Memristor-based multilayer neural networks with online gradient descent training

D Soudry, D Di Castro, A Gal, A Kolodny… - IEEE transactions on …, 2015 - ieeexplore.ieee.org
Learning in multilayer neural networks (MNNs) relies on continuous updating of large
matrices of synaptic weights by local rules. Such locality can be exploited for massive …

Bioinspired programming of memory devices for implementing an inference engine

D Querlioz, O Bichler, AF Vincent… - Proceedings of the …, 2015 - ieeexplore.ieee.org
Cognitive tasks are essential for the modern applications of electronics, and rely on the
capability to perform inference. The Von Neumann bottleneck is an important issue for such …

On-chip universal supervised learning methods for neuro-inspired block of memristive nanodevices

D Chabi, W Zhao, D Querlioz, JO Klein - ACM Journal on Emerging …, 2015 - dl.acm.org
Scaling down beyond CMOS transistors requires the combination of new computing
paradigms and novel devices. In this context, neuromorphic architecture is developed to …

A VLSI circuit emulation of chemical synaptic transmission dynamics and postsynaptic DNA transcription

S Alam, SMR Hasan - IEEE Transactions on Very Large Scale …, 2015 - ieeexplore.ieee.org
Chemical synaptic transmission dynamics in the mammalian wetware control the activities of
a living creature. During this cascading process, biological information is transferred from …

Bioinspired neuromorphic module based on carbon nanotube/C60/polymer composite

K Kim, A Tudor, CL Chen, D Lee… - Journal of …, 2015 - journals.sagepub.com
It is extremely challenging to imitate neural networks with their high-speed parallel signal
processing, low power consumption, and intelligent learning capability. In this work, we …

Delay generator using a programmable resistor based on a phase-change material

S Manan, B De Salvo - US Patent 9,015,094, 2015 - Google Patents
A delay generator comprises at least one programmable resistor R PCM made of a
chalcogenide-based phase-change material, said resistor R PCM being initialized, so as to …

Analysis of CMOS inhibitory synapse with varying neurotransmitter concentration, reuptake time and spread delay

SG Pradyumna, SS Rathod - 2015 19th International …, 2015 - ieeexplore.ieee.org
Biologically-realistic synapses serve the role of computation, modification and
communication, which makes it an important pillar of spike-based neuron model. Various …

[引用][C] О новой технологии вычислений в машинном обучении

ВН Шац - НЕЙРОИНФОРМАТИКА-2015, 2015 - elibrary.ru
О новой технологии вычислений в машинном обучении КОРЗИНА ПОИСК НАВИГАТОР
ЖУРНАЛЫ КНИГИ ПАТЕНТЫ ПОИСК АВТОРЫ ОРГАНИЗАЦИИ КЛЮЧЕВЫЕ СЛОВА …