
Robustness Hidden in Plain Sight: Can Analog Computing Defend Against Adversarial Attacks?
The everincreasing computational demand of Deep Learning has propelled ...
read it

DIETSNN: Direct Input Encoding With Leakage and Threshold Optimization in Deep Spiking Neural Networks
Bioinspired spiking neural networks (SNNs), operating with asynchronous...
read it

TREND: Transferability based Robust ENsemble Design
Deep Learning models hold stateoftheart performance in many fields, b...
read it

Towards Understanding the Effect of Leak in Spiking Neural Networks
Spiking Neural Networks (SNNs) are being explored to emulate the astound...
read it

Fitted QLearning for Relational Domains
We consider the problem of Approximate Dynamic Programming in relational...
read it

Conditionally Deep Hybrid Neural Networks Across Edge and Cloud
The pervasiveness of "InternetofThings" in our daily life has led to a...
read it

Enabling Deep Spiking Neural Networks with Hybrid Conversion and Spike Timing Dependent Backpropagation
Spiking Neural Networks (SNNs) operate with asynchronous discrete events...
read it

Hyperparameter Optimization in Binary Communication Networks for Neuromorphic Deployment
Training neural networks for neuromorphic deployment is nontrivial. The...
read it

IMAC: Inmemory multibit Multiplication andACcumulation in 6T SRAM Array
`Inmemory computing' is being widely explored as a novel computing para...
read it

Inherent Adversarial Robustness of Deep Spiking Neural Networks: Effects of Discrete Input Encoding and NonLinear Activations
In the recent quest for trustworthy neural networks, we present Spiking ...
read it

Vec2Face: Unveil Human Faces from their Blackbox Features in Face Recognition
Unveiling face images of a subject given his/her highlevel representati...
read it

SpikeFlowNet: Eventbased Optical Flow Estimation with EnergyEfficient Hybrid Neural Networks
Eventbased cameras display great potential for a variety of conditions ...
read it

Explicitly Trained Spiking Sparsity in Spiking Neural Networks with Backpropagation
Spiking Neural Networks (SNNs) are being explored for their potential en...
read it

sBSNN: StochasticBits Enabled Binary Spiking Neural Network with OnChip Learning for Energy Efficient Neuromorphic Computing at the Edge
In this work, we propose stochastic Binary Spiking Neural Network (sBSNN...
read it

RMPSNN: Residual Membrane Potential Neuron for Enabling Deeper HighAccuracy and LowLatency Spiking Neural Network
Spiking Neural Networks (SNNs) have recently attracted significant resea...
read it

RMPSNNs: Residual Membrane Potential Neuron for Enabling Deeper HighAccuracy and LowLatency Spiking Neural Networks
Spiking Neural Networks (SNNs) have recently attracted significant resea...
read it

Relevantfeatures based Auxiliary Cells for Energy Efficient Detection of Natural Errors
Deep neural networks have demonstrated stateoftheart performance on m...
read it

Gradual Channel Pruning while Training using Feature Relevance Scores for Convolutional Neural Networks
The enormous inference cost of deep neural networks can be scaled down b...
read it

Structured Compression and Sharing of Representational Space for Continual Learning
Humans are skilled at learning adaptively and efficiently throughout the...
read it

PANTHER: A Programmable Architecture for Neural Network Training Harnessing Energyefficient ReRAM
The wide adoption of deep neural networks has been accompanied by everi...
read it

Towards Scalable, Efficient and Accurate Deep Spiking Neural Networks with Backward Residual Connections, Stochastic Softmax and Hybridization
Spiking Neural Networks (SNNs) may offer an energyefficient alternative...
read it

PABO: Pseudo AgentBased MultiObjective Bayesian Hyperparameter Optimization for Efficient Neural Accelerator Design
The ever increasing computational cost of Deep Neural Networks (DNN) and...
read it

Reinforcement Learning with LowComplexity Liquid State Machines
We propose reinforcement learning on simple networks consisting of rando...
read it

PCAdriven Hybrid network design for enabling Intelligence at the Edge
The recent advent of IOT has increased the demand for enabling AIbased ...
read it

Synthesizing Images from SpatioTemporal Representations using Spikebased Backpropagation
Spiking neural networks (SNNs) offer a promising alternative to current ...
read it

