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 …
finance, commerce, and other industries. However, imitating high-level brain functions, such …
Fast and energy-efficient neuromorphic deep learning with first-spike times
For a biological agent operating under environmental pressure, energy consumption and
reaction times are of critical importance. Similarly, engineered systems are optimized for …
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 …
trying to find a new way out in brain-like computing. But we still know very little about how …
Accelerated analog neuromorphic computing
This chapter presents the concepts behind the BrainScales (BSS) accelerated analog
neuromorphic computing architecture. It describes the second-generation BrainScales-2 …
neuromorphic computing architecture. It describes the second-generation BrainScales-2 …
Evolving interpretable plasticity for spiking networks
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 …
synaptic coupling strength between neurons are essential for this capability, setting us apart …
Fast and deep neuromorphic learning with first-spike coding
For a biological agent operating under environmental pressure, energy consumption and
reaction times are of critical importance. Similarly, engineered systems also strive for short …
reaction times are of critical importance. Similarly, engineered systems also strive for short …
Sequence learning, prediction, and replay in networks of spiking neurons
Sequence learning, prediction and replay have been proposed to constitute the universal
computations performed by the neocortex. The Hierarchical Temporal Memory (HTM) …
computations performed by the neocortex. The Hierarchical Temporal Memory (HTM) …
Multilevel interpretability of artificial neural networks: leveraging framework and methods from neuroscience
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 …
internal structure to external behaviors becomes very challenging. Although daunting, this …
Chaotic neural dynamics facilitate probabilistic computations through sampling
Cortical neurons exhibit highly variable responses over trials and time. Theoretical works
posit that this variability arises potentially from chaotic network dynamics of recurrently …
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 …
It explains the mysteries of quantum mechanics by a novel approach to physics based on …