Log in

Relevant bibliographies by topics / Transfer of Learning / Journal articles

To see the other types of publications on this topic, follow the link: Transfer of Learning.

Journal articles on the topic 'Transfer of Learning'

Author: Grafiati

Published: 4 June 2021

Last updated: 9 March 2023

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

Select a source type:

Consult the top 50 journal articles for your research on the topic 'Transfer of Learning.'

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.

Browse journal articles on a wide variety of disciplines and organise your bibliography correctly.

1

Alla, Sri Sai Meghana, and Kavitha Athota. "Brain Tumor Detection Using Transfer Learning in Deep Learning." Indian Journal Of Science And Technology 15, no. 40 (October 27, 2022): 2093–102. http://dx.doi.org/10.17485/ijst/v15i40.1307.

Full text

APA, Harvard, Vancouver, ISO, and other styles

2

Xu, Mingle, Sook Yoon, Jaesu Lee, and Dong Sun Park. "Unsupervised Transfer Learning for Plant Anomaly Recognition." Korean Institute of Smart Media 11, no. 4 (May 31, 2022): 30–37. http://dx.doi.org/10.30693/smj.2022.11.4.30.

Full text

Abstract:

Disease threatens plant growth and recognizing the type of disease is essential to making a remedy. In recent years, deep learning has witnessed a significant improvement for this task, however, a large volume of labeled images is one of the requirements to get decent performance. But annotated images are difficult and expensive to obtain in the agricultural field. Therefore, designing an efficient and effective strategy is one of the challenges in this area with few labeled data. Transfer learning, assuming taking knowledge from a source domain to a target domain, is borrowed to address this issue and observed comparable results. However, current transfer learning strategies can be regarded as a supervised method as it hypothesizes that there are many labeled images in a source domain. In contrast, unsupervised transfer learning, using only images in a source domain, gives more convenience as collecting images is much easier than annotating. In this paper, we leverage unsupervised transfer learning to perform plant disease recognition, by which we achieve a better performance than supervised transfer learning in many cases. Besides, a vision transformer with a bigger model capacity than convolution is utilized to have a better-pretrained feature space. With the vision transformer-based unsupervised transfer learning, we achieve better results than current works in two datasets. Especially, we obtain 97.3% accuracy with only 30 training images for each class in the Plant Village dataset. We hope that our work can encourage the community to pay attention to vision transformer-based unsupervised transfer learning in the agricultural field when with few labeled images.

APA, Harvard, Vancouver, ISO, and other styles

3

Würschinger, Hubert, Matthias Mühlbauer, and Nico Hanenkamp. "Transfer Learning für visuelle Kontrollaufgaben/Potentials of Transfer Learning." wt Werkstattstechnik online 110, no. 04 (2020): 264–69. http://dx.doi.org/10.37544/1436-4980-2020-04-98.

Full text

Abstract:

In der industriellen Praxis wird eine Vielzahl von Prozess- und Qualitätskontrollaufgaben visuell von Mitarbeitern oder mithilfe von Kamerasystemen durchgeführt. Durch den Einsatz Künstlicher Intelligenz (KI) lässt sich die Programmierung und damit die Implementierung von Kamerasystemen effizienter gestalten. Im Bereich der Bildanalyse können dabei vortrainierte Künstliche Neuronale Netze verwendet werden. Das Anwenden dieser Netze auf neue Aufgaben wird dabei Transfer Learning genannt.   In industrial practice, a large number of process and quality control tasks are performed visually by employees or with the aid of camera systems. By using artificial intelligence, the programming effort and thus the implementation of camera systems can be made more efficient. Pre-trained ^neural networks can be used for image analysis. The application of these networks to new tasks is called transfer learning.

APA, Harvard, Vancouver, ISO, and other styles

4

Vaishnavi, J., and V. Narmatha. "Novel Transfer Learning Attitude for Automatic Video Captioning Using Deep Learning Models." Indian Journal Of Science And Technology 15, no. 43 (November 20, 2022): 2325–35. http://dx.doi.org/10.17485/ijst/v15i43.1846.

