Biology-inspired joint distribution neurons based on Hierarchical Correlation Reconstruction allowing for multidirectional neural networks Article Swipe

MAKE IMPACT

Jarek Duda · YOU? · · 2024 · Open Access · · DOI: https://doi.org/10.48550/arxiv.2405.05097

Biological neural networks seem qualitatively superior (e.g. in learning, flexibility, robustness) to current artificial like Multi-Layer Perceptron (MLP) or Kolmogorov-Arnold Network (KAN). Simultaneously, in contrast to them: biological have fundamentally multidirectional signal propagation \cite{axon}, also of probability distributions e.g. for uncertainty estimation, and are believed not being able to use standard backpropagation training \cite{backprop}. There are proposed novel artificial neurons based on HCR (Hierarchical Correlation Reconstruction) allowing to remove the above low level differences: with neurons containing local joint distribution model (of its connections), representing joint density on normalized variables as just linear combination of $(f_\mathbf{j})$ orthonormal polynomials: $ρ(\mathbf{x})=\sum_{\mathbf{j}\in B} a_\mathbf{j} f_\mathbf{j}(\mathbf{x})$ for $\mathbf{x} \in [0,1]^d$ and $B\subset \mathbb{N}^d$ some chosen basis. By various index summations of such $(a_\mathbf{j})_{\mathbf{j}\in B}$ tensor as neuron parameters, we get simple formulas for e.g. conditional expected values for propagation in any direction, like $E[x|y,z]$, $E[y|x]$, which degenerate to KAN-like parametrization if restricting to pairwise dependencies. Such HCR network can also propagate probability distributions (also joint) like $ρ(y,z|x)$. It also allows for additional training approaches, like direct $(a_\mathbf{j})$ estimation, through tensor decomposition, or more biologically plausible information bottleneck training: layers directly influencing only neighbors, optimizing content to maximize information about the next layer, and minimizing about the previous to remove noise, extract crucial information.

Type

preprint

Language

en

Landing Page

http://arxiv.org/abs/2405.05097

PDF

https://arxiv.org/pdf/2405.05097

OA Status

green

Related Works

10

OpenAlex ID

https://openalex.org/W4396817055

Raw OpenAlex JSON

OpenAlex ID

https://openalex.org/W4396817055

Canonical identifier for this work in OpenAlex

DOI

https://doi.org/10.48550/arxiv.2405.05097

Digital Object Identifier

Title

Biology-inspired joint distribution neurons based on Hierarchical Correlation Reconstruction allowing for multidirectional neural networks

Work title

Type

preprint

OpenAlex work type

Language

en

Primary language

Publication year

2024

Year of publication

Publication date

2024-05-08

Full publication date if available

Authors

Jarek Duda

List of authors in order

Landing page

https://arxiv.org/abs/2405.05097

Publisher landing page

PDF URL

https://arxiv.org/pdf/2405.05097

Direct link to full text PDF

Open access

Yes

Whether a free full text is available

OA status

green

Open access status per OpenAlex

OA URL

https://arxiv.org/pdf/2405.05097

Direct OA link when available

Concepts

Joint (building), Artificial neural network, Joint probability distribution, Correlation, Distribution (mathematics), Artificial intelligence, Computer science, Biology, Neuroscience, Statistical physics, Pattern recognition (psychology), Mathematics, Physics, Statistics, Engineering, Geometry, Mathematical analysis, Architectural engineering

Top concepts (fields/topics) attached by OpenAlex

Cited by

0

Total citation count in OpenAlex

Related works (count)

10

Other works algorithmically related by OpenAlex

Full payload