Deep Learning 2.0: Artificial Neurons That Matter -- Reject Correlation, Embrace Orthogonality

TL;DR

This paper introduces the Neural Matter Network (NMN), a novel deep learning architecture that achieves non-linear pattern recognition without activation functions, using yat-products to simplify design and enhance interpretability.

Contribution

The work presents a new neural network architecture that eliminates activation functions by leveraging yat-products, offering improved transparency and consistent performance across datasets.

Findings

NMN outperforms traditional MLPs on various datasets.

Eliminating activation functions does not compromise non-linear modeling capabilities.

Provides new insights into neural network interpretability.

Abstract

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.