Heterogeneous neuronal and synaptic dynamics for spike-efficient unsupervised learning: Theory and design principles
B Chakraborty, S Mukhopadhyay - arXiv preprint arXiv:2302.11618, 2023 - arxiv.org
This paper shows that the heterogeneity in neuronal and synaptic dynamics reduces the
spiking activity of a Recurrent Spiking Neural Network (RSNN) while improving prediction …
spiking activity of a Recurrent Spiking Neural Network (RSNN) while improving prediction …
Demonstrating analog inference on the brainscales-2 mobile system
Y Stradmann, S Billaudelle… - IEEE Open Journal …, 2022 - ieeexplore.ieee.org
We present the BrainScaleS-2 mobile system as a compact analog inference engine based
on the BrainScaleS-2 ASIC and demonstrate its capabilities at classifying a medical …
on the BrainScaleS-2 ASIC and demonstrate its capabilities at classifying a medical …
Brain-inspired spiking neural network for online unsupervised time series prediction
B Chakraborty, S Mukhopadhyay - 2023 International Joint …, 2023 - ieeexplore.ieee.org
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 update …
systems are critical in several fields, especially edge AI applications that need to update …
Exploiting Heterogeneity in Timescales for Sparse Recurrent Spiking Neural Networks for Energy-Efficient Edge Computing
B Chakraborty, S Mukhopadhyay - arXiv preprint arXiv:2407.06452, 2024 - arxiv.org
Spiking Neural Networks (SNNs) represent the forefront of neuromorphic computing,
promising energy-efficient and biologically plausible models for complex tasks. This paper …
promising energy-efficient and biologically plausible models for complex tasks. This paper …
Design and Analysis of Multibit Multiply and Accumulate (MAC) unit: An Analog In-Memory Computing Approach
S Ananthanarayanan, BS Reniwal… - … Conference on VLSI …, 2023 - ieeexplore.ieee.org
In-memory computing for multiplication operations is an approach towards mitigating the
overhead caused by the migration of data between the memory and the processor observed …
overhead caused by the migration of data between the memory and the processor observed …