paper-with-me

홈 › Papers

On improving deep learning generalization with adaptive sparse connectivity

2019-06-27 · Shiwei Liu, Decebal Constantin Mocanu, Mykola Pechenizkiy

Large neural networks are very successful in various tasks. However, with limited data, the generalization capabilities of deep neural networks are also very limited. In this paper, we empirically start showing that intrinsically sparse neural networks with adaptive sparse connectivity, which by design have a strict parameter budget during the training phase, have better generalization capabilities than their fully-connected counterparts. Besides this, we propose a new technique to train these sparse models by combining the Sparse Evolutionary Training (SET) procedure with neurons pruning. Operated on MultiLayer Perceptron (MLP) and tested on 15 datasets, our proposed technique zeros out around 50% of the hidden neurons during training, while having a linear number of parameters to optimize with respect to the number of neurons. The results show a competitive classification and generalization performance.

📄 PDF Abstract BibTeX arXiv:1906.11626

Code (1)

dcmocanu/sparse-evolutionary-artificial-neural-networks 공식 구현 tf

Tasks

Deep Learning

Similar Papers 제목 키워드 기반

Does Sparse Connectivity Improve Generalization? Convolutional Networks Below the Edge of Stability

2026-03-05 · Tongtong Liang, Esha Singh, Rahul Parhi, Alexander Cloninger 외 arxiv

Gradient descent on overparameterized neural networks typically operates at the Edge of Stability (EoS), where the largest Hessian eigenvalue hovers around a step-size-dependent threshold. We study how sparse connectivit…

A Novel Approach to Sparse Inverse Covariance Estimation Using Transform Domain Updates and Exponentially Adaptive Thresholding

2018-11-16 · Ashkan Esmaeili, Farokh Marvasti

Sparse Inverse Covariance Estimation (SICE) is useful in many practical data analyses. Recovering the connectivity, non-connectivity graph of covariates is classified amongst the most important data mining and learning p…

Sparsity Winning Twice: Better Robust Generalization from More Efficient Training

2022-02-20 · ICLR 2022 4 · Tianlong Chen, Zhenyu Zhang, Pengjun Wang, Santosh Balachandra 외

Recent studies demonstrate that deep networks, even robustified by the state-of-the-art adversarial training (AT), still suffer from large robust generalization gaps, in addition to the much more expensive training costs…

Topological Insights into Sparse Neural Networks

2020-06-24 · Shiwei Liu, Tim Van der Lee, Anil Yaman, Zahra Atashgahi 외

Sparse neural networks are effective approaches to reduce the resource requirements for the deployment of deep neural networks. Recently, the concept of adaptive sparse connectivity, has emerged to allow training sparse …

Biologically Inspired Mechanisms for Facilitating Grokking in Multilayer Perceptrons

2026-08-28 · Florin Leon arxiv

Grokking is a delayed transition from memorization to generalization that is often accompanied by substantial reorganization of internal representations. This paper studies whether biologically inspired mechanisms, many …