English
Related papers

Related papers: Bidirectionally Self-Normalizing Neural Networks

200 papers

We develop a new method for regularising neural networks. We learn a probability distribution over the activations of all layers of the model and then insert imputed values into the network during training. We obtain a posterior for an…

Machine Learning · Computer Science 2019-10-14 Matthew Willetts , Alexander Camuto , Stephen Roberts , Chris Holmes

We present here a new model and algorithm which performs an efficient Natural gradient descent for Multilayer Perceptrons. Natural gradient descent was originally proposed from a point of view of information geometry, and it performs the…

Machine Learning · Statistics 2018-07-11 Yuki Fujimoto , Toru Ohira

In this paper, we develop a new optimization framework for the least squares learning problem via fully connected neural networks or physics-informed neural networks. The gradient descent sometimes behaves inefficiently in deep learning…

Machine Learning · Computer Science 2025-05-01 Yaru Liu , Yiqi Gu , Michael K. Ng

The elusive nature of gradient-based optimization in neural networks is tied to their loss landscape geometry, which is poorly understood. However recent work has brought solid evidence that there is essentially no loss barrier between the…

Machine Learning · Statistics 2023-10-17 Simone Rossi , Ankit Singh , Thomas Hannagan

Neural networks have become a prominent approach to solve inverse problems in recent years. While a plethora of such methods was developed to solve inverse problems empirically, we are still lacking clear theoretical guarantees for these…

Machine Learning · Computer Science 2024-03-19 Nathan Buskulic , Jalal Fadili , Yvain Quéau

As deep learning applications continue to deploy increasingly large artificial neural networks, the associated high energy demands are creating a need for alternative neuromorphic approaches. Optics and photonics are particularly compelling…

Optics · Physics 2025-08-19 Nicola Dal Cin , Florian Marquardt , Clara C. Wanjura

Enforcing orthonormal or isometric property for the weight matrices has been shown to enhance the training of deep neural networks by mitigating gradient exploding/vanishing and increasing the robustness of the learned networks. However,…

Machine Learning · Computer Science 2024-03-01 Zhen Qin , Xuwei Tan , Zhihui Zhu

In a recently published paper [1], it is shown that deep neural networks (DNNs) with random Gaussian weights preserve the metric structure of the data, with the property that the distance shrinks more when the angle between the two data…

Machine Learning · Statistics 2019-04-02 Talha Cihad Gulcu , Alper Gungor

In this work, we study the training and generalization performance of two-layer neural networks (NNs) after one gradient descent step under structured data modeled by Gaussian mixtures. While previous research has extensively analyzed this…

Machine Learning · Statistics 2025-05-20 Samet Demir , Zafer Dogan

Neural networks have achieved remarkable empirical performance, while the current theoretical analysis is not adequate for understanding their success, e.g., the Neural Tangent Kernel approach fails to capture their key feature learning…

Machine Learning · Computer Science 2023-10-20 Zhenmei Shi , Junyi Wei , Yingyu Liang

There is significant need for principled uncertainty reasoning in machine learning systems as they are increasingly deployed in safety-critical domains. A new approach with uncertainty-aware neural networks (NNs), based on learning…

Machine Learning · Computer Science 2022-02-25 Nis Meinert , Alexander Lavin

Despite the widespread adoption of neural networks, their training dynamics remain poorly understood. We show experimentally that as the size of the dataset increases, a point forms where the magnitude of the gradient of the loss becomes…

Machine Learning · Computer Science 2024-07-23 Mark Lowell

Recent research has shown that one can train a neural network with binary weights and activations at train time by augmenting the weights with a high-precision continuous latent variable that accumulates small changes from stochastic…

Machine Learning · Computer Science 2017-05-23 Alexander G. Anderson , Cory P. Berg

We combine Riemannian geometry with the mean field theory of high dimensional chaos to study the nature of signal propagation in generic, deep neural networks with random weights. Our results reveal an order-to-chaos expressivity phase…

Machine Learning · Statistics 2016-06-22 Ben Poole , Subhaneil Lahiri , Maithra Raghu , Jascha Sohl-Dickstein , Surya Ganguli

This article gives a new proof that fully connected neural networks with random weights and biases converge to Gaussian processes in the regime where the input dimension, output dimension, and depth are kept fixed, while the hidden layer…

Probability · Mathematics 2021-07-06 Boris Hanin

A fairly comprehensive analysis is presented for the gradient descent dynamics for training two-layer neural network models in the situation when the parameters in both layers are updated. General initialization schemes as well as general…

Machine Learning · Computer Science 2020-02-27 Weinan E , Chao Ma , Lei Wu

Large multilayer neural networks trained with backpropagation have recently achieved state-of-the-art results in a wide range of problems. However, using backprop for neural net learning still has some disadvantages, e.g., having to tune a…

Machine Learning · Statistics 2015-07-16 José Miguel Hernández-Lobato , Ryan P. Adams

Recently, several studies have proven the global convergence and generalization abilities of the gradient descent method for two-layer ReLU networks. Most studies especially focused on the regression problems with the squared loss function,…

Machine Learning · Statistics 2020-03-19 Atsushi Nitanda , Geoffrey Chinot , Taiji Suzuki

Linearized Graph Neural Networks (GNNs) have attracted great attention in recent years for graph representation learning. Compared with nonlinear Graph Neural Network (GNN) models, linearized GNNs are much more time-efficient and can…

Machine Learning · Computer Science 2023-02-02 Yulin Zhu , Xing Ai , Qimai Li , Xiao-Ming Wu , Kai Zhou

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