[PDF][PDF] Bibliography of self-organizing map (SOM) papers: 1981–1997

S Kaski, J Kangas, T Kohonen - Neural computing surveys, 1998 - cis.legacy.ics.tkk.fi
Abstract The Self-Organizing Map (SOM) algorithm has attracted an ever increasing amount
of interest among researches and practitioners in a wide variety of elds. The SOM and a …

[图书][B] Handbook of neural computation

E Fiesler, R Beale - 2020 - books.google.com
The Handbook of Neural Computation is a practical, hands-on guide to the design and
implementation of neural networks used by scientists and engineers to tackle difficult and/or …

[PDF][PDF] Learning spiking neural systems with the event-driven forward-forward process

A Ororbia - arXiv preprint arXiv:2303.18187, 2023 - files.osf.io
We develop a novel credit assignment algorithm for information processing with spiking
neurons without requiring feedback synapses. Specifically, we propose an event-driven …

Mortal computation: A foundation for biomimetic intelligence

A Ororbia, K Friston - arXiv preprint arXiv:2311.09589, 2023 - arxiv.org
This review motivates and synthesizes research efforts in neuroscience-inspired artificial
intelligence and biomimetic computing in terms of mortal computation. Specifically, we …

Contrastive-signal-dependent plasticity: Forward-forward learning of spiking neural systems

A Ororbia - arXiv preprint arXiv:2303.18187, 2023 - arxiv.org
We develop a neuro-mimetic architecture, composed of spiking neuronal units, where
individual layers of neurons operate in parallel and adapt their synaptic efficacies without …

[图书][B] Optical neural networks

C Denz - 2013 - books.google.com
In recent years, there has been a rapid expansion in the field of nonlinear optics as weIl as
in the field of neural computing. Up to date, no one would doubt that nonlinear optics is one …

Perspective on photonic neuromorphic computing

E Goi, M Gu - Neuromorphic Photonic Devices and Applications, 2024 - Elsevier
Bioinspired neuromorphic algorithms can process information more rapidly and more
accurately than conventional algorithms, in the attempt to achieve brain-like capacity and …

Quantitative comparison of the computational complexity of optical, digital and hybrid neural network architectures for image classification tasks

M Chen, S Schoenhardt, M Gu, E Goi - Optics Express, 2023 - opg.optica.org
By implementing neuromorphic paradigms in processing visual information, machine
learning became crucial in an ever-increasing number of applications of our everyday lives …

Interpreting Restricted Boltzmann Machines from Optics Theory Perspectives

P Guo - 2023 IEEE Symposium Series on Computational …, 2023 - ieeexplore.ieee.org
Currently, lack of interpretability (or explainability) is one of the major drawbacks for artificial
intelligence (AI) models. When we intend to build a physical artificial intelligence (PAI) …

Optical learning neural network with a Pockels readout optical modulator

M Mori, Y Yagai, T Yatagai, M Watanabe - Applied optics, 1998 - opg.optica.org
We have constructed an optical neural-network system with learning capability by using a
Pockels readout optical modulator. The system has a two-dimensional structure that permits …