Full text

APA, Harvard, Vancouver, ISO, and other styles

5

Gardie, Birhanu, Smegnew Asemie, Kasahun Azezew, and Zemedkun Solomon. "Potato Plant Leaf Diseases Identification Using Transfer Learning." Indian Journal of Science and Technology 15, no. 4 (January 25, 2022): 158–65. http://dx.doi.org/10.17485/ijst/v15i4.1235.

Full text

APA, Harvard, Vancouver, ISO, and other styles

6

Cao, Bin, Sinno Jialin Pan, Yu Zhang, Dit-Yan Yeung, and Qiang Yang. "Adaptive Transfer Learning." Proceedings of the AAAI Conference on Artificial Intelligence 24, no. 1 (July 3, 2010): 407–12. http://dx.doi.org/10.1609/aaai.v24i1.7682.

Full text

Abstract:

Transfer learning aims at reusing the knowledge in some source tasks to improve the learning of a target task. Many transfer learning methods assume that the source tasks and the target task be related, even though many tasks are not related in reality. However, when two tasks are unrelated, the knowledge extracted from a source task may not help, and even hurt, the performance of a target task. Thus, how to avoid negative transfer and then ensure a "safe transfer" of knowledge is crucial in transfer learning. In this paper, we propose an Adaptive Transfer learning algorithm based on Gaussian Processes (AT-GP), which can be used to adapt the transfer learning schemes by automatically estimating the similarity between a source and a target task. The main contribution of our work is that we propose a new semi-parametric transfer kernel for transfer learning from a Bayesian perspective, and propose to learn the model with respect to the target task, rather than all tasks as in multi-task learning. We can formulate the transfer learning problem as a unified Gaussian Process (GP) model. The adaptive transfer ability of our approach is verified on both synthetic and real-world datasets.

APA, Harvard, Vancouver, ISO, and other styles

7

Yu, Zhengxu, Dong Shen, Zhongming Jin, Jianqiang Huang, Deng Cai, and Xian-Sheng Hua. "Progressive Transfer Learning." IEEE Transactions on Image Processing 31 (2022): 1340–48. http://dx.doi.org/10.1109/tip.2022.3141258.

Full text

APA, Harvard, Vancouver, ISO, and other styles

8

Renta-Davids, Ana-Inés, José-Miguel Jiménez-González, Manel Fandos-Garrido, and Ángel-Pío González-Soto. "Transfer of learning." European Journal of Training and Development 38, no. 8 (August 27, 2014): 728–44. http://dx.doi.org/10.1108/ejtd-03-2014-0026.

Full text

Abstract:

Purpose – This paper aims to analyse transfer of learning to workplace regarding to job-related training courses. Training courses analysed in this study are offered under the professional training for employment framework in Spain. Design/methodology/approach – During the training courses, trainees completed a self-reported survey of reasons for participation (time 1 data collection, N = 447). Two months after training, a second survey was sent to the trainees by email (time 2 data collection, N = 158). Factor analysis, correlations and multiple hierarchical regressions were performed. Findings – The results of this study demonstrate the importance of training relevance and training effectiveness in transfer of training. Results indicated that relevance, the extent training courses were related to participant’s workplace activities and professional development, positively influences transfer of training. Effectiveness, training features which facilitated participants to acquire knowledge and skills, also has a significantly positive influence in transfer of training. Motivation to participate and learning-conducive workplace features also have a positive influence in transfer of training. Originality/value – This study contributes to the understanding of transfer of learning in work-related training programmes by analysing the factors that influence transfer of learning back to the workplace. The study has practical implication for training designers and education providers to enhance work-related training in the context of the Professional Training for Employment Subsystem in Spain.

APA, Harvard, Vancouver, ISO, and other styles

9

Tetzlaff, Linda. "Transfer of learning." ACM SIGCHI Bulletin 17, SI (May 1986): 205–10. http://dx.doi.org/10.1145/30851.275631.

