the chapter is to present the application of Artificial Neural Network (ANN) modelling of the Electrical Discharge Machining (EDM) process. It establishes the best ANN model by comparing the prediction from different models under the effect of process parameters. In EDM, the motivation is frequently to get better Material Removal Rate (MRR) with fulfilling better surface quality of machined components. The vital requirements are as small a radial overcut with minimal tool wear rate. The quality of a machined surface is very important to fulfilling the growing demands of higher component performance, durability, and reliability. To improve the reliability of the machine component, it is necessary to have in depth knowledge of the effect of parameters on the aforesaid responses of the components. An extensive chain of experiments has been conducted over a wide range of input parameters, using the full factorial design. More than 150 experiments have been conducted on AISI D2 work piece materials using copper electrodes to get the data for training and testing. The additional experiments were obtained to validate the model predictions. The performance of three neural network models is discussed in the evaluation of the generalization ability of the trained neural network. It was observed that the artificial neural network models could predict the process performance with reasonable accuracy, under varying machining conditions.
APA, Harvard, Vancouver, ISO, and other styles

Conference papers on the topic "Generalization performance evaluation"

1

Elangovan, Aparna, Jiayuan He, and Karin Verspoor. "Memorization vs. Generalization : Quantifying Data Leakage in NLP Performance Evaluation." In Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics: Main Volume. Stroudsburg, PA, USA: Association for Computational Linguistics, 2021. http://dx.doi.org/10.18653/v1/2021.eacl-main.113.

Full text
APA, Harvard, Vancouver, ISO, and other styles
2

Komninelli, Foteini, Athanasios Iliopoulos, and John G. Michopoulos. "Performance of a Lotka-Volterra System for Representing Biofouling Processes." In ASME 2014 International Design Engineering Technical Conferences and Computers and Information in Engineering Conference. American Society of Mechanical Engineers, 2014. http://dx.doi.org/10.1115/detc2014-35002.

Full text
Abstract:
In order to assess the feasibility and performance of a minimal multiphysics model for representing the spatiotemporal evolution of biofouling process, we selected the coupled diffusive generalization of the Lotka-Volterra PDEs to govern the spatiotemporal evolution of population densities of predator-prey colonies in a computational domain. The implementation of the finite element solution of the system was performed and the associated numerical solution of the system was achieved. An analysis was performed that highlights certain choices of the control parameters of the model and their effect on the spatiotemporal behavior of the system. Potential extensions of the model are presented to incorporate an agent that inhibits antibiofouling and study its effect. An evaluation of the features of the model are concluding the paper.
APA, Harvard, Vancouver, ISO, and other styles
3

Yang, Zhengyu, Kan Ren, Xufang Luo, Minghuan Liu, Weiqing Liu, Jiang Bian, Weinan Zhang, and Dongsheng Li. "Towards Applicable Reinforcement Learning: Improving the Generalization and Sample Efficiency with Policy Ensemble." In Thirty-First International Joint Conference on Artificial Intelligence {IJCAI-22}. California: International Joint Conferences on Artificial Intelligence Organization, 2022. http://dx.doi.org/10.24963/ijcai.2022/508.

Full text
Abstract:
It is challenging for reinforcement learning (RL) algorithms to succeed in real-world applications. Take financial trading as an example, the market information is noisy yet imperfect and the macroeconomic regulation or other factors may shift between training and evaluation, thus it requires both generalization and high sample efficiency for resolving the task. However, directly applying typical RL algorithms can lead to poor performance in such scenarios. To derive a robust and applicable RL algorithm, in this work, we design a simple but effective method named Ensemble Proximal Policy Optimization (EPPO), which learns ensemble policies in an end-to-end manner. Notably, EPPO combines each policy and the policy ensemble organically and optimizes both simultaneously. In addition, EPPO adopts a diversity enhancement regularization over the policy space which helps to generalize to unseen states and promotes exploration. We theoretically prove that EPPO can increase exploration efficacy, and through comprehensive experimental evaluations on various tasks, we demonstrate that EPPO achieves higher efficiency and is robust for real-world applications compared with vanilla policy optimization algorithms and other ensemble methods. Code and supplemental materials are available at https://seqml.github.io/eppo.
APA, Harvard, Vancouver, ISO, and other styles
4

Juliani, Arthur, Ahmed Khalifa, Vincent-Pierre Berges, Jonathan Harper, Ervin Teng, Hunter Henry, Adam Crespi, Julian Togelius, and Danny Lange. "Obstacle Tower: A Generalization Challenge in Vision, Control, and Planning." In Twenty-Eighth International Joint Conference on Artificial Intelligence {IJCAI-19}. California: International Joint Conferences on Artificial Intelligence Organization, 2019. http://dx.doi.org/10.24963/ijcai.2019/373.

