Salvato in:
Dettagli Bibliografici
Autore principale: Bouhsine, Taha
Natura: Preprint
Pubblicazione: 2024
Soggetti:
Accesso online:https://arxiv.org/abs/2411.08085
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866916502248095744
author Bouhsine, Taha
author_facet Bouhsine, Taha
contents We introduce a yat-product-powered neural network, the Neural Matter Network (NMN), a breakthrough in deep learning that achieves non-linear pattern recognition without activation functions. Our key innovation relies on the yat-product and yat-product, which naturally induces non-linearity by projecting inputs into a pseudo-metric space, eliminating the need for traditional activation functions while maintaining only a softmax layer for final class probability distribution. This approach simplifies network architecture and provides unprecedented transparency into the network's decision-making process. Our comprehensive empirical evaluation across different datasets demonstrates that NMN consistently outperforms traditional MLPs. The results challenge the assumption that separate activation functions are necessary for effective deep-learning models. The implications of this work extend beyond immediate architectural benefits, by eliminating intermediate activation functions while preserving non-linear capabilities, yat-MLP establishes a new paradigm for neural network design that combines simplicity with effectiveness. Most importantly, our approach provides unprecedented insights into the traditionally opaque "black-box" nature of neural networks, offering a clearer understanding of how these models process and classify information.
format Preprint
id arxiv_https___arxiv_org_abs_2411_08085
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Deep Learning 2.0: Artificial Neurons That Matter -- Reject Correlation, Embrace Orthogonality
Bouhsine, Taha
Machine Learning
Computer Vision and Pattern Recognition
General Topology
We introduce a yat-product-powered neural network, the Neural Matter Network (NMN), a breakthrough in deep learning that achieves non-linear pattern recognition without activation functions. Our key innovation relies on the yat-product and yat-product, which naturally induces non-linearity by projecting inputs into a pseudo-metric space, eliminating the need for traditional activation functions while maintaining only a softmax layer for final class probability distribution. This approach simplifies network architecture and provides unprecedented transparency into the network's decision-making process. Our comprehensive empirical evaluation across different datasets demonstrates that NMN consistently outperforms traditional MLPs. The results challenge the assumption that separate activation functions are necessary for effective deep-learning models. The implications of this work extend beyond immediate architectural benefits, by eliminating intermediate activation functions while preserving non-linear capabilities, yat-MLP establishes a new paradigm for neural network design that combines simplicity with effectiveness. Most importantly, our approach provides unprecedented insights into the traditionally opaque "black-box" nature of neural networks, offering a clearer understanding of how these models process and classify information.
title Deep Learning 2.0: Artificial Neurons That Matter -- Reject Correlation, Embrace Orthogonality
topic Machine Learning
Computer Vision and Pattern Recognition
General Topology
url https://arxiv.org/abs/2411.08085