Full text

APA, Harvard, Vancouver, ISO, and other styles

10

Koçer, Barış, and Ahmet Arslan. "Genetic transfer learning." Expert Systems with Applications 37, no. 10 (October 2010): 6997–7002. http://dx.doi.org/10.1016/j.eswa.2010.03.019.

Full text

APA, Harvard, Vancouver, ISO, and other styles

11

Tetzlaff, Linda. "Transfer of learning." ACM SIGCHI Bulletin 18, no. 4 (April 1987): 205–10. http://dx.doi.org/10.1145/1165387.275631.

Full text

APA, Harvard, Vancouver, ISO, and other styles

12

Zhao, Peilin, Steven C. H. Hoi, Jialei Wang, and Bin Li. "Online Transfer Learning." Artificial Intelligence 216 (November 2014): 76–102. http://dx.doi.org/10.1016/j.artint.2014.06.003.

Full text

APA, Harvard, Vancouver, ISO, and other styles

13

SATO, Hirokazu, Ryoji OTSU, Yonghoon JI, Hiromitsu FUJII, and Hitoshi KONO. "Automatic Transfer Rate Estimation for Transfer Learning in Reinforcement Learning." Proceedings of JSME annual Conference on Robotics and Mechatronics (Robomec) 2020 (2020): 2A2—J03. http://dx.doi.org/10.1299/jsmermd.2020.2a2-j03.

Full text

APA, Harvard, Vancouver, ISO, and other styles

14

Velada, Raquel, António Caetano, Reid Bates, and Ed Holton. "Learning transfer – validation of the learning transfer system inventory in Portugal." Journal of European Industrial Training 33, no. 7 (August 28, 2009): 635–56. http://dx.doi.org/10.1108/03090590910985390.

Full text

APA, Harvard, Vancouver, ISO, and other styles

15

Rani, S. V. Jansi. "Plant Disease Detection using Transfer Learning in Precision Agriculture." AMBIENT SCIENCE 9, no. 3 (November 2022): 34–39. http://dx.doi.org/10.21276/ambi.2022.09.3.ta02.

Full text

APA, Harvard, Vancouver, ISO, and other styles

16

Gui, Lin, Ruifeng Xu, Qin Lu, Jiachen Du, and Yu Zhou. "Negative transfer detection in transductive transfer learning." International Journal of Machine Learning and Cybernetics 9, no. 2 (February 9, 2017): 185–97. http://dx.doi.org/10.1007/s13042-016-0634-8.

Full text

APA, Harvard, Vancouver, ISO, and other styles

17

Hurt, Brian, Meagan A. Rubel, Evan M. Masutani, Kathleen Jacobs, Lewis Hahn, Michael Horowitz, Seth Kligerman, and Albert Hsiao. "Radiologist-supervised Transfer Learning." Journal of Thoracic Imaging 37, no. 2 (October 28, 2021): 90–99. http://dx.doi.org/10.1097/rti.0000000000000618.

Full text

APA, Harvard, Vancouver, ISO, and other styles

18

Ford, J. Kevin. "Defining Transfer of Learning." Adult Learning 5, no. 4 (March 1994): 22–30. http://dx.doi.org/10.1177/104515959400500412.

Full text

APA, Harvard, Vancouver, ISO, and other styles

19

Steenhuis, Harm-Jan, and Erik J. De Bruijn. "Technology Transfer and Learning." Technology Analysis & Strategic Management 14, no. 1 (March 2002): 57–66. http://dx.doi.org/10.1080/09537320220125883.

Full text

APA, Harvard, Vancouver, ISO, and other styles

20

Hu, Junlin, Jiwen Lu, Yap-Peng Tan, and Jie Zhou. "Deep Transfer Metric Learning." IEEE Transactions on Image Processing 25, no. 12 (December 2016): 5576–88. http://dx.doi.org/10.1109/tip.2016.2612827.

