no code implementations • 20 Feb 2021 • Sourav Dutta, Georgios Detorakis, Abhishek Khanna, Benjamin Grisafe, Emre Neftci, Suman Datta
We experimentally show that the inherent stochastic switching of the selector element between the insulator and metallic state introduces a multiplicative stochastic noise within the synapses of NSM that samples the conductance states of the FeFET, both during learning and inference.
1 code implementation • NeurIPS 2019 • Georgios Detorakis, Sourav Dutta, Abhishek Khanna, Matthew Jerry, Suman Datta, Emre Neftci
Multiplicative stochasticity such as Dropout improves the robustness and generalizability of deep neural networks.
1 code implementation • 19 Jun 2018 • Georgios Detorakis, Travis Bartley, Emre Neftci
It operates in two phases, the forward (or free) phase, where the data are fed to the network, and a backward (or clamped) phase, where the target signals are clamped to the output layer of the network and the feedback signals are transformed through the transpose synaptic weight matrices.
no code implementations • 29 Sep 2017 • Georgios Detorakis, Sadique Sheik, Charles Augustine, Somnath Paul, Bruno U. Pedroni, Nikil Dutt, Jeffrey Krichmar, Gert Cauwenberghs, Emre Neftci
Embedded, continual learning for autonomous and adaptive behavior is a key application of neuromorphic hardware.
1 code implementation • 16 Dec 2016 • Emre Neftci, Charles Augustine, Somnath Paul, Georgios Detorakis
Building on these results, we demonstrate an event-driven random BP (eRBP) rule that uses an error-modulated synaptic plasticity for learning deep representations in neuromorphic computing hardware.
no code implementations • 11 Jul 2016 • Bruno U. Pedroni, Sadique Sheik, Siddharth Joshi, Georgios Detorakis, Somnath Paul, Charles Augustine, Emre Neftci, Gert Cauwenberghs
We present a novel method for realizing both causal and acausal weight updates using only forward lookup access of the synaptic connectivity table, permitting memory-efficient implementation.