Using memristors for robust local learning of hardware restricted Boltzmann machines

M Ernoult, J Grollier, D Querlioz - Scientific reports, 2019 - nature.com
One of the biggest stakes in nanoelectronics today is to meet the needs of Artificial
Intelligence by designing hardware neural networks which, by fusing computation and …

Stochastic learning in deep neural networks based on nanoscale PCMO device characteristics

AV Babu, S Lashkare, U Ganguly, B Rajendran - Neurocomputing, 2018 - Elsevier
Abstract Deep Neural Networks (DNN) have proven to be highly effective in extracting high
level abstractions of input data using multiple neural network layers. However, the huge …

Uncorrelated stochastic bitstream generation and arithmetic computations using Cu: ZnO memristors

PKR Boppidi, B Suresh, G Abhijith, PMP Raj… - Materials Science in …, 2022 - Elsevier
One popular approach under approximate computing is stochastic computing, wherein
values are encoded in bitstreams to perform arithmetic operations in a low-power and …

Acceleration of convolutional networks using nanoscale memristive devices

SR Kulkarni, AV Babu, B Rajendran - … 2018, Bristol, UK, September 3-5 …, 2018 - Springer
We discuss a convolutional neural network for handwritten digit classification and its
hardware acceleration as an inference engine using nanoscale memristive devices in the …

Efficient hardware implementations of bio-inspired networks

A Vasanthakumaribabu - 2020 - search.proquest.com
The human brain, with its massive computational capability and power efficiency in small
form factor, continues to inspire the ultimate goal of building machines that can perform tasks …

Rethinking biologically inspired learning algorithmstowards better credit assignment for on-chip learning

M Ernoult - 2020 - theses.hal.science
The deep learning approach to AI has taken upon the whole society thanks to the use of
Graphical Computing Units (GPUs). Going beyond the capability of the GPUs for deep …

Matrix sketching using analog crossbar architectures

L Horesh, OM Onen, H Avron, T Gokmen… - US Patent …, 2022 - Google Patents
(57) ABSTRACT A computer-implemented method is presented for perform ing matrix
sketching by employing an analog crossbar architecture. The method includes low rank …

Bio-Inspired Learning and Hardware Acceleration with Emerging Memories

SR Kulkarni - 2019 - search.proquest.com
Abstract Machine Learning has permeated many aspects of engineering, ranging from the
Internet of Things (IoT) applications to big data analytics. While computing resources …