English
Related papers

Related papers: Beyond Gaussian Initializations: Signal Preserving…

200 papers

We consider the optimal approximate posterior over the top-layer weights in a Bayesian neural network for regression, and show that it exhibits strong dependencies on the lower-layer weights. We adapt this result to develop a correlated…

Machine Learning · Statistics 2021-06-23 Sebastian W. Ober , Laurence Aitchison

Despite the recent success of stochastic gradient descent in deep learning, it is often difficult to train a deep neural network with an inappropriate choice of its initial parameters. Even if training is successful, it has been known that…

Machine Learning · Computer Science 2023-02-10 Cheolhyoung Lee , Kyunghyun Cho

We provide an overview of several non-linear activation functions in a neural network architecture that have proven successful in many machine learning applications. We conduct an empirical analysis on the effectiveness of using these…

Machine Learning · Computer Science 2017-11-01 Giovanni Alcantara

Plasticity loss, a critical challenge in neural network training, limits a model's ability to adapt to new tasks or shifts in data distribution. This paper introduces AID (Activation by Interval-wise Dropout), a novel method inspired by…

Machine Learning · Computer Science 2025-06-24 Sangyeon Park , Isaac Han , Seungwon Oh , Kyung-Joong Kim

Stochastic gradient descent (SGD), one of the most fundamental optimization algorithms in machine learning (ML), can be recast through a continuous-time approximation as a Fokker-Planck equation for Langevin dynamics, a viewpoint that has…

Machine Learning · Statistics 2025-08-19 Hiroshi Horii , Sothea Has

Arguably the biggest challenge in applying neural networks is tuning the hyperparameters, in particular the learning rate. The sensitivity to the learning rate is due to the reliance on backpropagation to train the network. In this paper we…

Machine Learning · Statistics 2018-08-08 Francois Fagan , Garud Iyengar

Sparsification of neural networks is one of the effective complexity reduction methods to improve efficiency and generalizability. Binarized activation offers an additional computational saving for inference. Due to vanishing gradient issue…

Optimization and Control · Mathematics 2019-02-12 Thu Dinh , Jack Xin

We consider the problem of active learning for global sensitivity analysis of expensive black-box functions. Our aim is to efficiently learn the importance of different input variables, e.g., in vehicle safety experimentation, we study the…

Machine Learning · Computer Science 2024-10-22 Syrine Belakaria , Benjamin Letham , Janardhan Rao Doppa , Barbara Engelhardt , Stefano Ermon , Eytan Bakshy

Physics-informed neural networks (PINNs) are known to suffer from optimization difficulty. In this work, we reveal the connection between the optimization difficulty of PINNs and activation functions. Specifically, we show that PINNs…

Machine Learning · Computer Science 2023-11-27 Honghui Wang , Lu Lu , Shiji Song , Gao Huang

In recent years, newly developed methods to train spiking neural networks (SNNs) have rendered them as a plausible alternative to Artificial Neural Networks (ANNs) in terms of accuracy, while at the same time being much more energy…

Neural and Evolutionary Computing · Computer Science 2023-05-17 Nicolas Perez-Nieves , Dan F. M Goodman

In this paper, we propose a novel optimization algorithm for training machine learning models called Input Normalized Stochastic Gradient Descent (INSGD), inspired by the Normalized Least Mean Squares (NLMS) algorithm used in adaptive…

Machine Learning · Computer Science 2023-06-28 Salih Atici , Hongyi Pan , Ahmet Enis Cetin

We focus on a specific class of shallow neural networks with a single hidden layer, namely those with $L_2$-normalised data and either a sigmoid-shaped Gaussian error function ("erf") activation or a Gaussian Error Linear Unit (GELU)…

Machine Learning · Computer Science 2022-10-21 Felix Biggs , Benjamin Guedj

We consider Bayesian inverse problems wherein the unknown state is assumed to be a function with discontinuous structure a priori. A class of prior distributions based on the output of neural networks with heavy-tailed weights is…

Machine Learning · Computer Science 2021-12-21 Chen Li , Matthew Dunlop , Georg Stadler

Recent work has established the equivalence between deep neural networks and Gaussian processes (GPs), resulting in so-called neural network Gaussian processes (NNGPs). The behaviour of these models depends on the initialisation of the…

Machine Learning · Computer Science 2020-07-15 Arnu Pretorius , Herman Kamper , Steve Kroon

This work identifies and attempts to address a fundamental limitation of implicit neural representations with sinusoidal activation. The fitting error of SIRENs is highly sensitive to the target frequency content and to the choice of…

Audio and Speech Processing · Electrical Eng. & Systems 2025-12-24 Hemanth Chandravamsi , Dhanush V. Shenoy , Itay Zinn , Ziv Chen , Shimon Pisnoy , Steven H. Frankel

In this paper, we introduce the concept of Prior Activation Distribution (PAD) as a versatile and general technique to capture the typical activation patterns of hidden layer units of a Deep Neural Network used for classification tasks. We…

Computer Vision and Pattern Recognition · Computer Science 2019-07-08 Lakmal Meegahapola , Vengateswaran Subramaniam , Lance Kaplan , Archan Misra

Overparameterized neural networks often show a benign overfitting property in the sense of achieving excellent generalization behavior despite the number of parameters exceeding the number of training examples. A promising direction to…

Machine Learning · Computer Science 2026-04-23 Yunwen Lei , Yufeng Xie

While end-to-end training of Deep Neural Networks (DNNs) yields state of the art performance in an increasing array of applications, it does not provide insight into, or control over, the features being extracted. We report here on a…

Neural and Evolutionary Computing · Computer Science 2022-07-11 Metehan Cekic , Can Bakiskan , Upamanyu Madhow

In recent years significant progress has been made in successfully training recurrent neural networks (RNNs) on sequence learning problems involving long range temporal dependencies. The progress has been made on three fronts: (a)…

Neural and Evolutionary Computing · Computer Science 2016-06-24 Sachin S. Talathi , Aniket Vartak

Deep neural networks often suffer from poor performance or even training failure due to the ill-conditioned problem, the vanishing/exploding gradient problem, and the saddle point problem. In this paper, a novel method by acting the…

Computer Vision and Pattern Recognition · Computer Science 2021-07-12 Mei Liu , Liangming Chen , Xiaohao Du , Long Jin , Mingsheng Shang