paper-with-me

홈 › Papers

Deep-RLS: A Model-Inspired Deep Learning Approach to Nonlinear PCA

2020-11-15 · Zahra Esmaeilbeig, Shahin Khobahi, Mojtaba Soltanalian

In this work, we consider the application of model-based deep learning in nonlinear principal component analysis (PCA). Inspired by the deep unfolding methodology, we propose a task-based deep learning approach, referred to as Deep-RLS, that unfolds the iterations of the well-known recursive least squares (RLS) algorithm into the layers of a deep neural network in order to perform nonlinear PCA. In particular, we formulate the nonlinear PCA for the blind source separation (BSS) problem and show through numerical analysis that Deep-RLS results in a significant improvement in the accuracy of recovering the source signals in BSS when compared to the traditional RLS algorithm.

📄 PDF Abstract BibTeX arXiv:2011.07458

Code (0)

등록된 구현이 없습니다.

Tasks

blind source separationDeep Learning

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

Physical Reservoir Computing Enabled by Solitary Waves and Biologically-Inspired Nonlinear Transformation of Input Data

2024-01-03 · Ivan S. Maksymov

Reservoir computing (RC) systems can efficiently forecast chaotic time series using nonlinear dynamical properties of an artificial neural network of random connections. The versatility of RC systems has motivated furthe…

Time Series

Transformer as a hippocampal memory consolidation model based on NMDAR-inspired nonlinearity

2023-09-21 · NeurIPS 2023 11

The hippocampus plays a critical role in learning, memory, and spatial representation, processes that depend on the NMDA receptor (NMDAR). Inspired by recent findings that compare deep learning models to the hippocampus,…

Nature-Inspired Optimization Algorithms: Challenges and Open Problems

2020-03-08 · Xin-She Yang

Many problems in science and engineering can be formulated as optimization problems, subject to complex nonlinear constraints. The solutions of highly nonlinear problems usually require sophisticated optimization algorit…

Benchmarking

Causality-Inspired Robustness for Nonlinear Models via Representation Learning

2025-05-19 · Marin Šola, Peter Bühlmann, Xinwei Shen

Distributional robustness is a central goal of prediction algorithms due to the prevalent distribution shifts in real-world data. The prediction model aims to minimize the worst-case risk among a class of distributions, …

Representation Learning

Approximation-free control based on the bioinspired reference model for suspension systems with uncertainty and unknown nonlinearity

2022-04-09 · Xiaoyan Hu, Guilin Wen, Shan Yin, Zhao Tan 외

Uncertainty and unknown nonlinearity are often inevitable in the suspension systems, which were often solved using fuzzy logic system (FLS) or neural networks (NNs). However, these methods are restricted by the structura…