Full text

APA, Harvard, Vancouver, ISO, and other styles

21

Larsen-Freeman, Diane. "Transfer of Learning Transformed." Language Learning 63 (February 13, 2013): 107–29. http://dx.doi.org/10.1111/j.1467-9922.2012.00740.x.

Full text

APA, Harvard, Vancouver, ISO, and other styles

22

Liu, Xiaobo. "Ensemble Inductive Transfer Learning." Journal of Fiber Bioengineering and Informatics 8, no. 1 (June 2015): 105–15. http://dx.doi.org/10.3993/jfbi03201510.

Full text

APA, Harvard, Vancouver, ISO, and other styles

23

Ashburner, Jill, Jenny Ziviani, Sylvia Rodger, Elizabeth A. Hinder, Linda Cartmill, Jessica White, and Sandy Vickerstaff. "Improving Transfer of Learning." Journal of Continuing Education in the Health Professions 35, no. 4 (2015): 270–77. http://dx.doi.org/10.1097/ceh.0000000000000000.

Full text

APA, Harvard, Vancouver, ISO, and other styles

24

Hu, Xuegang, Jianhan Pan, Peipei Li, Huizong Li, Wei He, and Yuhong Zhang. "Multi-bridge transfer learning." Knowledge-Based Systems 97 (April 2016): 60–74. http://dx.doi.org/10.1016/j.knosys.2016.01.016.

Full text

APA, Harvard, Vancouver, ISO, and other styles

25

Karbalayghareh, Alireza, Xiaoning Qian, and Edward R. Dougherty. "Optimal Bayesian Transfer Learning." IEEE Transactions on Signal Processing 66, no. 14 (July 15, 2018): 3724–39. http://dx.doi.org/10.1109/tsp.2018.2839583.

Full text

APA, Harvard, Vancouver, ISO, and other styles

26

Liu, Xiaobo, Zhentao Liu, Guangjun Wang, Zhihua Cai, and Harry Zhang. "Ensemble Transfer Learning Algorithm." IEEE Access 6 (2018): 2389–96. http://dx.doi.org/10.1109/access.2017.2782884.

Full text

APA, Harvard, Vancouver, ISO, and other styles

27

Hassan Mahmud, M. M. "On universal transfer learning." Theoretical Computer Science 410, no. 19 (April 2009): 1826–46. http://dx.doi.org/10.1016/j.tcs.2009.01.013.

Full text

APA, Harvard, Vancouver, ISO, and other styles

28

Chun-Wei Seah, Ivor W. Tsang, and Yew-Soon Ong. "Transfer Ordinal Label Learning." IEEE Transactions on Neural Networks and Learning Systems 24, no. 11 (November 2013): 1863–76. http://dx.doi.org/10.1109/tnnls.2013.2268541.

Full text

APA, Harvard, Vancouver, ISO, and other styles

29

Ding, Zhengming, Ming Shao, and Yun Fu. "Incomplete Multisource Transfer Learning." IEEE Transactions on Neural Networks and Learning Systems 29, no. 2 (February 2018): 310–23. http://dx.doi.org/10.1109/tnnls.2016.2618765.

Full text

APA, Harvard, Vancouver, ISO, and other styles

30

Silva, Felipe Leno da, and Anna Helena Reali Costa. "Transfer Learning for Multiagent Reinforcement Learning Systems." Synthesis Lectures on Artificial Intelligence and Machine Learning 15, no. 3 (May 27, 2021): 1–129. http://dx.doi.org/10.2200/s01091ed1v01y202104aim049.

Full text

APA, Harvard, Vancouver, ISO, and other styles

31

Rajkumar, R., Arnav Kaushal, and Aishik Saha. "Accelerating Machine Learning Research Using Transfer Learning." Indian Journal of Computer Science 3, no. 2 (April 1, 2018): 7. http://dx.doi.org/10.17010/ijcs/2018/v3/i2/123212.