Full text
Abstract:
The rapid pace of recent research in AI has been driven in part by the presence of fast and challenging simulation environments. These environments often take the form of games; with tasks ranging from simple board games, to competitive video games. We propose a new benchmark - Obstacle Tower: a high fidelity, 3D, 3rd person, procedurally generated environment. An agent in Obstacle Tower must learn to solve both low-level control and high-level planning problems in tandem while learning from pixels and a sparse reward signal. Unlike other benchmarks such as the Arcade Learning Environment, evaluation of agent performance in Obstacle Tower is based on an agent's ability to perform well on unseen instances of the environment. In this paper we outline the environment and provide a set of baseline results produced by current state-of-the-art Deep RL methods as well as human players. These algorithms fail to produce agents capable of performing near human level.
APA, Harvard, Vancouver, ISO, and other styles
5

McDonald, Dale B. "Locally Precise Response Surface Models for the Generalization of Controlled Dynamic Systems and Associated Performance Measures." In ASME 2013 International Mechanical Engineering Congress and Exposition. American Society of Mechanical Engineers, 2013. http://dx.doi.org/10.1115/imece2013-62099.

Full text
Abstract:
This treatment demonstrates the utility of response surface models (RSMs) as predictive, companion tools which aid in the development of harvesting (control) strategies applicable to predator-prey dynamic systems. To this end a control algorithm is derived that considers the regulation of a predator-prey natural resource while considering revenue for commercial ventures and regulatory agencies. Numerical simulations provide the mechanism to quantify performance measures associated with control algorithms, yet complicated problems require that all “tools” available be considered. Complex problems may be more tractable when simulation results are combined with alternate, continuous models exhibiting predictive capacities. For this reason, RSMs are appealing; analytic evaluation of the state, the gradient, and the Hessian matrix is possible. From these models we may glean valuable information linked to the gathered data revealing information about the “true nature” of the ecological system. Therefore, we propose to create RSMs based on scattered data obtained from the ordinary differential equation (ODE) dynamic system model. These response surface models are constructed using radial basis functions (RBFs); RSMs so created have the desirable property of matching the objective function value exactly at each sampled data point. Furthermore, they have the ability to interpolate to any desired point throughout the parameter space. This is powerful as the “objective function” may be any function of critical importance to the analyst which in this treatment is the predator biomass time rate of change (ODE) itself. This has the immediate implication of providing a single ODE model, with a “locally” or even perhaps a “globally” precise nature. Since such models are constructed from scattered data, which is consistent with what would be collected from field measurements, a further connection of theory to practice is realized. It will be shown that these RSMs provide greater insight into ecological systems, with special emphasis on parameter estimation.
APA, Harvard, Vancouver, ISO, and other styles
6

Simpson, Z., N. Janse van Rensburg, and M. van Ryneveld. "Developing Students as Higher-Order Thinkers: Analyzing Student Performance Against Levels of Cognitive Demand in a Material Science Course." In ASME 2010 International Mechanical Engineering Congress and Exposition. ASMEDC, 2010. http://dx.doi.org/10.1115/imece2010-37652.

Full text
Abstract:
Today’s increasingly complex engineering workplace demands skill in evaluation, reasoning and critical thinking; however, engineering curricula often test lower-order learning at the expense of higher-order reasoning. This paper analyzes the level of cognitive demand in a course on Material Science in the Department of Mechanical Engineering Science at the University of Johannesburg, South Africa. This is done by applying Biggs’ SOLO taxonomy to classify test and exam questions in the course and then analyzing student performance against this taxonomy of higher- and lower-order learning. The results demonstrate that many students battle with questions that require extended abstract reasoning (argument, evaluation, hypothesizing and generalization). Similarly, relational thinking (through comparison, contrast, application and so on) proves to be a significant problem for weaker students. The paper recommends that engineering lecturers build higher-order thinking into course outcomes, teaching and assessment and that engineering qualifications work systematically towards developing students as higher-order thinkers.
APA, Harvard, Vancouver, ISO, and other styles
7

HU, XIAOYI, YUNJIAN JING, ZHIKUN SONG, and LICHENG XU. "STUDY ON FAULT DIAGNOSIS FOR AXLEBOX BEARING OF HIGH SPEED EMU BASED ON CONVOLUTIONAL NEURAL NETWORK." In 3rd International Workshop on Structural Health Monitoring for Railway System (IWSHM-RS 2021). Destech Publications, Inc., 2021. http://dx.doi.org/10.12783/iwshm-rs2021/36020.

