Quantum tunneling based ultra-compact and energy efficient spiking neuron enables hardware SNN
Low-power and low-area neurons are essential for hardware implementation of large-scale
SNNs. Various novel-physics-based leaky-integrate-and-fire (LIF) neuron architectures have …
SNNs. Various novel-physics-based leaky-integrate-and-fire (LIF) neuron architectures have …
SHIP: a computational framework for simulating and validating novel technologies in hardware spiking neural networks
Investigations in the field of spiking neural networks (SNNs) encompass diverse, yet
overlapping, scientific disciplines. Examples range from purely neuroscientific …
overlapping, scientific disciplines. Examples range from purely neuroscientific …
Hardware-friendly synaptic orders and timescales in liquid state machines for speech classification
V Saraswat, A Gorad, A Naik, A Patil… - … Joint Conference on …, 2021 - ieeexplore.ieee.org
Liquid State Machines are brain inspired spiking neural networks (SNNs) with random
reservoir connectivity and bio-mimetic neuronal and synaptic models. Reservoir computing …
reservoir connectivity and bio-mimetic neuronal and synaptic models. Reservoir computing …
P-CRITICAL: a reservoir autoregulation plasticity rule for neuromorphic hardware
Backpropagation algorithms on recurrent artificial neural networks require an unfolding of
accumulated states over time. These states must be kept in memory for an undefined period …
accumulated states over time. These states must be kept in memory for an undefined period …
Real-world performance estimation of liquid state machines for spoken digit classification
Liquid State Machine (LSM) is a brain-inspired neural network architecture for solving
temporal classification problems like speech recognition. The simple structure of LSM with a …
temporal classification problems like speech recognition. The simple structure of LSM with a …
Liquid state machine on loihi: Memory metric for performance prediction
Abstract Liquid State Machine (LSM) is a spiking variant of recurrent neural networks with
promising results for speech, video and other temporal datasets classification. LSM employ …
promising results for speech, video and other temporal datasets classification. LSM employ …
MAdapter: A Multimodal Adapter for Liquid State Machines configures the Input Layer for the same Reservoir to enable Vision and Speech Classification
A Biswas, NS Nambiar, K Kejriwal… - 2023 International Joint …, 2023 - ieeexplore.ieee.org
The human cortex is capable of multi-modal processing. Then, assuming that the biological
model of the brain cortex is captured by Liquid State Machines (LSMs), it should be …
model of the brain cortex is captured by Liquid State Machines (LSMs), it should be …