English
Related papers

Related papers: A comparison of deep networks with ReLU activation…

200 papers

In studying the expressiveness of neural networks, an important question is whether there are functions which can only be approximated by sufficiently deep networks, assuming their size is bounded. However, for constant depths, existing…

Machine Learning · Computer Science 2020-12-29 Gal Vardi , Ohad Shamir

Recurrent Neural Networks (RNNs) offer fast inference on long sequences but are hard to optimize and slow to train. Deep state-space models (SSMs) have recently been shown to perform remarkably well on long sequence modeling tasks, and have…

Machine Learning · Computer Science 2023-03-14 Antonio Orvieto , Samuel L Smith , Albert Gu , Anushan Fernando , Caglar Gulcehre , Razvan Pascanu , Soham De

We discuss approximation of functions using deep neural nets. Given a function $f$ on a $d$-dimensional manifold $\Gamma \subset \mathbb{R}^m$, we construct a sparsely-connected depth-4 neural network and bound its error in approximating…

Machine Learning · Statistics 2017-04-24 Uri Shaham , Alexander Cloninger , Ronald R. Coifman

Rectifier (ReLU) deep neural networks (DNN) and their connection with piecewise affine (PWA) functions is analyzed. The paper is an effort to find and study the possibility of representing explicit state feedback policy of model predictive…

Machine Learning · Computer Science 2020-11-06 Saman Fahandezh-Saadi , Masayoshi Tomizuka

Deep Neural Networks (DNNs) have become very popular for prediction in many areas. Their strength is in representation with a high number of parameters that are commonly learned via gradient descent or similar optimization methods. However,…

Machine Learning · Statistics 2016-10-11 Anthony Caterini , Dong Eui Chang

Artificial neural networks (ANN), typically referred to as neural networks, are a class of Machine Learning algorithms and have achieved widespread success, having been inspired by the biological structure of the human brain. Neural…

Machine Learning · Computer Science 2022-04-08 Murilo Gustineli

This paper establishes the (nearly) optimal approximation error characterization of deep rectified linear unit (ReLU) networks for smooth functions in terms of both width and depth simultaneously. To that end, we first prove that…

Machine Learning · Computer Science 2021-11-03 Jianfeng Lu , Zuowei Shen , Haizhao Yang , Shijun Zhang

The scope of research in the domain of activation functions remains limited and centered around improving the ease of optimization or generalization quality of neural networks (NNs). However, to develop a deeper understanding of deep…

Machine Learning · Computer Science 2020-12-10 Mohit Goyal , Rajan Goyal , Brejesh Lall

The intrinsically infinite-dimensional features of the functional observations over multidimensional domains render the standard classification methods effectively inapplicable. To address this problem, we introduce a novel multiclass…

Machine Learning · Computer Science 2023-05-25 Shuoyang Wang , Guanqun Cao

The loss surfaces of deep neural networks have been the subject of several studies, theoretical and experimental, over the last few years. One strand of work considers the complexity, in the sense of local optima, of high dimensional random…

We prove that training neural networks on 1-D data is equivalent to solving convex Lasso problems with discrete, explicitly defined dictionary matrices. We consider neural networks with piecewise linear activations and depths ranging from 2…

Machine Learning · Computer Science 2024-07-25 Emi Zeger , Yifei Wang , Aaron Mishkin , Tolga Ergen , Emmanuel Candès , Mert Pilanci

An increasingly popular machine learning paradigm is to pretrain a neural network (NN) on many tasks offline, then adapt it to downstream tasks, often by re-training only the last linear layer of the network. This approach yields strong…

Machine Learning · Computer Science 2024-06-10 Liam Collins , Hamed Hassani , Mahdi Soltanolkotabi , Aryan Mokhtari , Sanjay Shakkottai

A recurrent neural network (RNN) is a widely used deep-learning network for dealing with sequential data. Imitating a dynamical system, an infinite-width RNN can approximate any open dynamical system in a compact domain. In general, deep…

Machine Learning · Statistics 2023-03-30 Chang hoon Song , Geonho Hwang , Jun ho Lee , Myungjoo Kang

Multi-scale deep neural networks (MscaleDNNs) with downing-scaling mapping have demonstrated superiority over traditional DNNs in approximating target functions characterized by high frequency features. However, the performance of…

Machine Learning · Computer Science 2024-10-02 Jizu Huang , Rukang You , Tao Zhou

We study the complexity of functions computable by deep feedforward neural networks with piecewise linear activations in terms of the symmetries and the number of linear regions that they have. Deep networks are able to sequentially map…

Machine Learning · Statistics 2014-06-10 Guido Montúfar , Razvan Pascanu , Kyunghyun Cho , Yoshua Bengio

Inductive rule learning is arguably among the most traditional paradigms in machine learning. Although we have seen considerable progress over the years in learning rule-based theories, all state-of-the-art learners still learn descriptions…

Machine Learning · Computer Science 2021-06-21 Florian Beck , Johannes Fürnkranz

Deep Neural Networks (DNNs) have emerged as a core tool for machine learning. The computations performed during DNN training and inference are dominated by operations on the weight matrices describing the DNN. As DNNs incorporate more…

Distributed, Parallel, and Cluster Computing · Computer Science 2018-03-06 Jeremy Kepner , Manoj Kumar , José Moreira , Pratap Pattnaik , Mauricio Serrano , Henry Tufo

The problem of automatic and accurate forecasting of time-series data has always been an interesting challenge for the machine learning and forecasting community. A majority of the real-world time-series problems have non-stationary…

Neural and Evolutionary Computing · Computer Science 2021-08-18 Rohit Kaushik , Shikhar Jain , Siddhant Jain , Tirtharaj Dash

Based on the tree architecture, the objective of this paper is to design deep neural networks with two or more hidden layers (called deep nets) for realization of radial functions so as to enable rotational invariance for near-optimal…

Machine Learning · Computer Science 2019-04-04 Charles K. Chui , Shao-Bo Lin , Ding-Xuan Zhou

We develop a variational framework to understand the properties of functions learned by fitting deep neural networks with rectified linear unit activations to data. We propose a new function space, which is reminiscent of classical bounded…

Machine Learning · Statistics 2022-04-18 Rahul Parhi , Robert D. Nowak
‹ Prev 1 3 4 5 6 7 10 Next ›