Full text

APA, Harvard, Vancouver, ISO, and other styles

32

Tamaazousti, Youssef, Herve Le Borgne, Celine Hudelot, Mohamed-El-Amine Seddik, and Mohamed Tamaazousti. "Learning More Universal Representations for Transfer-Learning." IEEE Transactions on Pattern Analysis and Machine Intelligence 42, no. 9 (September 1, 2020): 2212–24. http://dx.doi.org/10.1109/tpami.2019.2913857.

Full text

APA, Harvard, Vancouver, ISO, and other styles

33

Lewis, Kyle, Donald Lange, and Lynette Gillis. "Transactive Memory Systems, Learning, and Learning Transfer." Organization Science 16, no. 6 (December 2005): 581–98. http://dx.doi.org/10.1287/orsc.1050.0143.

Full text

APA, Harvard, Vancouver, ISO, and other styles

34

Iqbal, Muhammad Shahid, Bin Luo, Tamoor Khan, Rashid Mehmood, and Muhammad Sadiq. "Heterogeneous transfer learning techniques for machine learning." Iran Journal of Computer Science 1, no. 1 (January 9, 2018): 31–46. http://dx.doi.org/10.1007/s42044-017-0004-z.

Full text

APA, Harvard, Vancouver, ISO, and other styles

35

Hua, Jiang, Liangcai Zeng, Gongfa Li, and Zhaojie Ju. "Learning for a Robot: Deep Reinforcement Learning, Imitation Learning, Transfer Learning." Sensors 21, no. 4 (February 11, 2021): 1278. http://dx.doi.org/10.3390/s21041278.

Full text

Abstract:

Dexterous manipulation of the robot is an important part of realizing intelligence, but manipulators can only perform simple tasks such as sorting and packing in a structured environment. In view of the existing problem, this paper presents a state-of-the-art survey on an intelligent robot with the capability of autonomous deciding and learning. The paper first reviews the main achievements and research of the robot, which were mainly based on the breakthrough of automatic control and hardware in mechanics. With the evolution of artificial intelligence, many pieces of research have made further progresses in adaptive and robust control. The survey reveals that the latest research in deep learning and reinforcement learning has paved the way for highly complex tasks to be performed by robots. Furthermore, deep reinforcement learning, imitation learning, and transfer learning in robot control are discussed in detail. Finally, major achievements based on these methods are summarized and analyzed thoroughly, and future research challenges are proposed.

APA, Harvard, Vancouver, ISO, and other styles

36

Ali, W., and S. Kolyubin. "EMG-Based Grasping Force Estimation for Robot Skill Transfer Learning." Nelineinaya Dinamika 18, no. 5 (2022): 0. http://dx.doi.org/10.20537/nd221221.

Full text

Abstract:

In this study, we discuss a new machine learning architecture, the multilayer preceptron-random forest regressors pipeline (MLP-RF model), which stacks two ML regressors of different kinds to estimate the generated gripping forces from recorded surface electromyographic activity signals (EMG) during a gripping task. We evaluate our proposed approach on a publicly available dataset, putEMG-Force, which represents a sEMG-Force data profile. The sEMG signals were then filtered and preprocessed to get the features-target data frame that will be used to train the proposed ML model. The proposed ML model is a pipeline of stacking 2 different natural ML models; a random forest regressor model (RF regressor) and a multiple layer perceptron artificial neural network (MLP regressor). The models were stacked together, and the outputs were penalized by a Ridge regressor to get the best estimation of both models. The model was evaluated by different metrics; mean squared error and coefficient of determination, or $r^{2}$ score, to improve the model prediction performance. We tuned the most significant hyperparameters of each of the MLP-RF model components using a random search algorithm followed by a grid search algorithm. Finally, we evaluated our MLP-RF model performance on the data by training a recurrent neural network consisting of 2 LSTM layers, 2 dropouts, and one dense layer on the same data (as it is the common approach for problems with sequential datasets) and comparing the prediction results with our proposed model. The results show that the MLP-RF outperforms the RNN model.

