no code implementations • 6 Jul 2020 • Samiran Ganguly, Avik W. Ghosh
Biologically inspired recurrent neural networks, such as reservoir computers are of interest in designing spatio-temporal data processors from a hardware point of view due to the simple learning scheme and deep connections to Kalman filters.
no code implementations • 4 Oct 2018 • Jianhua Ma, Puhan Zhang, Yao-Hua Tan, Avik W. Ghosh, Gia-Wei Chern
Learning from data has led to a paradigm shift in computational materials science.
no code implementations • 7 Sep 2018 • Samiran Ganguly, Yunfei Gu, Yunkun Xie, Mircea R. Stan, Avik W. Ghosh, Nibir K. Dhar
Clean images are an important requirement for machine vision systems to recognize visual features correctly.
no code implementations • 23 Mar 2018 • Samiran Ganguly, Yunfei Gu, Mircea R. Stan, Avik W. Ghosh
In this work we show how we can build a technology platform for cognitive imaging sensors using recent advances in recurrent neural network architectures and training methods inspired from biology.
no code implementations • 29 Sep 2017 • Samiran Ganguly, Kerem Y. Camsari, Avik W. Ghosh
We present a general hardware framework for building networks that directly implement Reservoir Computing, a popular software method for implementing and training Recurrent Neural Networks and are particularly suited for temporal inferencing and pattern recognition.