Search

Your search keyword '"Yang, Changju"' showing total 129 results
Start Over Author "Yang, Changju"
129 results on '"Yang, Changju"'

3. A Circuit-Based Neural Network with Hybrid Learning of Backpropagation and Random Weight Change Algorithms

Author

Yang, Changju, Kim, Hyongsuk, Adhikari, Shyam Prasad, and Chua, Leon O

Subjects
Information and Computing Sciences, Artificial Intelligence, Machine Learning, software-based learning, circuit-based learning, complementary learning, backpropagation, RWC, Analytical Chemistry, Environmental Science and Management, Ecology, Distributed Computing, Electrical and Electronic Engineering, Electrical engineering, Electronics, sensors and digital hardware, Environmental management, Distributed computing and systems software
Abstract

A hybrid learning method of a software-based backpropagation learning and a hardware-based RWC learning is proposed for the development of circuit-based neural networks. The backpropagation is known as one of the most efficient learning algorithms. A weak point is that its hardware implementation is extremely difficult. The RWC algorithm, which is very easy to implement with respect to its hardware circuits, takes too many iterations for learning. The proposed learning algorithm is a hybrid one of these two. The main learning is performed with a software version of the BP algorithm, firstly, and then, learned weights are transplanted on a hardware version of a neural circuit. At the time of the weight transplantation, a significant amount of output error would occur due to the characteristic difference between the software and the hardware. In the proposed method, such error is reduced via a complementary learning of the RWC algorithm, which is implemented in a simple hardware. The usefulness of the proposed hybrid learning system is verified via simulations upon several classical learning problems.

Published
2017

4. A Circuit-Based Neural Network with Hybrid Learning of Backpropagation and Random Weight Change Algorithms.

Author

Yang, Changju, Kim, Hyongsuk, Adhikari, Shyam, and CHUA, Leon O.

Subjects
RWC, backpropagation, circuit-based learning, complementary learning, software-based learning
Abstract

A hybrid learning method of a software-based backpropagation learning and a hardware-based RWC learning is proposed for the development of circuit-based neural networks. The backpropagation is known as one of the most efficient learning algorithms. A weak point is that its hardware implementation is extremely difficult. The RWC algorithm, which is very easy to implement with respect to its hardware circuits, takes too many iterations for learning. The proposed learning algorithm is a hybrid one of these two. The main learning is performed with a software version of the BP algorithm, firstly, and then, learned weights are transplanted on a hardware version of a neural circuit. At the time of the weight transplantation, a significant amount of output error would occur due to the characteristic difference between the software and the hardware. In the proposed method, such error is reduced via a complementary learning of the RWC algorithm, which is implemented in a simple hardware. The usefulness of the proposed hybrid learning system is verified via simulations upon several classical learning problems.

Published
2016

9. A Neural Network Circuit Development via Software-Based Learning and Circuit-Based Fine Tuning

Author

Yang, Changju, Adhikari, Shyam Prasad, Strzelecki, Michal, Kim, Hyongsuk, Hutchison, David, Series editor, Kanade, Takeo, Series editor, Kittler, Josef, Series editor, Kleinberg, Jon M., Series editor, Mattern, Friedemann, Series editor, Mitchell, John C., Series editor, Naor, Moni, Series editor, Pandu Rangan, C., Series editor, Steffen, Bernhard, Series editor, Terzopoulos, Demetri, Series editor, Tygar, Doug, Series editor, Weikum, Gerhard, Series editor, Rutkowski, Leszek, editor, Korytkowski, Marcin, editor, Scherer, Rafał, editor, Tadeusiewicz, Ryszard, editor, Zadeh, Lotfi A., editor, and Zurada, Jacek M., editor

Published
2017
Full Text
View/download PDF

30. Susceptibility of Field Populations ofAnopheles sinensis(Diptera: Culicidae) toBacillus thuringiensissubsp.israelensis

Author

Huang Jingye, Zhang HongYu, Lü Lin, and Yang Changju

Subjects
Larva, Veterinary medicine, biology, Strain (chemistry), ved/biology, Low dose, ved/biology.organism_classification_rank.species, Central china, Field population, biology.organism_classification, Pupa, Anopheles sinensis, Insect Science, Bacillus thuringiensis, Botany, Agronomy and Crop Science
Abstract

The susceptibility of Anopheles sinensis to Bacillus thuringiensis subsp. israelensis (Bti) was evaluated through exposure to varying concentrations of Bti. Mosquitoes were collected from five field populations of southern and central China (Zhongshan, Hengxian, Wuchang, Xinzhou, and Ruichang) and compared with a standard laboratory strain. The LC50 values were 146.4, 50.4, 57.9, 50.0, 41.6 and 24.6 ng/mL, respectively. Differences in susceptibility to Bti ranging from 1.7 to 5.9-fold compared with the laboratory strain. The Zhongshan strain had the greatest resistance. At low doses, Bti displayed residual effects. Peak mortality occurred from the first to the fourth day. Exposure to low doses increased the duration of larval development and decreased the duration of pupal development, indicating that low doses of Bti have a sublethal effect on their hosts.

Published
2004

48. Memristor Bridge Synapses

Author

Kim, Hyongsuk, primary, Sah, Maheshwar Pd., additional, Yang, Changju, additional, Roska, Tamás, additional, and Chua, Leon O., additional

Published
2012
Full Text
View/download PDF

Catalog

Books, media, physical & digital resources
See catalog results