Full text
Abstract:
Considering that the traditional intelligent diagnosis methods rely too much on signal processing and expert experience to extract fault features and poor model generalization ability, based on deep learning theory, a convolutional neural network algorithm combined with Softmax classifier is proposed to construct deep convolutional neural network model suitable for fault diagnosis for axlebox bearings of high speed EMU. The model convolutions layer by layer from the measured axlebox vibration signals of high speed trains to achieve adaptive feature extraction and fault recognition. The introduction of batch normalization, regularization and Dropout processing effectively improves the model's recognition accuracy and generalization ability. The experimental results show that the optimized deep learning model can accurately extract fault features, realize accurate recognition of single faults and compound faults, and can maintain better recognition performance on unbalanced data sets, and performance evaluation based on statistical indicators. The superiority of model classification performance is also proved in this paper.
APA, Harvard, Vancouver, ISO, and other styles
8

Rahman, Tahrima, Shasha Jin, and Vibhav Gogate. "Cutset Bayesian Networks: A New Representation for Learning Rao-Blackwellised Graphical Models." In Twenty-Eighth International Joint Conference on Artificial Intelligence {IJCAI-19}. California: International Joint Conferences on Artificial Intelligence Organization, 2019. http://dx.doi.org/10.24963/ijcai.2019/797.

Full text
Abstract:
Recently there has been growing interest in learning probabilistic models that admit poly-time inference called tractable probabilistic models from data. Although they generalize poorly as compared to intractable models, they often yield more accurate estimates at prediction time. In this paper, we seek to further explore this trade-off between generalization performance and inference accuracy by proposing a novel, partially tractable representation called cutset Bayesian networks (CBNs). The main idea in CBNs is to partition the variables into two subsets X and Y, learn a (intractable) Bayesian network that represents P(X) and a tractable conditional model that represents P(Y|X). The hope is that the intractable model will help improve generalization while the tractable model, by leveraging Rao-Blackwellised sampling which combines exact inference and sampling, will help improve the prediction accuracy. To compactly model P(Y|X), we introduce a novel tractable representation called conditional cutset networks (CCNs) in which all conditional probability distributions are represented using calibrated classifiers—classifiers which typically yield higher quality probability estimates than conventional classifiers. We show via a rigorous experimental evaluation that CBNs and CCNs yield more accurate posterior estimates than their tractable as well as intractable counterparts.
APA, Harvard, Vancouver, ISO, and other styles
9

Wang, He. "A Review of Neural Network Application for Fault Diagnosis of NPP." In 17th International Conference on Nuclear Engineering. ASMEDC, 2009. http://dx.doi.org/10.1115/icone17-75255.

Full text
Abstract:
Artificial Neural Network (ANN) with its self-learning capabilities, nonlinear mapping ability and generalization ability, has been widely applied for fault diagnosis of complex system like Nuclear Power Plant (NPP). In this paper, an overview of the application of supervised multi-layer feed-forward neural network for fault diagnosis of NPP is presented, including the following aspects: the acquisition of the training sample data, the determination of appropriate input and output data, the choice of hidden layer structure and the evaluation of network model performance. Finally, a number of key issues about the engineering application of neural network fault diagnosis in practice were discussed.
APA, Harvard, Vancouver, ISO, and other styles
10

Cai, Yitao, and Xiaojun Wan. "Multi-Domain Sentiment Classification Based on Domain-Aware Embedding and Attention." In Twenty-Eighth International Joint Conference on Artificial Intelligence {IJCAI-19}. California: International Joint Conferences on Artificial Intelligence Organization, 2019. http://dx.doi.org/10.24963/ijcai.2019/681.

Full text
Abstract:
Sentiment classification is a fundamental task in NLP. However, as revealed by many researches, sentiment classification models are highly domain-dependent. It is worth investigating to leverage data from different domains to improve the classification performance in each domain. In this work, we propose a novel completely-shared multi-domain neural sentiment classification model to learn domain-aware word embeddings and make use of domain-aware attention mechanism. Our model first utilizes BiLSTM for domain classification and extracts domain-specific features for words, which are then combined with general word embeddings to form domain-aware word embeddings. Domain-aware word embeddings are fed into another BiLSTM to extract sentence features. The domain-aware attention mechanism is used for selecting significant features, by using the domain-aware sentence representation as the query vector. Evaluation results on public datasets with 16 different domains demonstrate the efficacy of our proposed model. Further experiments show the generalization ability and the transferability of our model.
APA, Harvard, Vancouver, ISO, and other styles
You might also be interested in the extended bibliographies on the topic 'Generalization performance evaluation' for particular source types:
Journal articles
We offer discounts on all premium plans for authors whose works are included in thematic literature selections. Contact us to get a unique promo code!

To the bibliography