Results 51 to 60 of about 127,617 (265)

Unsupervised Domain Adaptation by Backpropagation [PDF]

, 2015
Top-performing deep architectures are trained on massive amounts of labeled data. In the absence of labeled data for a certain task, domain adaptation often provides an attractive option given that labeled data of similar nature but from a different ...
Ganin, Yaroslav, Lempitsky, Victor
core  

Additive Manufacturing of NiTi Shape Memory Alloys for Elastocaloric Applications: A Review

Advanced Functional Materials, EarlyView.
Additive manufacturing enables complex NiTi architectures that overcome key limitations in elastocaloric refrigeration, including poor heat transfer and high mechanical work input. This review surveys recent advances in LPBF‐ and DED‐fabricated NiTi shape memory alloys for elastocaloric applications, highlighting process–structure–performance ...
Ignatius Andre Setiawan, Mohammad Mehrali, Jaka Tušek, Shiva Mohajerani, Xiebin Wang, Dermot Brabazon, Mohammad Elahinia, Mehrshad Mehrpouya   +7 more
wiley   +1 more source

Multilayered feed forward Artificial Neural Network model to predict the average summer-monsoon rainfall in India

, 2006
In the present research, possibility of predicting average summer-monsoon rainfall over India has been analyzed through Artificial Neural Network models.
A.J. Matthews, B. Men, B. Sivakumar, B. Sivakumar, B. Sivakumar, B. Widrow, B.G. Brown, C. Cartalis, C. Varotsos, C. Varotsos, C. Varotsos, C.P. Jacovides, D.S. Wilks, D.S. Wilks, E.H. Chin, J.B. Elsner, J.M. Gregory, K.Y. Kondratyev, K.Y. Kondratyev, L. Ferranti, M. Gevrey, M.J.C. Hu, M.W. Gardner, O.C. Clark, P. Guhathakurta, P. Perez, P. Perez, P.D. Sardeshmukh, P.R.C. Reddy, S. Gadgil, S. Haykin, S. Lee, S.K. Pal, S.M.S. Nagendra, S.V. Kamarthi, S.V. Kartalopoulos, Surajit Chattopadhyay, T. Shinoda, T.J. Sejnowski, T.M. Smith, W.W. Hsieh   +40 more
core   +1 more source

BEOL‐Compatible Liquid‐Metal‐Printing of Ultrathin 2D Oxide Memtransistors and Its Applications in Neuromorphic Computing

Advanced Functional Materials, EarlyView.
Ultrathin 2D indium oxide memtransistors are reproducibly fabricated via a scalable liquid‐metal‐printing process under ambient, low‐temperature conditions. The devices achieve robust, gate‐tunable bipolar memristive switching with high switching ratios at a BEOL‐compatible maximum processing temperature of 300°C. Governed by trap‐controlled transport,
Sanghyun Moon, Seungyun Lee, Sunghan Cho, Donggyu Lee, Jehwan Park, Seongyun Yang, Jihyun Kim   +6 more
wiley   +1 more source

Combining backpropagation with Equilibrium Propagation to improve an Actor-Critic reinforcement learning framework

Frontiers in Computational Neuroscience, 2022
Backpropagation (BP) has been used to train neural networks for many years, allowing them to solve a wide variety of tasks like image classification, speech recognition, and reinforcement learning tasks.
Yoshimasa Kubo, Eric Chalmers, Artur Luczak   +2 more
doaj   +1 more source

Optoelectronic Control of Redox Dynamics in POM Memristors for Noise‐Resilient Speech and Hardware‐Level Motion Recognition

Advanced Functional Materials, EarlyView.
Optoelectronic control of redox‐active polyoxometalate clusters in polymer matrices yields hybrid memristors with switchable volatile and non‐volatile modes, enabling reservoir‐type in‐sensor optical preprocessing and stable multilevel synapses for multimodal neuromorphic computing, including noise‐tolerant audiovisual keyword recognition and hardware ...
Xiangyu Ma, Ziyu Lv, Guohua Zhang, Zhongyue Xu, Yongbiao Zhai, Haiming Huang, Qiyan Zhang, Xiaojin Zhao, Yan Wang, Ye Zhou, Ziyu Xiong, Guanglong Ding, Wentao Xu, Su‐Ting Han   +13 more
wiley   +1 more source

Recunoașterea unei cifre scrise de mână folosind o rețea neuronală convoluțională și biblioteca TensorFlow unei cifre scrise de mână folosind o rețea neuronală convoluțională și biblioteca TensorFlow [PDF]

Revista Română de Informatică și Automatică, 2019
In this paper it is proposed to solve a visual problem of recognizing a handwritten figure. A machine learning technique will be used in which a result is produced based on previous experience.
Paul TEODORESCU
doaj   +1 more source

Nonlinear backpropagation: doing backpropagation without derivatives of the activation function [PDF]

IEEE Transactions on Neural Networks, 1997
The conventional linear backpropagation algorithm is replaced by a nonlinear version, which avoids the necessity for calculating the derivative of the activation function. This may be exploited in hardware realizations of neural processors. In this paper we derive the nonlinear backpropagation algorithms in the framework of recurrent backpropagation ...
Hertz, J., Krogh, A., Lautrup, B., Lehmann, T.   +3 more
openaire   +2 more sources

Transistor‐Level Activation Functions via Two‐Gate Designs: From Analog Sigmoid and Gaussian Control to Real‐Time Hardware Demonstrations

Advanced Materials, EarlyView.
Screen gate‐based transistors are presented, enabling tunable analog sigmoid and Gaussian activations. The SA‐transistor improves MRI classification accuracy, while the GA‐transistor supports precise Gaussian kernel tuning for forecasting. Both functions are implemented in a single device, offering compact, energy‐efficient analog AI processing ...
Junhyung Cho, Youngmin Han, Won Woo Lee, Youngwoo Yoo, Kannan Udaya Mohanan, Chang‐Hyun Kim, Junhwan Choi, Young‐Joon Kim, Wonjun Shin, Hocheon Yoo   +9 more
wiley   +1 more source

Backpropagation Through Soft Body: Investigating Information Processing in Brain–Body Coupling Systems

Advanced Robotics Research, EarlyView.
This study explores how information processing is distributed between brains and bodies through a codesign approach. Using the “backpropagation through soft body” framework, brain–body coupling agents are developed and analyzed across several tasks in which output is generated through the agents’ physical dynamics.
Hiroki Tomioka, Katsuma Inoue, Yasuo Kuniyoshi, Kohei Nakajima   +3 more
wiley   +1 more source