Search Results for author:
Found 12 papers, 4 papers with code
Complexity-aware Adaptive Training and Inference for Edge-Cloud Distributed AI Systems
Only data with high probabilities of belonging to hard classes would be sent to the extension block for prediction.
Enabling Deep Spiking Neural Networks with Hybrid Conversion and Spike Timing Dependent Backpropagation
We propose a hybrid training methodology: 1) take a converted SNN and use its weights and thresholds as an initialization step for spike-based backpropagation, and 2) perform incremental spike-timing dependent backpropagation (STDB) on this carefully initialized network to obtain an SNN that converges within few epochs and requires fewer time steps for input processing.
Pruning Filters while Training for Efficiently Optimizing Deep Learning Networks
Our results for VGG-16 trained on CIFAR10 shows that L1 normalization provides the best performance among all the techniques explored in this work with less than 1% drop in accuracy after pruning 80% of the filters compared to the original network.
Explicitly Trained Spiking Sparsity in Spiking Neural Networks with Backpropagation
Spiking Neural Networks (SNNs) are being explored for their potential energy efficiency resulting from sparse, event-driven computations.
RMP-SNN: Residual Membrane Potential Neuron for Enabling Deeper High-Accuracy and Low-Latency Spiking Neural Network
We find that performance degradation in the converted SNN stems from using "hard reset" spiking neuron that is driven to fixed reset potential once its membrane potential exceeds the firing threshold, leading to information loss during SNN inference.
Reinforcement Learning with Low-Complexity Liquid State Machines
We propose reinforcement learning on simple networks consisting of random connections of spiking neurons (both recurrent and feed-forward) that can learn complex tasks with very little trainable parameters.
Enabling Spike-based Backpropagation for Training Deep Neural Network Architectures
Spiking Neural Networks (SNNs) have recently emerged as a prominent neural computing paradigm.
ReStoCNet: Residual Stochastic Binary Convolutional Spiking Neural Network for Memory-Efficient Neuromorphic Computing
In addition, we introduce residual connections between the stacked convolutional layers to improve the hierarchical feature learning capability of deep SNNs.
Xcel-RAM: Accelerating Binary Neural Networks in High-Throughput SRAM Compute Arrays
In this paper, we demonstrate how deep binary networks can be accelerated in modified von-Neumann machines by enabling binary convolutions within the SRAM array.
Emerging Technologies
Convolutional Spike Timing Dependent Plasticity based Feature Learning in Spiking Neural Networks
Brain-inspired learning models attempt to mimic the cortical architecture and computations performed in the neurons and synapses constituting the human brain to achieve its efficiency in cognitive tasks.
Proposal for a Leaky-Integrate-Fire Spiking Neuron based on Magneto-Electric Switching of Ferro-magnets
The efficiency of the human brain in performing classification tasks has attracted considerable research interest in brain-inspired neuromorphic computing.
Significance Driven Hybrid 8T-6T SRAM for Energy-Efficient Synaptic Storage in Artificial Neural Networks
Our analysis on a widely used digit recognition dataset indicates that the voltage can be scaled by 200mV from the nominal operating voltage (950mV) for practically no loss (less than 0. 5%) in accuracy (22nm predictive technology).
