paper-with-me

홈 › Papers

DNArch: Learning Convolutional Neural Architectures by Backpropagation

2023-02-10 · David W. Romero, Neil Zeghidour

We present Differentiable Neural Architectures (DNArch), a method that jointly learns the weights and the architecture of Convolutional Neural Networks (CNNs) by backpropagation. In particular, DNArch allows learning (i) the size of convolutional kernels at each layer, (ii) the number of channels at each layer, (iii) the position and values of downsampling layers, and (iv) the depth of the network. To this end, DNArch views neural architectures as continuous multidimensional entities, and uses learnable differentiable masks along each dimension to control their size. Unlike existing methods, DNArch is not limited to a predefined set of possible neural components, but instead it is able to discover entire CNN architectures across all feasible combinations of kernel sizes, widths, depths and downsampling. Empirically, DNArch finds performant CNN architectures for several classification and dense prediction tasks on sequential and image data. When combined with a loss term that controls the network complexity, DNArch constrains its search to architectures that respect a predefined computational budget during training.

📄 PDF Abstract BibTeX arXiv:2302.05400

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Scalable Forward-Forward Algorithm

2025-01-06 · Andrii Krutsylo

We propose a scalable Forward-Forward (FF) algorithm that eliminates the need for backpropagation by training each layer separately. Unlike backpropagation, FF avoids backward gradients and can be more modular and memory…

Transfer Learning

Learning on tree architectures outperforms a convolutional feedforward network

2022-11-21 · Yuval Meir, Itamar Ben-Noam, Yarden Tzach, Shiri Hodassman 외

Advanced deep learning architectures consist of tens of fully connected and convolutional hidden layers, currently extended to hundreds, are far from their biological realization. Their implausible biological dynamics re…

Deep Learning

Biological Plausibility and Representational Alignment of Feedback Alignment in Convolutional Networks

2026-05-08 · Jake Lance, Larry Kieu arxiv

The feedback alignment (FA) algorithm offers a biologically plausible alternative to backpropagation (BP) for training neural networks yet notably fails to scale to convolutional architectures. Modifications have been pr…

Deep learning: Technical introduction

2017-09-05 · Thomas Epelbaum

This note presents in a technical though hopefully pedagogical way the three most common forms of neural network architectures: Feedforward, Convolutional and Recurrent. For each network, their fundamental building block…

Deep Learning

Forward Only Learning for Orthogonal Neural Networks of any Depth

2025-12-19 · Paul Caillon, Alex Colagrande, Erwan Fagnou, Blaise Delattre 외 arxiv

Backpropagation is still the de facto algorithm used today to train neural networks. With the exponential growth of recent architectures, the computational cost of this algorithm also becomes a burden. The recent PEPITA …