English
Related papers

Related papers: Initializing ReLU networks in an expressive subspa…

200 papers

Batch Normalization is a key component in almost all state-of-the-art image classifiers, but it also introduces practical challenges: it breaks the independence between training examples within a batch, can incur compute and memory…

Machine Learning · Computer Science 2021-01-28 Andrew Brock , Soham De , Samuel L. Smith

Recently, neural networks in machine learning use rectified linear units (ReLUs) in early processing layers for better performance. Training these structures sometimes results in "dying ReLU units" with near-zero outputs. We first explore…

Machine Learning · Computer Science 2018-12-17 Scott C. Douglas , Jiutian Yu

In neural network compression, most current methods reduce unnecessary parameters by measuring importance and redundancy. To augment already highly optimized existing solutions, we propose linearity-based compression as a novel way to…

Machine Learning · Computer Science 2025-06-27 Silas Dobler , Florian Lemmerich

The development of effective initialization methods requires an understanding of random neural networks. In this work, a rigorous probabilistic analysis of deep unbiased Leaky ReLU networks is provided. We prove a Law of Large Numbers and a…

Machine Learning · Statistics 2026-02-12 Constantin Kogler , Tassilo Schwarz , Samuel Kittle

We introduce the "exponential linear unit" (ELU) which speeds up learning in deep neural networks and leads to higher classification accuracies. Like rectified linear units (ReLUs), leaky ReLUs (LReLUs) and parametrized ReLUs (PReLUs), ELUs…

Machine Learning · Computer Science 2016-02-23 Djork-Arné Clevert , Thomas Unterthiner , Sepp Hochreiter

Over-parameterized deep neural networks have proven to be able to learn an arbitrary dataset with 100$\%$ training accuracy. Because of a risk of overfitting and computational cost issues, we cannot afford to increase the number of network…

Machine Learning · Computer Science 2019-04-08 Bukweon Kim , Sung Min Lee , Jin Keun Seo

The phenomenon of distinct behaviors exhibited by neural networks under varying scales of initialization remains an enigma in deep learning research. In this paper, based on the earlier work by Luo et al.~\cite{luo2021phase}, we present a…

Machine Learning · Computer Science 2026-04-02 Zhengan Chen , Yuqing Li , Tao Luo , Zhangchen Zhou , Zhi-Qin John Xu

This work investigates the ways in which deep learning methods can benefit from random projection (RP), a classic linear dimensionality reduction method. We focus on two areas where, as we have found, employing RP techniques can improve…

Machine Learning · Computer Science 2018-12-27 Piotr Iwo Wójcik

Neural circuits exhibit complex activity patterns, both spontaneously and evoked by external stimuli. Information encoding and learning in neural circuits depend on how well time-varying stimuli can control spontaneous network activity. We…

Neurons and Cognition · Quantitative Biology 2023-01-11 Rainer Engelken , Alessandro Ingrosso , Ramin Khajeh , Sven Goedeke , L. F. Abbott

Neural networks with random weights appear in a variety of machine learning applications, most prominently as the initialization of many deep learning algorithms and as a computationally cheap alternative to fully learned neural networks.…

Machine Learning · Computer Science 2022-11-29 Sjoerd Dirksen , Martin Genzel , Laurent Jacques , Alexander Stollenwerk

Neural fields are an emerging paradigm that represent data as continuous functions parameterized by neural networks. Despite many advantages, neural fields often have a high training cost, which prevents a broader adoption. In this paper,…

Machine Learning · Computer Science 2026-02-04 Taesun Yeom , Sangyoon Lee , Jaeho Lee

A remarkable recent discovery in machine learning has been that deep neural networks can achieve impressive performance (in terms of both lower training error and higher generalization capacity) in the regime where they are massively…

Machine Learning · Computer Science 2020-03-03 Thanh V. Nguyen , Raymond K. W. Wong , Chinmay Hegde

Understanding theoretical properties of deep and locally connected nonlinear network, such as deep convolutional neural network (DCNN), is still a hard problem despite its empirical success. In this paper, we propose a novel theoretical…

Machine Learning · Computer Science 2018-10-01 Yuandong Tian

It has been noted in existing literature that over-parameterization in ReLU networks generally improves performance. While there could be several factors involved behind this, we prove some desirable theoretical properties at initialization…

Machine Learning · Statistics 2019-10-03 Devansh Arpit , Yoshua Bengio

The implicit bias of gradient-based training algorithms has been considered mostly beneficial as it leads to trained networks that often generalize well. However, Frei et al. (2023) show that such implicit bias can harm adversarial…

Machine Learning · Computer Science 2024-06-06 Hancheng Min , René Vidal

Residual neural networks (ResNets) are a promising class of deep neural networks that have shown excellent performance for a number of learning tasks, e.g., image classification and recognition. Mathematically, ResNet architectures can be…

Optimization and Control · Mathematics 2019-07-26 S. Günther , L. Ruthotto , J. B. Schroder , E. C. Cyr , N. R. Gauger

In this work, we propose a novel technique to boost training efficiency of a neural network. Our work is based on an excellent idea that whitening the inputs of neural networks can achieve a fast convergence speed. Given the well-known fact…

Machine Learning · Computer Science 2019-05-16 Guangyong Chen , Pengfei Chen , Yujun Shi , Chang-Yu Hsieh , Benben Liao , Shengyu Zhang

Each year, deep learning demonstrates new and improved empirical results with deeper and wider neural networks. Meanwhile, with existing theoretical frameworks, it is difficult to analyze networks deeper than two layers without resorting to…

Machine Learning · Computer Science 2023-03-28 Hong Jun Jeon , Yifan Zhu , Benjamin Van Roy

Our community has greatly improved the efficiency of deep learning applications, including by exploiting sparsity in inputs. Most of that work, though, is for inference, where weight sparsity is known statically, and/or for specialized…

Machine Learning · Computer Science 2020-12-04 Zhangxiaowen Gong , Houxiang Ji , Christopher Fletcher , Christopher Hughes , Josep Torrellas

Finding the right initialisation for neural networks is crucial to ensure smooth training and good performance. In transformers, the wrong initialisation can lead to one of two failure modes of self-attention layers: rank collapse, where…

Machine Learning · Statistics 2026-05-22 Alessio Giorlandino , Sebastian Goldt
‹ Prev 1 4 5 6 7 8 10 Next ›