Evaluating the Stability of Recurrent Neural Models during Training with Eigenvalue Spectra Analysis
We analyze the stability of recurrent networks, specifically, reservoir ...
read it

A Comprehensive Analysis on Adversarial Robustness of Spiking Neural Networks
In this era of machine learning models, their functionality is being thr...
read it

Enabling Spikebased Backpropagation in Stateoftheart Deep Neural Network Architectures
Spiking Neural Networks (SNNs) has recently emerged as a prominent neura...
read it

ReStoCNet: Residual Stochastic Binary Convolutional Spiking Neural Network for MemoryEfficient Neuromorphic Computing
In this work, we propose ReStoCNet, a residual stochastic multilayer con...
read it

Stimulating STDP to Exploit Locality for Lifelong Learning without Catastrophic Forgetting
Stochastic gradient descent requires that training samples be drawn from...
read it

Discretization based Solutions for Secure Machine Learning against Adversarial Attacks
Adversarial examples are perturbed inputs that are designed (from a deep...
read it

Efficient Hybrid Network Architectures for Extremely Quantized Neural Networks Enabling Intelligence at the Edge
The recent advent of `Internet of Things' (IOT) has increased the demand...
read it

PUMA: A Programmable Ultraefficient Memristorbased Accelerator for Machine Learning Inference
Memristor crossbars are circuits capable of performing analog matrixvec...
read it

A Low Effort Approach to Structured CNN Design Using PCA
Deep learning models hold state of the art performance in many fields, y...
read it

RxCaffe: Framework for evaluating and training Deep Neural Networks on Resistive Crossbars
Deep Neural Networks (DNNs) are widely used to perform machine learning ...
read it

Explainable Learning: Implicit Generative Modelling during Training for Adversarial Robustness
We introduce Explainable Learning ,ExL, an approach for training neural ...
read it

Exploiting Inherent ErrorResiliency of Neuromorphic Computing to achieve Extreme EnergyEfficiency through MixedSignal Neurons
Neuromorphic computing, inspired by the brain, promises extreme efficien...
read it

TreeCNN: A Deep Convolutional Neural Network for Lifelong Learning
In recent years, Convolutional Neural Networks (CNNs) have shown remarka...
read it

Going Deeper in Spiking Neural Networks: VGG and Residual Architectures
Over the past few years, Spiking Neural Networks (SNNs) have become popu...
read it

Deep learning for wordlevel handwritten Indic script identification
We propose a novel method that uses convolutional neural networks (CNNs)...
read it

Chaosguided Input Structuring for Improved Learning in Recurrent Neural Networks
Anatomical studies demonstrate that brain reformats input information to...
read it

Incremental Learning in Deep Convolutional Neural Networks Using Partial Network Sharing
Deep convolutional neural network (DCNN) based supervised learning is a ...
read it

An EnergyEfficient MixedSignal Neuron for Inherently ErrorResilient Neuromorphic Systems
This work presents the design and analysis of a mixedsignal neuron (MS...
read it

STDP Based Pruning of Connections and Weight Quantization in Spiking Neural Networks for Energy Efficient Recognition
Spiking Neural Networks (SNNs) with a large number of weights and varied...
read it

TraNNsformer: Neural Network Transformation for Memristive Crossbar based Neuromorphic System Design
Implementation of Neuromorphic Systems using post Complementary MetalOx...
read it

VoltageDriven DomainWall Motion based NeuroSynaptic Devices for Dynamic Online Learning
Conventional vonNeumann computing models have achieved remarkable feats...
read it

Gabor Filter Assisted Energy Efficient Fast Learning Convolutional Neural Networks
Convolutional Neural Networks (CNN) are being increasingly used in compu...
read it

ASP: Learning to Forget with Adaptive Synaptic Plasticity in Spiking Neural Networks
A fundamental feature of learning in animals is the "ability to forget" ...
read it

Convolutional Spike Timing Dependent Plasticity based Feature Learning in Spiking Neural Networks
Braininspired learning models attempt to mimic the cortical architectur...
read it

RESPARC: A Reconfigurable and EnergyEfficient Architecture with Memristive Crossbars for Deep Spiking Neural Networks
Neuromorphic computing using postCMOS technologies is gaining immense p...
read it