English
Related papers

Related papers: Dying ReLU and Initialization: Theory and Numerica…

200 papers

This paper studies the problem of training a two-layer ReLU network for binary classification using gradient flow with small initialization. We consider a training dataset with well-separated input vectors: Any pair of input data with the…

Machine Learning · Computer Science 2024-03-26 Hancheng Min , Enrique Mallada , René Vidal

Implicit neural networks have become increasingly attractive in the machine learning community since they can achieve competitive performance but use much less computational resources. Recently, a line of theoretical works established the…

Machine Learning · Computer Science 2022-10-03 Tianxiang Gao , Hongyang Gao

We study the role of depth in training randomly initialized overparameterized neural networks. We give a general result showing that depth improves trainability of neural networks by improving the conditioning of certain kernel matrices of…

Machine Learning · Computer Science 2021-02-18 Naman Agarwal , Pranjal Awasthi , Satyen Kale

An artificial neuron is modelled as a weighted summation followed by an activation function which determines its output. A wide variety of activation functions such as rectified linear units (ReLU), leaky-ReLU, Swish, MISH, etc. have been…

Machine Learning · Computer Science 2019-12-30 Fayyaz ul Amir Afsar Minhas , Amina Asif

We propose ReDense as a simple and low complexity way to improve the performance of trained neural networks. We use a combination of random weights and rectified linear unit (ReLU) activation function to add a ReLU dense (ReDense) layer to…

Machine Learning · Computer Science 2020-10-27 Alireza M. Javid , Sandipan Das , Mikael Skoglund , Saikat Chatterjee

In many information processing systems, it may be desirable to ensure that any change of the input, whether by shifting or scaling, results in a corresponding change in the system response. While deep neural networks are gradually replacing…

Computer Vision and Pattern Recognition · Computer Science 2024-02-22 Sébastien Herbreteau , Emmanuel Moebel , Charles Kervrann

Weight initialization is important for faster convergence and stability of deep neural networks training. In this paper, a robust initialization method is developed to address the training instability in long short-term memory (LSTM)…

Recent seminal work at the intersection of deep neural networks practice and random matrix theory has linked the convergence speed and robustness of these networks with the combination of random weight initialization and nonlinear…

Machine Learning · Computer Science 2019-05-07 Pierre H. Richemond , Yike Guo

ReLU is a widely used activation function in deep neural networks. This paper explores the stability properties of the ReLU map. For any weight matrix $\boldsymbol{A} \in \mathbb{R}^{m \times n}$ and bias vector $\boldsymbol{b} \in…

Information Theory · Computer Science 2025-04-17 Yu Xia , Haoyu Zhou

Empirical works show that for ReLU neural networks (NNs) with small initialization, input weights of hidden neurons (the input weight of a hidden neuron consists of the weight from its input layer to the hidden neuron and its bias term)…

Machine Learning · Computer Science 2022-10-20 Hanxu Zhou , Qixuan Zhou , Tao Luo , Yaoyu Zhang , Zhi-Qin John Xu

Understanding the underlying mechanisms that enable the empirical successes of deep neural networks is essential for further improving their performance and explaining such networks. Towards this goal, a specific question is how to explain…

Machine Learning · Computer Science 2019-10-22 Shaeke Salman , Canlin Zhang , Xiuwen Liu , Washington Mio

Two networks are equivalent if they produce the same output for any given input. In this paper, we study the possibility of transforming a deep neural network to another network with a different number of units or layers, which can be…

Machine Learning · Computer Science 2019-05-29 Abhinav Kumar , Thiago Serra , Srikumar Ramalingam

The Rectified Power Unit (RePU) activation function, a differentiable generalization of the Rectified Linear Unit (ReLU), has shown promise in constructing neural networks due to its smoothness properties. However, deep RePU networks often…

Machine Learning · Computer Science 2026-02-10 Taeyoung Kim , Myungjoo Kang

To theoretically understand the behavior of trained deep neural networks, it is necessary to study the dynamics induced by gradient methods from a random initialization. However, the nonlinear and compositional structure of these models…

Machine Learning · Computer Science 2021-12-21 Karl Hajjar , Lénaïc Chizat , Christophe Giraud

In this paper, we consider one dimensional (shallow) ReLU neural networks in which weights are chosen randomly and only the terminal layer is trained. First, we mathematically show that for such networks L2-regularized regression…

Machine Learning · Computer Science 2023-10-05 Jakob Heiss , Josef Teichmann , Hanna Wutte

Stochastic regularisation is an important weapon in the arsenal of a deep learning practitioner. However, despite recent theoretical advances, our understanding of how noise influences signal propagation in deep neural networks remains…

Machine Learning · Statistics 2018-12-03 Arnu Pretorius , Elan Van Biljon , Steve Kroon , Herman Kamper

We introduce stochastic activations. This novel strategy randomly selects between several non-linear functions in the feed-forward layer of a large language model. In particular, we choose between SILU or RELU depending on a Bernoulli draw.…

It is commonly recognized that the expressiveness of deep neural networks is contingent upon a range of factors, encompassing their depth, width, and other relevant considerations. Currently, the practical performance of the majority of…

Machine Learning · Computer Science 2023-11-08 Xuan Qi , Yi Wei

We consider neural networks with rational activation functions. The choice of the nonlinear activation function in deep learning architectures is crucial and heavily impacts the performance of a neural network. We establish optimal bounds…

Neural and Evolutionary Computing · Computer Science 2020-10-01 Nicolas Boullé , Yuji Nakatsukasa , Alex Townsend

The success of deep neural networks is in part due to the use of normalization layers. Normalization layers like Batch Normalization, Layer Normalization and Weight Normalization are ubiquitous in practice, as they improve generalization…

Machine Learning · Computer Science 2020-06-15 Yonatan Dukler , Quanquan Gu , Guido Montúfar