7 papers
Exploiting Heterogeneity in Timescales for Sparse Recurrent Spiking Neural Networks for Energy-Efficient Edge Computing
Biswadeep Chakraborty, Saibal Mukhopadhyay
Spiking Neural Networks (SNNs) represent the forefront of neuromorphic computing, promising energy-efficient and biologically plausible models for complex tasks. This paper weaves…
Towards Robust Real-Time Hardware-based Mobile Malware Detection using Multiple Instance Learning Formulation
Harshit Kumar, Sudarshan Sharma, Biswadeep Chakraborty +1
This study introduces RT-HMD, a Hardware-based Malware Detector (HMD) for mobile devices, that refines malware representation in segmented time-series through a Multiple Instance L…
Topological Representations of Heterogeneous Learning Dynamics of Recurrent Spiking Neural Networks
Biswadeep Chakraborty, Saibal Mukhopadhyay
Spiking Neural Networks (SNNs) have become an essential paradigm in neuroscience and artificial intelligence, providing brain-inspired computation. Recent advances in literature ha…
Sparse Spiking Neural Network: Exploiting Heterogeneity in Timescales for Pruning Recurrent SNN
Biswadeep Chakraborty, Beomseok Kang, Harshit Kumar +1
Recurrent Spiking Neural Networks (RSNNs) have emerged as a computationally efficient and brain-inspired learning model. The design of sparse RSNNs with fewer neurons and synapses…
STEMFold: Stochastic Temporal Manifold for Multi-Agent Interactions in the Presence of Hidden Agents
Hemant Kumawat, Biswadeep Chakraborty, Saibal Mukhopadhyay
Learning accurate, data-driven predictive models for multiple interacting agents following unknown dynamics is crucial in many real-world physical and social systems. In many scena…
Brain-Inspired Spiking Neural Network for Online Unsupervised Time Series Prediction
Biswadeep Chakraborty, Saibal Mukhopadhyay
Energy and data-efficient online time series prediction for predicting evolving dynamical systems are critical in several fields, especially edge AI applications that need to updat…