no code implementations • 28 Jan 2024 • Lakshmi Annamalai, Chetan Singh Thakur
Bio-inspired Address Event Representation (AER) sensors have attracted significant popularity owing to their low power consumption, high sparsity, and high temporal resolution.
no code implementations • 10 Jun 2023 • Adithya Krishna, Srikanth Rohit Nudurupati, Chandana D G, Pritesh Dwivedi, André van Schaik, Mahesh Mehendale, Chetan Singh Thakur
In this paper, we present RAMAN, a Re-configurable and spArse tinyML Accelerator for infereNce on edge, architected to exploit the sparsity to reduce area (storage), power as well as latency.
no code implementations • 27 Apr 2023 • Madhuvanthi Srivatsav R, Shantanu Chakrabartty, Chetan Singh Thakur
Address-Event-Representation (AER) is a spike-routing protocol that allows the scaling of neuromorphic and spiking neural network (SNN) architectures to a size that is comparable to that of digital neural network architectures.
no code implementations • 24 Apr 2023 • Abhishek Ramdas Nair, Pallab Kumar Nath, Shantanu Chakrabartty, Chetan Singh Thakur
Wildlife conservation using continuous monitoring of environmental factors and biomedical classification, which generate a vast amount of sensor data, is a challenge due to limited bandwidth in the case of remote monitoring.
no code implementations • 15 Sep 2022 • Lakshmi Annamalai, Chetan Singh Thakur
Batch normalization is widely used in deep learning to normalize intermediate activations.
no code implementations • 11 May 2022 • Pratik Kumar, Ankita Nandi, Shantanu Chakrabartty, Chetan Singh Thakur
Analog computing is attractive compared to digital computing due to its potential for achieving higher computational density and higher energy efficiency.
no code implementations • 10 Feb 2022 • Pratik Kumar, Ankita Nandi, Shantanu Chakrabartty, Chetan Singh Thakur
In this paper, we demonstrate the implementation of bias-scalable approximate analog computing circuits using the generalization of the margin-propagation principle called shape-based analog computing (S-AC).
no code implementations • 11 Sep 2021 • Abhishek Ramdas Nair, Shantanu Chakrabartty, Chetan Singh Thakur
We present a novel in-filter computing framework that can be used for designing ultra-light acoustic classifiers for use in smart internet-of-things (IoTs).
no code implementations • 3 Jun 2021 • Abhishek Ramdas Nair, Pallab Kumar Nath, Shantanu Chakrabartty, Chetan Singh Thakur
We present a novel framework for designing multiplierless kernel machines that can be used on resource-constrained platforms like intelligent edge devices.
no code implementations • 10 May 2021 • Lakshmi Annamalai, Vignesh Ramanathan, Chetan Singh Thakur
Compared to competing supervised approaches, ours is a task-agnostic approach ideally suited for the event domain, where task specific labeled data is scarce.
no code implementations • 27 Feb 2020 • Jamal Lottier Molin, Chetan Singh Thakur, Ralph Etienne-Cummings, Ernst Niebur
The ability to attend to salient regions of a visual scene is an innate and necessary preprocessing step for both biological and engineered systems performing high-level visual tasks (e. g. object detection, tracking, and classification).
no code implementations • 18 Dec 2019 • Yeshwanth Ravi Theja Bethi, Sathyaprakash Narayanan, Venkat Rangan, Chetan Singh Thakur
Though cameras that perform compressive sensing save a lot of bandwidth at the time of sampling and minimize the memory required to store videos, we cannot do much in terms of processing until the videos are reconstructed to the original frames.
no code implementations • 21 Nov 2019 • Lakshmi Annamalai, Anirban Chakraborty, Chetan Singh Thakur
Event-based cameras are bio-inspired novel sensors that asynchronously record changes in illumination in the form of events, thus resulting in significant advantages over conventional cameras in terms of low power utilization, high dynamic range, and no motion blur.
no code implementations • 5 Oct 2019 • Nazreen P. M., Shantanu Chakrabartty, Chetan Singh Thakur
This is because at the fundamental level, neural network and machine learning operations extensively use MVM operations and hardware compilers exploit the inherent parallelism in MVM operations to achieve hardware acceleration on GPUs and FPGAs.
no code implementations • 24 May 2019 • Sathyaprakash Narayanan, Yeshwanth Bethi, Chetan Singh Thakur
The first one is sparsity which requires the signal to be sparse in some domain.
no code implementations • 23 May 2018 • Chetan Singh Thakur, Jamal Molin, Gert Cauwenberghs, Giacomo Indiveri, Kundan Kumar, Ning Qiao, Johannes Schemmel, Runchun Wang, Elisabetta Chicca, Jennifer Olson Hasler, Jae-sun Seo, Shimeng Yu, Yu Cao, André van Schaik, Ralph Etienne-Cummings
Neuromorphic engineering (NE) encompasses a diverse range of approaches to information processing that are inspired by neurobiological systems, and this feature distinguishes neuromorphic systems from conventional computing systems.
no code implementations • 8 Mar 2018 • Runchun Wang, Chetan Singh Thakur, Andre van Schaik
This paper presents a massively parallel and scalable neuromorphic cortex simulator designed for simulating large and structurally connected spiking neural networks, such as complex models of various areas of the cortex.
no code implementations • 13 Mar 2016 • Runchun Wang, Chetan Singh Thakur, Tara Julia Hamilton, Jonathan Tapson, André van Schaik
The decay generator will then generate an exponential decay, which will be used by the STDP adaptor to perform the weight adaption.
no code implementations • 3 Sep 2015 • Runchun Wang, Chetan Singh Thakur, Tara Julia Hamilton, Jonathan Tapson, Andre van Schaik
We present an analogue Very Large Scale Integration (aVLSI) implementation that uses first-order lowpass filters to implement a conductance-based silicon neuron for high-speed neuromorphic systems.
no code implementations • 3 Sep 2015 • Ying Xu, Chetan Singh Thakur, Tara Julia Hamilton, Jonathan Tapson, Runchun Wang, Andre van Schaik
The architecture consists of an analogue chip and a control module.
1 code implementation • 21 Jul 2015 • Runchun Wang, Chetan Singh Thakur, Tara Julia Hamilton, Jonathan Tapson, Andre van Schaik
The architecture is not limited to handwriting recognition, but is generally applicable as an extremely fast pattern recognition processor for various kinds of patterns such as speech and images.
no code implementations • 10 Jul 2015 • Chetan Singh Thakur, Runchun Wang, Tara Julia Hamilton, Jonathan Tapson, Andre van Schaik
Additionally, we characterise each neuron and discuss the statistical variability of its tuning curve that arises due to random device mismatch, a desirable property for the learning capability of the TAB.
no code implementations • 11 May 2015 • Chetan Singh Thakur, Runchun Wang, Saeed Afshar, Gregory Cohen, Tara Julia Hamilton, Jonathan Tapson, Andre van Schaik
We propose a sign-based online learning (SOL) algorithm for a neuromorphic hardware framework called Trainable Analogue Block (TAB).
no code implementations • 2 Mar 2015 • Chetan Singh Thakur, Tara Julia Hamilton, Runchun Wang, Jonathan Tapson, André van Schaik
These neuronal populations are characterised by a diverse distribution of tuning curves, ensuring that the entire range of input stimuli is encoded.
no code implementations • 2 Mar 2015 • Chetan Singh Thakur, Tara Julia Hamilton, Jonathan Tapson, Richard F. Lyon, André van Schaik
Here, we implement the Cascade of Asymmetric Resonators (CAR) model of the cochlea on an FPGA.