English
Related papers

Related papers: A representer theorem for deep neural networks

200 papers

In this paper, we consider the problem of descriptors construction for the task of content-based image retrieval using deep neural networks. The idea of neural codes, based on fully connected layers activations, is extended by incorporating…

Computer Vision and Pattern Recognition · Computer Science 2020-07-15 Paweł Staszewski , Maciej Jaworski , Jinde Cao , Leszek Rutkowski

In this paper, we investigate the expressivity and approximation properties of deep neural networks employing the ReLU$^k$ activation function for $k \geq 2$. Although deep ReLU networks can approximate polynomials effectively, deep…

Machine Learning · Computer Science 2024-01-12 Juncai He , Tong Mao , Jinchao Xu

A linear restriction of a function is the same function with its domain restricted to points on a given line. This paper addresses the problem of computing a succinct representation for a linear restriction of a piecewise-linear neural…

Machine Learning · Computer Science 2019-12-09 Matthew Sotoudeh , Aditya V. Thakur

Recent theoretical work has demonstrated that deep neural networks have superior performance over shallow networks, but their training is more difficult, e.g., they suffer from the vanishing gradient problem. This problem can be typically…

Machine Learning · Statistics 2021-11-03 Lu Lu , Yanhui Su , George Em Karniadakis

This paper presents two main theoretical results concerning shallow neural networks with ReLU$^k$ activation functions. We establish a novel integral representation for Sobolev spaces, showing that every function in…

Numerical Analysis · Mathematics 2025-05-13 Xinliang Liu , Tong Mao , Jinchao Xu

We draw connections between simple neural networks and under-determined linear systems to comprehensively explore several interesting theoretical questions in the study of neural networks. First, we emphatically show that it is unsurprising…

Numerical Analysis · Mathematics 2020-11-02 Austin R. Benson , Anil Damle , Alex Townsend

Deep predictive models of neuronal activity have recently enabled several new discoveries about the selectivity and invariance of neurons in the visual cortex. These models learn a shared set of nonlinear basis functions, which are linearly…

Neurons and Cognition · Quantitative Biology 2024-06-19 Polina Turishcheva , Max Burg , Fabian H. Sinz , Alexander Ecker

While deep neural networks have succeeded in several visual applications, such as object recognition, detection, and localization, by reaching very high classification accuracies, it is important to note that many real-world applications…

Computer Vision and Pattern Recognition · Computer Science 2020-10-06 Yu-An Chung , Shao-Wen Yang , Hsuan-Tien Lin

Most existing expressivity theories for neural networks assume exact real arithmetic, whereas practical neural networks are executed under finite-precision floating-point arithmetic with implementation-dependent execution semantics. Recent…

Machine Learning · Computer Science 2026-05-28 Yeachan Park , Geonho Hwang , Wonyeol Lee , Sejun Park

We propose a novel explanation method that explains the decisions of a deep neural network by investigating how the intermediate representations at each layer of the deep network were refined during the training process. This way we can a)…

Machine Learning · Computer Science 2021-09-14 Lukas Pfahler , Katharina Morik

We study the implicit bias of gradient flow (i.e., gradient descent with infinitesimal step size) on linear neural network training. We propose a tensor formulation of neural networks that includes fully-connected, diagonal, and…

Machine Learning · Computer Science 2021-09-13 Chulhee Yun , Shankar Krishnan , Hossein Mobahi

Activation functions are non-linearities in neural networks that allow them to learn complex mapping between inputs and outputs. Typical choices for activation functions are ReLU, Tanh, Sigmoid etc., where the choice generally depends on…

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

Deep ReLU neural networks admit nontrivial functional symmetries: vastly different architectures and parameters (weights and biases) can realize the same function. We address the complete identification problem -- given a function f,…

Artificial Intelligence · Computer Science 2026-02-03 Yani Zhang , Helmut Bölcskei

Quantization and pruning are core techniques used to reduce the inference costs of deep neural networks. State-of-the-art quantization techniques are currently applied to both the weights and activations; however, pruning is most often…

Machine Learning · Computer Science 2021-11-02 Xinyu Zhang , Ian Colbert , Ken Kreutz-Delgado , Srinjoy Das

Neural network (NN) denoisers are an essential building block in many common tasks, ranging from image reconstruction to image generation. However, the success of these models is not well understood from a theoretical perspective. In this…

Machine Learning · Statistics 2024-01-17 Chen Zeno , Greg Ongie , Yaniv Blumenfeld , Nir Weinberger , Daniel Soudry

We introduce Dynamic Deep Neural Networks (D2NN), a new type of feed-forward deep neural network that allows selective execution. Given an input, only a subset of D2NN neurons are executed, and the particular subset is determined by the…

Machine Learning · Computer Science 2018-03-06 Lanlan Liu , Jia Deng

Discrete structures are currently second-class in differentiable programming. Since functions over discrete structures lack overt derivatives, differentiable programs do not differentiate through them and limit where they can be used. For…

Programming Languages · Computer Science 2025-11-20 Joey Velez-Ginorio , Nada Amin , Konrad Kording , Steve Zdancewic

Neural networks often operate in the overparameterized regime, in which there are far more parameters than training samples, allowing the training data to be fit perfectly. That is, training the network effectively learns an interpolating…

Machine Learning · Computer Science 2025-03-19 Suzanna Parkinson , Greg Ongie , Rebecca Willett

For any given neural network architecture a permutation of weights and biases results in the same functional network. This implies that optimization algorithms used to `train' or `learn' the network are faced with a very large number (in…

Optimization and Control · Mathematics 2022-02-22 Harbir Antil , Thomas S. Brown , Rainald Löhner , Fumiya Togashi , Deepanshu Verma
‹ Prev 1 8 9 10 Next ›