Photonic online learning: a perspective
Emerging neuromorphic hardware promises to solve certain problems faster and with higher
energy efficiency than traditional computing by using physical processes that take place at …
energy efficiency than traditional computing by using physical processes that take place at …
[HTML][HTML] Multiplexed gradient descent: Fast online training of modern datasets on hardware neural networks without backpropagation
We present multiplexed gradient descent (MGD), a gradient descent framework designed to
easily train analog or digital neural networks in hardware. MGD utilizes zero-order …
easily train analog or digital neural networks in hardware. MGD utilizes zero-order …
Device Modeling Bias in ReRAM-based Neural Network Simulations
Emerging technologies based on resistive switching (ReRAM) devices promise to improve
the speed and energy efficiency of next generation machine learning accelerators, but …
the speed and energy efficiency of next generation machine learning accelerators, but …
A general approach to fast online training of modern datasets on real neuromorphic systems without backpropagation
S Buckley, A McCaughan - Proceedings of the International Conference …, 2022 - dl.acm.org
We present parameter-multiplexed gradient descent (PMGD), a perturbative gradient
descent framework designed to easily train emergent neuromorphic hardware platforms. We …
descent framework designed to easily train emergent neuromorphic hardware platforms. We …
Layer Ensemble Averaging for Improving Memristor-Based Artificial Neural Network Performance
Artificial neural networks have advanced due to scaling dimensions, but conventional
computing faces inefficiency due to the von Neumann bottleneck. In-memory computation …
computing faces inefficiency due to the von Neumann bottleneck. In-memory computation …
A Discovery Platform to Characterize Emerging Nonvolatile Memories for Computing
D Wilson, N Gilbert, M Spear, J Short… - 2024 IEEE 42nd …, 2024 - ieeexplore.ieee.org
Memory-centric architectures such as analog in memory computing (IMC) offer the potential
for orders of magnitude improvements in energy efficiency and performance beyond state of …
for orders of magnitude improvements in energy efficiency and performance beyond state of …
Neural Network Modeling Bias for Hafnia-based FeFETs
Modeling bias–the difference between the test accuracy obtained by a reference network
prototype and a simulated model of that prototype–is explored in the context of hafnia-based …
prototype and a simulated model of that prototype–is explored in the context of hafnia-based …