Basabdatta Sen Bhattacharya
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Basabdatta Sen Bhattacharya has a total of 69 co-authors. Here are the top co-authors by number of shared publications:
- Damien Coyle
University of Bath
9 shared publications - Liam Philip Maguire
Ulster University
9 shared publications - Steve Furber
University of Manchester, Manchester, UK
7 shared publications - Atulya Kumar Nagar
School of Mathematics, Computer Science and Engineering, Liverpool Hope University, Liverpool, U.K.
3 shared publications - Pavan Kumar Enuganti
Birla Institute of Technology and Science (BITS) Pilani, Goa Campus
3 shared publications - Teresa Serrano-Gotarredona
Instituto de Microelectrónica de Sevilla (IMSE-CNM), CSIC and Universidad de Sevilla, Sevilla, Spain
3 shared publications
Latest Publications
- Open Access
- 17 April 2026
- Published by MDPI AG in Brain Sciences
- Vol. 16 (4) , 422
Event-Based Vision at the Edge: A Review
Spiking Neural Networks (SNNs) executed on neuromorphic hardware promise energyefficient, low-latency inference well-suited to edge deployment in size, weight, and powerconstrained environments such as autonomous vehicles, wearable devices, and unmanned aerial platforms. However, a coherent research pathway to deployment of neuromorphic devices remains elusive. This paper presents a structured review and position on the state of SNN-based vision across four interconnected dimensions: network architectures, training methodologies, event-based datasets and simulation techniques, and neuromorphic computing hardware. We survey the evolution from shallow convolutional SNNs to spiking Transformers and hybrid designs which leverage the advantages of SNNs and conventional artificial neural networks. We also examine surrogate gradient training and ANN-to-SNN conversion approaches, catalogue real-world and simulated event-based datasets, and assess the landscape of neuromorphic platforms ranging from rigid mixed-signal architectures to fully-configurable digital systems. Our analysis reveals that while each area has matured considerably in isolation, critical integration challenges persist. In particular, event-based datasets remain scarce and lack standardisation, training methodologies introduce systematic gaps relative to deployment hardware, and access to neuromorphic platforms is restricted by proprietary toolchains and limited development kit availability. We conclude that bridging these integration gaps, rather than advancing individual components alone, represents the most important and least addressed work required to realise the potential of SNN-based vision at the edge.
- 17 April 2026
- Published by MDPI AG in Brain Sciences
- Vol. 16 (4) , 422
Open AccessEvent-Based Vision at the Edge: A Review
Spiking Neural Networks (SNNs) executed on neuromorphic hardware promise energyefficient, low-latency inference well-suited to edge deployment in size, weight, and powerconstrained environments such as autonomous vehicles, wearable devices, and unmanned aerial platforms. However, a coherent research pathway to deployment of neuromorphic devices remains elusive. This paper presents a structured review and position on the state of SNN-based vision across four interconnected dimensions: network architectures, training methodologies, event-based datasets and simulation techniques, and neuromorphic computing hardware. We survey the evolution from shallow convolutional SNNs to spiking Transformers and hybrid designs which leverage the advantages of SNNs and conventional artificial neural networks. We also examine surrogate gradient training and ANN-to-SNN conversion approaches, catalogue real-world and simulated event-based datasets, and assess the landscape of neuromorphic platforms ranging from rigid mixed-signal architectures to fully-configurable digital systems. Our analysis reveals that while each area has matured considerably in isolation, critical integration challenges persist. In particular, event-based datasets remain scarce and lack standardisation, training methodologies introduce systematic gaps relative to deployment hardware, and access to neuromorphic platforms is restricted by proprietary toolchains and limited development kit availability. We conclude that bridging these integration gaps, rather than advancing individual components alone, represents the most important and least addressed work required to realise the potential of SNN-based vision at the edge.
- 12 September 2025
- Published by Springer Nature
- p. 497-508
Dopamine-Modulated Learning and Decision-Making with Neuromorphic Computing
- 12 September 2025
- Published by Springer Nature
- p. 497-508
Dopamine-Modulated Learning and Decision-Making with Neuromorphic Computing
- 21 August 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-8
A Brain-Inspired Neural Network for Image Classification
We have presented for the first time a neuromorphic network that performs image classification task successfully. The thalamus is a crucial deep brain structure that receives sensory information for processing and communicates this to the neocortex, the seat of intelligence in our brain, for perception and subsequent decisions and actions. However, replicating the very large-scale networks of the brain is challenging, not to mention the requirement of high-energy resources. Current emphasis is on building sustainable technology. In this work, we have implemented a spiking neural network of the thalamus using the recently proposed snnTorch software library that extends the capabilities of PyTorch and successfully implements gradientbased learning for spiking neural networks; tensor data structure facilitates parallel computation on GPUs. Our work demonstrates that small-scale spiking neural networks mimicking deep-brain recurrent architectures and simulated on the snnTorch platform are successful in categorising images of the MNIST and F-MNIST datasets with high accuracy of 93.72% and 74.34% respectively even in the presence of background noise.
