English
Related papers

Related papers: Principles for Initialization and Architecture Sel…

200 papers

We address the efficiency issue for the construction of a deep graph neural network (GNN). The approach exploits the idea of representing each input graph as a fixed point of a dynamical system (implemented through a recurrent neural…

Machine Learning · Computer Science 2019-11-21 Claudio Gallicchio , Alessio Micheli

An emerging trend in deep learning research focuses on the applications of graph neural networks (GNNs) for mesh-based continuum mechanics simulations. Most of these learning frameworks operate on graphs wherein each edge connects two…

Fluid Dynamics · Physics 2024-10-08 Rui Gao , Indu Kant Deo , Rajeev K. Jaiman

We design and analyze a new paradigm for building supervised learning networks, driven only by local optimization rules without relying on a global error function. Traditional neural networks with a fixed topology are made up of identical…

Adaptation and Self-Organizing Systems · Physics 2024-10-04 S. Barland , L. Gil

Activation functions critically influence trainability and expressivity, and recent work has therefore explored a broad range of nonlinearities. However, widely used Gaussian i.i.d. initializations are designed to preserve activation…

Machine Learning · Computer Science 2025-12-17 Hyunwoo Lee , Hayoung Choi , Hyunju Kim

Residual Network (ResNet) is the state-of-the-art architecture that realizes successful training of really deep neural network. It is also known that good weight initialization of neural network avoids problem of vanishing/exploding…

Machine Learning · Computer Science 2017-10-16 Masato Taki

This research project studies the impact of convolutional neural networks (CNN) in image classification tasks. We explore different architectures and training configurations with the use of ReLUs, Nesterov's accelerated gradient, dropout…

Computer Vision and Pattern Recognition · Computer Science 2019-10-30 Anderson de Andrade

Let F:R^n -> R be a feedforward ReLU neural network. It is well-known that for any choice of parameters, F is continuous and piecewise (affine) linear. We lay some foundations for a systematic investigation of how the architecture of F…

Combinatorics · Mathematics 2021-12-03 J. Elisenda Grigsby , Kathryn Lindsey

How does the geometric representation of a dataset change after the application of each randomly initialized layer of a neural network? The celebrated Johnson--Lindenstrauss lemma answers this question for linear fully-connected neural…

Machine Learning · Computer Science 2022-03-08 Ido Nachum , Jan Hązła , Michael Gastpar , Anatoly Khina

Graph convolutional networks (GCNs) are a powerful deep learning approach for graph-structured data. Recently, GCNs and subsequent variants have shown superior performance in various application areas on real-world datasets. Despite their…

Machine Learning · Computer Science 2020-07-07 Ming Chen , Zhewei Wei , Zengfeng Huang , Bolin Ding , Yaliang Li

We introduce a novel approach for analyzing the training dynamics of ReLU networks by examining the characteristic activation boundaries of individual ReLU neurons. Our proposed analysis reveals a critical instability in common neural…

Machine Learning · Computer Science 2024-10-15 Wenlin Chen , Hong Ge

Inducing and leveraging sparse activations during training and inference is a promising avenue for improving the computational efficiency of deep networks, which is increasingly important as network sizes continue to grow and their…

Machine Learning · Computer Science 2024-02-27 Ilan Price , Nicholas Daultry Ball , Samuel C. H. Lam , Adam C. Jones , Jared Tanner

We investigate hybrid linear-morphological networks. Recent studies highlight the inherent affinity of morphological layers to pruning, but also their difficulty in training. We propose a hybrid network structure, wherein morphological…

Machine Learning · Computer Science 2025-04-15 Konstantinos Fotopoulos , Christos Garoufis , Petros Maragos

Recent works have cast some light on the mystery of why deep nets fit any data and generalize despite being very overparametrized. This paper analyzes training and generalization for a simple 2-layer ReLU net with random initialization, and…

Machine Learning · Computer Science 2019-05-28 Sanjeev Arora , Simon S. Du , Wei Hu , Zhiyuan Li , Ruosong Wang

In machine learning, graph embedding algorithms seek low-dimensional representations of the input network data, thereby allowing for downstream tasks on compressed encodings. Recently, within the framework of network renormalization,…

Physics and Society · Physics 2025-08-29 Riccardo Milocco , Fabian Jansen , Diego Garlaschelli

Rectified linear units (ReLU) are well-known to be helpful in obtaining faster convergence and thus higher performance for many deep-learning-based applications. However, networks with ReLU tend to perform poorly when the number of filter…

Computer Vision and Pattern Recognition · Computer Science 2018-12-14 Jae-Seok Choi , Munchurl Kim

Graph convolution operator of the GCN model is originally motivated from a localized first-order approximation of spectral graph convolutions. This work stands on a different view; establishing a \textit{mathematical connection between…

Machine Learning · Computer Science 2021-03-03 Lingxiao Zhao , Leman Akoglu

Deep artificial neural networks achieve surprising generalization abilities that remain poorly understood. In this paper, we present a new approach to analyzing generalization for deep feed-forward ReLU networks that takes advantage of the…

Machine Learning · Computer Science 2023-07-06 Ramchandran Muthukumar , Jeremias Sulam

Training deep graph neural networks (GNNs) is notoriously hard. Besides the standard plights in training deep architectures such as vanishing gradients and overfitting, it also uniquely suffers from over-smoothing, information squashing,…

Machine Learning · Computer Science 2022-05-10 Tianlong Chen , Kaixiong Zhou , Keyu Duan , Wenqing Zheng , Peihao Wang , Xia Hu , Zhangyang Wang

The graph structure is a commonly used data storage mode, and it turns out that the low-dimensional embedded representation of nodes in the graph is extremely useful in various typical tasks, such as node classification, link prediction ,…

Social and Information Networks · Computer Science 2020-08-03 Xing Li , Wei Wei , Xiangnan Feng , Xue Liu , Zhiming Zheng

Before training a neural net, a classic rule of thumb is to randomly initialize the weights so the variance of activations is preserved across layers. This is traditionally interpreted using the total variance due to randomness in both…

Machine Learning · Computer Science 2019-08-07 Kyle Luther , H. Sebastian Seung
‹ Prev 1 8 9 10 Next ›