Emerging artificial neuron devices for probabilistic computing

Z Li, X Geng, J Wang, F Zhuge - Frontiers in Neuroscience, 2021 - frontiersin.org
In recent decades, artificial intelligence has been successively employed in the fields of
finance, commerce, and other industries. However, imitating high-level brain functions, such …

Fast and energy-efficient neuromorphic deep learning with first-spike times

J Göltz, L Kriener, A Baumbach, S Billaudelle… - Nature machine …, 2021 - nature.com
For a biological agent operating under environmental pressure, energy consumption and
reaction times are of critical importance. Similarly, engineered systems are optimized for …

An overview of brain-like computing: Architecture, applications, and future trends

W Ou, S **ao, C Zhu, W Han, Q Zhang - Frontiers in neurorobotics, 2022 - frontiersin.org
With the development of technology, Moore's law will come to an end, and scientists are
trying to find a new way out in brain-like computing. But we still know very little about how …

Accelerated analog neuromorphic computing

J Schemmel, S Billaudelle, P Dauer, J Weis - Analog Circuits for Machine …, 2021 - Springer
This chapter presents the concepts behind the BrainScales (BSS) accelerated analog
neuromorphic computing architecture. It describes the second-generation BrainScales-2 …

Evolving interpretable plasticity for spiking networks

J Jordan, M Schmidt, W Senn, MA Petrovici - Elife, 2021 - elifesciences.org
Continuous adaptation allows survival in an ever-changing world. Adjustments in the
synaptic coupling strength between neurons are essential for this capability, setting us apart …

Fast and deep neuromorphic learning with first-spike coding

J Göltz, A Baumbach, S Billaudelle, AF Kungl… - Proceedings of the …, 2020 - dl.acm.org
For a biological agent operating under environmental pressure, energy consumption and
reaction times are of critical importance. Similarly, engineered systems also strive for short …

Sequence learning, prediction, and replay in networks of spiking neurons

Y Bouhadjar, DJ Wouters, M Diesmann… - PLOS Computational …, 2022 - journals.plos.org
Sequence learning, prediction and replay have been proposed to constitute the universal
computations performed by the neocortex. The Hierarchical Temporal Memory (HTM) …

Multilevel interpretability of artificial neural networks: leveraging framework and methods from neuroscience

Z He, J Achterberg, K Collins, K Nejad… - arxiv preprint arxiv …, 2024 - arxiv.org
As deep learning systems are scaled up to many billions of parameters, relating their
internal structure to external behaviors becomes very challenging. Although daunting, this …

Chaotic neural dynamics facilitate probabilistic computations through sampling

Y Terada, T Toyoizumi - Proceedings of the National …, 2024 - National Acad Sciences
Cortical neurons exhibit highly variable responses over trials and time. Theoretical works
posit that this variability arises potentially from chaotic network dynamics of recurrently …

The probabilistic world

C Wetterich - arxiv preprint arxiv:2011.02867, 2020 - Springer
This book addresses fundamental questions about our understanding of the quantum world.
It explains the mysteries of quantum mechanics by a novel approach to physics based on …