- 21 August 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-8
A Brain-Inspired Neural Network for Image Classification
We have presented for the first time a neuromorphic network that performs image classification task successfully. The thalamus is a crucial deep brain structure that receives sensory information for processing and communicates this to the neocortex, the seat of intelligence in our brain, for perception and subsequent decisions and actions. However, replicating the very large-scale networks of the brain is challenging, not to mention the requirement of high-energy resources. Current emphasis is on building sustainable technology. In this work, we have implemented a spiking neural network of the thalamus using the recently proposed snnTorch software library that extends the capabilities of PyTorch and successfully implements gradientbased learning for spiking neural networks; tensor data structure facilitates parallel computation on GPUs. Our work demonstrates that small-scale spiking neural networks mimicking deep-brain recurrent architectures and simulated on the snnTorch platform are successful in categorising images of the MNIST and F-MNIST datasets with high accuracy of 93.72% and 74.34% respectively even in the presence of background noise.
- 28 April 2025
- Published by Wiley in WIREs Data Mining and Knowledge Discovery
- Vol. 15 (2)
Neuromorphic Computing and Applications: A Topical Review
Neuromorphic computers achieve energy efficiency by emulating brain structure and event‐driven processing that reduces energy consumption significantly. An increasing interest in this technology started in the initial years of this millennium, sparked by the awareness and concern on the ever‐increasing power demands of modern‐day computing. In current times, there are several neuromorphic computers and sensors that continue to be developed in both industry and academic research. The focus of this survey is on the neuromorphic computing applications of these devices that include brain‐inspired neural networks, brain‐inspired artificial neural networks, and Hybrid circuits comprising both artificial and brain‐inspired units of computation. Many of these applications use neuromorphic sensors as input devices. We have surveyed three specific neuromorphic computers viz. SpiNNaker, TrueNorth, Loihi, and one neuromorphic sensor viz. Dynamic vision sensor (DVS)‐based electronic retina; the demonstration of neuromorphic computing and applications using these devices far outnumbers those on the others that are currently available, which forms the basis of our choice. The applications include low‐power cognitive machine intelligence as well as neuropathological understanding and knowledge discovery. Overall, our survey identifies the potential for neuromorphic computing to provide low power, low cost, and dynamic solutions for societal and scientific problems in the not‐too‐distant future.
- 28 April 2025
- Published by Wiley in WIREs Data Mining and Knowledge Discovery
- Vol. 15 (2)
Neuromorphic Computing and Applications: A Topical Review
Neuromorphic computers achieve energy efficiency by emulating brain structure and event‐driven processing that reduces energy consumption significantly. An increasing interest in this technology started in the initial years of this millennium, sparked by the awareness and concern on the ever‐increasing power demands of modern‐day computing. In current times, there are several neuromorphic computers and sensors that continue to be developed in both industry and academic research. The focus of this survey is on the neuromorphic computing applications of these devices that include brain‐inspired neural networks, brain‐inspired artificial neural networks, and Hybrid circuits comprising both artificial and brain‐inspired units of computation. Many of these applications use neuromorphic sensors as input devices. We have surveyed three specific neuromorphic computers viz. SpiNNaker, TrueNorth, Loihi, and one neuromorphic sensor viz. Dynamic vision sensor (DVS)‐based electronic retina; the demonstration of neuromorphic computing and applications using these devices far outnumbers those on the others that are currently available, which forms the basis of our choice. The applications include low‐power cognitive machine intelligence as well as neuropathological understanding and knowledge discovery. Overall, our survey identifies the potential for neuromorphic computing to provide low power, low cost, and dynamic solutions for societal and scientific problems in the not‐too‐distant future.
- 20 April 2025
- Published by Elsevier in Computers in Biology and Medicine
- Vol. 192 (Pt A) , 110190
Neural mass modelling of brain stimulation to Alleviate Schizophrenia biomarkers in brain rhythms
- 20 April 2025
- Published by Elsevier in Computers in Biology and Medicine
- Vol. 192 (Pt A) , 110190
Neural mass modelling of brain stimulation to Alleviate Schizophrenia biomarkers in brain rhythms
- 22 September 2023
- Published by Springer Nature
- p. 363-374
Mixed-Mode Response of Nigral Dopaminergic Neurons: An in Silico Study on SpiNNaker
- 22 September 2023
- Published by Springer Nature
- p. 363-374
Mixed-Mode Response of Nigral Dopaminergic Neurons: An in Silico Study on SpiNNaker
- 22 September 2023
- Published by Springer Nature
- p. 385-396
In Silico Study of Single Synapse Dynamics Using a Three-State Kinetic Model
- 22 September 2023
- Published by Springer Nature
- p. 385-396
In Silico Study of Single Synapse Dynamics Using a Three-State Kinetic Model
- 22 September 2023
- Published by Springer Nature
- p. 394-406
Robustness of Biologically-Inspired Filter-Based ConvNet to Signal Perturbation
- 22 September 2023
- Published by Springer Nature
- p. 394-406
Robustness of Biologically-Inspired Filter-Based ConvNet to Signal Perturbation
- Open Access
- 30 July 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in TechRxiv
Assistive Chatbots for healthcare: a succinct review
Brief Survey paper on Chatbots that are designed to be of assistance in mental and physical healthcare. Focuss on the last 10 years 2013-2023, and on AI-enabled technology only.
- 30 July 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in TechRxiv
Open AccessAssistive Chatbots for healthcare: a succinct review
Brief Survey paper on Chatbots that are designed to be of assistance in mental and physical healthcare. Focuss on the last 10 years 2013-2023, and on AI-enabled technology only.
- 13 April 2023
- Published by Springer Nature
- p. 148-159
Instrumental Conditioning with Neuromodulated Plasticity on SpiNNaker
- 13 April 2023
- Published by Springer Nature
- p. 148-159
Instrumental Conditioning with Neuromodulated Plasticity on SpiNNaker