paper-with-me

Papers

PHYDI: Initializing Parameterized Hypercomplex Neural Networks as Identity Functions

2023-10-11 · Matteo Mancanelli, Eleonora Grassucci, Aurelio Uncini, Danilo Comminiello

Neural models based on hypercomplex algebra systems are growing and prolificating for a plethora of applications, ranging from computer vision to natural language processing. Hand in hand with their adoption, parameterized hypercomplex neural networks (PHNNs) are growing in size and no techniques have been adopted so far to control their convergence at a large scale. In this paper, we study PHNNs convergence and propose parameterized hypercomplex identity initialization (PHYDI), a method to improve their convergence at different scales, leading to more robust performance when the number of layers scales up, while also reaching the same performance with fewer iterations. We show the effectiveness of this approach in different benchmarks and with common PHNNs with ResNets- and Transformer-based architecture. The code is available at https://github.com/ispamm/PHYDI.

📄 PDF Abstract BibTeX arXiv:2310.07612

Code (1)

ispamm/phydi 공식 구현 pytorch

Similar Papers 제목 키워드 기반

Enhancing ResNet Image Classification Performance by using Parameterized Hypercomplex Multiplication

2023-01-11 · Nazmul Shahadat, Anthony S. Maida

Recently, many deep networks have introduced hypercomplex and related calculations into their architectures. In regard to convolutional networks for classification, these enhancements have been applied to the convolution…

image-classificationImage Classification

PHNNs: Lightweight Neural Networks via Parameterized Hypercomplex Convolutions

2021-10-08 · Eleonora Grassucci, Aston Zhang, Danilo Comminiello

Hypercomplex neural networks have proven to reduce the overall number of parameters while ensuring valuable performance by leveraging the properties of Clifford algebras. Recently, hypercomplex linear layers have been fu…

Sound Event Detection

Towards Explaining Hypercomplex Neural Networks

2024-03-26 · Eleonora Lopez, Eleonora Grassucci, Debora Capriotti, Danilo Comminiello

Hypercomplex neural networks are gaining increasing interest in the deep learning community. The attention directed towards hypercomplex models originates from several aspects, spanning from purely theoretical and mathem…

Hierarchical Hypercomplex Network for Multimodal Emotion Recognition

2024-09-13 · Eleonora Lopez, Aurelio Uncini, Danilo Comminiello

Emotion recognition is relevant in various domains, ranging from healthcare to human-computer interaction. Physiological signals, being beyond voluntary control, offer reliable information for this purpose, unlike speech…

Emotion RecognitionMultimodal Emotion Recognition

Deep Axial Hypercomplex Networks

2023-01-11 · Nazmul Shahadat, Anthony S. Maida

Over the past decade, deep hypercomplex-inspired networks have enhanced feature extraction for image classification by enabling weight sharing across input channels. Recent works make it possible to improve representatio…

image-classificationImage Classification