Deep Learning 2.0: Artificial Neurons That Matter -- Reject Correlation, Embrace Orthogonality
This work proposes a new paradigm for neural network design that simplifies architecture and improves transparency, potentially impacting all of ML/AI by challenging fundamental assumptions about activation functions.
The paper tackles the problem of non-linear pattern recognition in deep learning by introducing the Neural Matter Network (NMN), which uses a yat-product to eliminate activation functions while maintaining performance, and it demonstrates that NMN consistently outperforms traditional MLPs across datasets.
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.