APA, Harvard, Vancouver, ISO, and other styles

37

Kono, Hitoshi, Yuto Sakamoto, Yonghoon Ji, and Hiromitsu Fujii. "Automatic Transfer Rate Adjustment for Transfer Reinforcement Learning." International Journal of Artificial Intelligence & Applications 11, no. 6 (November 30, 2020): 47–54. http://dx.doi.org/10.5121/ijaia.2020.11605.

Full text

Abstract:

This paper proposes a novel parameter for transfer reinforcement learning to avoid over-fitting when an agent uses a transferred policy from a source task. Learning robot systems have recently been studied for many applications, such as home robots, communication robots, and warehouse robots. However, if the agent reuses the knowledge that has been sufficiently learned in the source task, deadlock may occur and appropriate transfer learning may not be realized. In the previous work, a parameter called transfer rate was proposed to adjust the ratio of transfer, and its contribution include avoiding dead lock in the target task. However, adjusting the parameter depends on human intuition and experiences. Furthermore, the method for deciding transfer rate has not discussed. Therefore, an automatic method for adjusting the transfer rate is proposed in this paper using a sigmoid function. Further, computer simulations are used to evaluate the effectiveness of the proposed method to improve the environmental adaptation performance in a target task, which refers to the situation of reusing knowledge.

APA, Harvard, Vancouver, ISO, and other styles

38

Rezapour, Mahdi, and Khaled Ksaibati. "Convolutional Neural Network for Roadside Barriers Detection: Transfer Learning versus Non-Transfer Learning." Signals 2, no. 1 (February 1, 2021): 72–86. http://dx.doi.org/10.3390/signals2010007.

Full text

Abstract:

Increasingly more governmental organizations in the U.S. have started to implement artificial intelligence to enhance the asset management process with an objective of controlling the costs of data collection. To help the Wyoming Department of Transportation (WYDOT) to automate the data collections process, related to various assets in the state, an automated assets management data collection was proposed. As an example, the automated traffic barriers asset dataset would collect geometric characteristics, and barriers’ materials’ conditions, e.g., being rusty or not. The information would be stored and accessed for asset-management-decision-making and optimization process to fulfill various objectives such as traffic safety improvement, or assets’ enhancement. For instance, the State of Wyoming has more than a million feet of roadside barriers, worth more than 100 million dollars. One-time collection of various characteristics of those barriers has cost the state more than half a million dollars. Thus, this study, as a first step for comprehensive data collection, proposed a novel approach in identification of roadside barrier types. Pre-trained inception v3, denseNet 121, and VGG 19 were implemented in this study. Transfer learning was used as there were only 250 images for training of the dataset for each category. For that method, the topmost layers were removed, along with adding two more new layers while freezing the remaining layers. This study achieved an accuracy of 97% by the VGG 19 network, training only the few last layers of the model along with adding two dense layers for top layers. The results indicated that although there are not enough observations related to traffic barrier images, a transfer learning application could be considered in data collection. A simple architecture non-transfer model was also implemented. This model achieved an accuracy of 85%, being better that the two other transfer learning techniques. It should be reiterated that although non-transfer learning technique outperformed inception and denseNet networks, it comes short significantly when it come to the VGG network.

APA, Harvard, Vancouver, ISO, and other styles

39

Hung, Woei. "Problem-Based Learning: A Learning Environment for Enhancing Learning Transfer." New Directions for Adult and Continuing Education 2013, no. 137 (March 2013): 27–38. http://dx.doi.org/10.1002/ace.20042.

Full text

APA, Harvard, Vancouver, ISO, and other styles

40

Lee, Seung-Hyun, and Sung-Hyun Yoon. "The Effect of the Learning Transfer Climate of Korea Coast Guard on the Learning and Learning Transfer." Korean Security Science Review 51 (June 30, 2017): 59–78. http://dx.doi.org/10.36623/kssa.2017.51.3.

Full text

APA, Harvard, Vancouver, ISO, and other styles

41

Lee, Seung-Hyun, and Sung-Hyun Yoon. "The Effect of the Learning Transfer Climate of Korea Coast Guard on the Learning and Learning Transfer." Korean Security Science Review 51 (June 30, 2017): 59–78. http://dx.doi.org/10.36623/kssa.2019.51.3.

