paper-with-me

홈 › Papers

Principal Components for Neural Network Initialization

2025-01-31 · Nhan Phan, Thu Nguyen, Pål Halvorsen, Michael A. Riegler

Principal Component Analysis (PCA) is a commonly used tool for dimension reduction and denoising. Therefore, it is also widely used on the data prior to training a neural network. However, this approach can complicate the explanation of explainable AI (XAI) methods for the decision of the model. In this work, we analyze the potential issues with this approach and propose Principal Components-based Initialization (PCsInit), a strategy to incorporate PCA into the first layer of a neural network via initialization of the first layer in the network with the principal components, and its two variants PCsInit-Act and PCsInit-Sub. Explanations using these strategies are as direct and straightforward as for neural networks and are simpler than using PCA prior to training a neural network on the principal components. Moreover, as will be illustrated in the experiments, such training strategies can also allow further improvement of training via backpropagation.

📄 PDF Abstract BibTeX arXiv:2501.19114

Code (1)

pthnhan/pcsinit 공식 구현 pytorch

Tasks

DenoisingDimensionality Reduction

Methods 이 논문이 사용한 방법론

PCA Principle Components Analysis (PCA) is an unsupervised method primary used for dimensionality reduction within machine learning. PCA is calculated via a singular value…

Similar Papers 제목 키워드 기반

Initialization of Self-Organizing Maps: Principal Components Versus Random Initialization. A Case Study

2012-10-22 · A. A. Akinduko, E. M. Mirkes

The performance of the Self-Organizing Map (SOM) algorithm is dependent on the initial weights of the map. The different initialization methods can broadly be classified into random and data analysis based initialization…

Least but not Last: Fine-tuning Intermediate Principal Components for Better Performance-Forgetting Trade-Offs

2026-02-03 · Alessio Quercia, Arya Bangun, Ira Assent, Hanno Scharr arxiv

Low-Rank Adaptation (LoRA) methods have emerged as crucial techniques for adapting large pre-trained models to downstream tasks under computational and memory constraints. However, they face a fundamental challenge in ba…

Continual Learning

Convergence Analysis and Implicit Regularization of Feedback Alignment for Deep Linear Networks

2021-10-20 · Manuela Girotti, Ioannis Mitliagkas, Gauthier Gidel

We theoretically analyze the Feedback Alignment (FA) algorithm, an efficient alternative to backpropagation for training neural networks. We provide convergence guarantees with rates for deep linear networks for both con…

Incremental Learning

Transfer learning for predicting source terms of principal component transport in chemically reactive flow

2023-12-01 · Ki Sung Jung, Tarek Echekki, Jacqueline H. Chen, Mohammad Khalil

The objective of this study is to evaluate whether the number of requisite training samples can be reduced with the use of various transfer learning models for predicting, for example, the chemical source terms of the da…

Transfer Learning

Algorithmic Regularization in Model-free Overparametrized Asymmetric Matrix Factorization

2022-03-06 · Liwei Jiang, Yudong Chen, Lijun Ding

We study the asymmetric matrix factorization problem under a natural nonconvex formulation with arbitrary overparametrization. The model-free setting is considered, with minimal assumption on the rank or singular values …