A survey on hyperdimensional computing aka vector symbolic architectures, part ii: Applications, cognitive models, and challenges

D Kleyko, D Rachkovskij, E Osipov, A Rahimi - ACM Computing Surveys, 2023 - dl.acm.org
This is Part II of the two-part comprehensive survey devoted to a computing framework most
commonly known under the names Hyperdimensional Computing and Vector Symbolic …

Vector symbolic architectures as a computing framework for emerging hardware

D Kleyko, M Davies, EP Frady, P Kanerva… - Proceedings of the …, 2022 - ieeexplore.ieee.org
This article reviews recent progress in the development of the computing framework vector
symbolic architectures (VSA)(also known as hyperdimensional computing). This framework …

Advancing neuromorphic computing with loihi: A survey of results and outlook

M Davies, A Wild, G Orchard… - Proceedings of the …, 2021 - ieeexplore.ieee.org
Deep artificial neural networks apply principles of the brain's information processing that led
to breakthroughs in machine learning spanning many problem domains. Neuromorphic …

Diet-snn: A low-latency spiking neural network with direct input encoding and leakage and threshold optimization

N Rathi, K Roy - IEEE Transactions on Neural Networks and …, 2021 - ieeexplore.ieee.org
Bioinspired spiking neural networks (SNNs), operating with asynchronous binary signals (or
spikes) distributed over time, can potentially lead to greater computational efficiency on …

Diet-snn: Direct input encoding with leakage and threshold optimization in deep spiking neural networks

N Rathi, K Roy - arxiv preprint arxiv:2008.03658, 2020 - arxiv.org
Bio-inspired spiking neural networks (SNNs), operating with asynchronous binary signals
(or spikes) distributed over time, can potentially lead to greater computational efficiency on …

A survey on neuromorphic computing: Models and hardware

A Shrestha, H Fang, Z Mei, DP Rider… - IEEE Circuits and …, 2022 - ieeexplore.ieee.org
The explosion of “big data” applications imposes severe challenges of speed and scalability
on traditional computer systems. As the performance of traditional Von Neumann machines …

Optimized spiking neurons can classify images with high accuracy through temporal coding with two spikes

C Stöckl, W Maass - Nature Machine Intelligence, 2021 - nature.com
Spike-based neuromorphic hardware promises to reduce the energy consumption of image
classification and other deep-learning applications, particularly on mobile phones and other …

Beyond classification: Directly training spiking neural networks for semantic segmentation

Y Kim, J Chough, P Panda - Neuromorphic Computing and …, 2022 - iopscience.iop.org
Spiking neural networks (SNNs) have recently emerged as the low-power alternative to
artificial neural networks (ANNs) because of their sparse, asynchronous, and binary event …

Brain-inspired multimodal hybrid neural network for robot place recognition

F Yu, Y Wu, S Ma, M Xu, H Li, H Qu, C Song, T Wang… - Science Robotics, 2023 - science.org
Place recognition is an essential spatial intelligence capability for robots to understand and
navigate the world. However, recognizing places in natural environments remains a …

Variable binding for sparse distributed representations: Theory and applications

EP Frady, D Kleyko, FT Sommer - IEEE Transactions on Neural …, 2021 - ieeexplore.ieee.org
Variable binding is a cornerstone of symbolic reasoning and cognition. But how binding can
be implemented in connectionist models has puzzled neuroscientists, cognitive …