Full text

APA, Harvard, Vancouver, ISO, and other styles

42

Gupta, Jaya, Sunil Pathak, and Gireesh Kumar. "Deep Learning (CNN) and Transfer Learning: A Review." Journal of Physics: Conference Series 2273, no. 1 (May 1, 2022): 012029. http://dx.doi.org/10.1088/1742-6596/2273/1/012029.

Full text

Abstract:

Abstract Deep Learning is a machine learning area that has recently been used in a variety of industries. Unsupervised, semi-supervised, and supervised-learning are only a few of the strategies that have been developed to accommodate different types of learning. A number of experiments showed that deep learning systems fared better than traditional ones when it came to image processing, computer vision, and pattern recognition. Several real-world applications and hierarchical systems have utilised transfer learning and deep learning algorithms for pattern recognition and classification tasks. Real-world machine learning settings, on the other hand, often do not support this assumption since training data can be difficult or expensive to get, and there is a constant need to generate high-performance beginners who can work with data from a variety of sources. The objective of this paper is using deep learning to uncover higher-level representational features, to clearly explain transfer learning, to provide current solutions and evaluate applications in diverse areas of transfer learning as well as deep learning.

APA, Harvard, Vancouver, ISO, and other styles

43

Gupta, Jaya, Sunil Pathak, and Gireesh Kumar. "Deep Learning (CNN) and Transfer Learning: A Review." Journal of Physics: Conference Series 2273, no. 1 (May 1, 2022): 012029. http://dx.doi.org/10.1088/1742-6596/2273/1/012029.

Full text

Abstract:

Abstract Deep Learning is a machine learning area that has recently been used in a variety of industries. Unsupervised, semi-supervised, and supervised-learning are only a few of the strategies that have been developed to accommodate different types of learning. A number of experiments showed that deep learning systems fared better than traditional ones when it came to image processing, computer vision, and pattern recognition. Several real-world applications and hierarchical systems have utilised transfer learning and deep learning algorithms for pattern recognition and classification tasks. Real-world machine learning settings, on the other hand, often do not support this assumption since training data can be difficult or expensive to get, and there is a constant need to generate high-performance beginners who can work with data from a variety of sources. The objective of this paper is using deep learning to uncover higher-level representational features, to clearly explain transfer learning, to provide current solutions and evaluate applications in diverse areas of transfer learning as well as deep learning.

APA, Harvard, Vancouver, ISO, and other styles

44

Desai, Chitra. "Image Classification Using Transfer Learning and Deep Learning." International Journal of Engineering and Computer Science 10, no. 9 (September 23, 2021): 25394–98. http://dx.doi.org/10.18535/ijecs/v10i9.4622.

Full text

Abstract:

Deep learning models have demonstrated improved efficacy in image classification since the ImageNet Large Scale Visual Recognition Challenge started since 2010. Classification of images has further augmented in the field of computer vision with the dawn of transfer learning. To train a model on huge dataset demands huge computational resources and add a lot of cost to learning. Transfer learning allows to reduce on cost of learning and also help avoid reinventing the wheel. There are several pretrained models like VGG16, VGG19, ResNet50, Inceptionv3, EfficientNet etc which are widely used. This paper demonstrates image classification using pretrained deep neural network model VGG16 which is trained on images from ImageNet dataset. After obtaining the convolutional base model, a new deep neural network model is built on top of it for image classification based on fully connected network. This classifier will use features extracted from the convolutional base model.

APA, Harvard, Vancouver, ISO, and other styles

45

Kiranov, Dmitry Maratovich, Maxim Alexeevitch Ryndin, and Ilya Sergeevich Kozlov. "Active learning and transfer learning for document segmentation." Proceedings of the Institute for System Programming of the RAS 33, no. 6 (2021): 205–16. http://dx.doi.org/10.15514/ispras-2021-33(6)-14.

Full text

Abstract:

In this paper, we investigate the effectiveness of classical approaches of active learning in the problem of segmentation of document images in order to reduce the training sample. A modified approach to the selection of images for marking and subsequent training is presented. The results obtained through active learning are compared to transfer learning using fully labeled data. It also investigates how the subject area of the training set, on which the model is initialized for transfer learning, affects the subsequent additional training of the model.

APA, Harvard, Vancouver, ISO, and other styles

46

Green, C. Shawn. "Transfer and Learning to Learn in Perceptual Learning." i-Perception 2, no. 4 (May 2011): 408. http://dx.doi.org/10.1068/ic408.

Full text

APA, Harvard, Vancouver, ISO, and other styles

47

Christiansen, Morten H., and Suzanne Curtin. "Transfer of learning: rule acquisition or statistical learning?" Trends in Cognitive Sciences 3, no. 8 (August 1999): 289–90. http://dx.doi.org/10.1016/s1364-6613(99)01356-x.

Full text

APA, Harvard, Vancouver, ISO, and other styles

48

He, Yiwei, Yingjie Tian, and Dalian Liu. "Multi-view transfer learning with privileged learning framework." Neurocomputing 335 (March 2019): 131–42. http://dx.doi.org/10.1016/j.neucom.2019.01.019.

Full text

APA, Harvard, Vancouver, ISO, and other styles

49

Son, Ji Y., and Robert L. Goldstone. "Fostering general transfer with specific simulations." Pragmatics and Cognition 17, no. 1 (February 18, 2009): 1–42. http://dx.doi.org/10.1075/pc.17.1.01son.

Full text

Abstract:

Science education faces the difficult task of helping students understand and appropriately generalize scientific principles across a variety of superficially dissimilar specific phenomena. Can cognitive technologies be adapted to benefit both learning specific domains and generalizable transfer? This issue is examined by teaching students complex adaptive systems with computer-based simulations. With a particular emphasis on fostering understanding that transfers to dissimilar phenomena, the studies reported here examine the influence of different descriptions and perceptual instantiations of the scientific principle of competitive specialization. Experiment 1 examines the role of intuitive descriptions to concrete ones, finding that intuitive descriptions leads to enhanced domain-specific learning but also deters transfer. Experiment 2 successfully alleviated these difficulties by combining intuitive descriptions with idealized graphical elements. Experiment 3 demonstrates that idealized graphics are more effective than concrete graphics even when unintuitive descriptions are applied to them. When graphics are concrete, learning and transfer largely depend on the particular description. However, when graphics are idealized, a wider variety of descriptions results in levels of learning and transfer similar to the best combination involving concrete graphics. Although computer-based simulations can be effective for learning that transfers, designing effective simulations requires an understanding of concreteness and idealization in both the graphical interface and its description.

APA, Harvard, Vancouver, ISO, and other styles

50

Gurjar, Aparna, and Preeti Voditel. "Transfer Learning: A Paradigm for Machine Assisted Knowledge Transfer." ECS Transactions 107, no. 1 (April 24, 2022): 7179–88. http://dx.doi.org/10.1149/10701.7179ecst.

Full text

Abstract:

This paper surveys transfer learning as a sustainable knowledge transfer mechanism. Conventional machine learning algorithms require a huge amount of labeled data for supervised learning. In absence of such data, the models suffer from performance degradation. Transfer learning enables the prior knowledge gained in doing a particular task to be reused or transferred to another new task of similar nature. This can speed up and improve the learning curve of the tasks in the new domain. The paper gives an overview of the transfer learning process and highlights how this innovative artificial intelligence (AI) technique can help achieve the goals of sustainable development. The literature survey highlights widely used mechanisms of Transfer Learning like homogeneous, heterogeneous, as well as instance-based, parameter-based, and relational-based implementation of transfer learning. It discusses how these mechanisms are utilized to create efficient AI-based applications which aid sustainability in the long run.

APA, Harvard, Vancouver, ISO, and other styles

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!