English
Related papers

Related papers: Modular Duality in Deep Learning

200 papers

We consider the problem of deep neural net compression by quantization: given a large, reference net, we want to quantize its real-valued weights using a codebook with $K$ entries so that the training loss of the quantized net is minimal.…

Machine Learning · Computer Science 2017-07-17 Miguel Á. Carreira-Perpiñán , Yerlan Idelbayev

We introduce a general theoretical framework, designed for the study of gradient optimisation of deep neural networks, that encompasses ubiquitous architecture choices including batch normalisation, weight normalisation and skip…

Machine Learning · Computer Science 2023-12-05 Lachlan Ewen MacDonald , Jack Valmadre , Hemanth Saratchandran , Simon Lucey

This paper introduces a deep learning system based on a quantum neural network for the binary classification of points of a specific geometric pattern (Two-Moons Classification problem) on a plane. We believe that the use of hybrid deep…

Quantum Physics · Physics 2022-08-10 Marco Simonetti , Damiano Perri , Osvaldo Gervasi

Sequential learning paradigms pose challenges for gradient-based deep learning due to difficulties incorporating new data and retaining prior knowledge. While Gaussian processes elegantly tackle these problems, they struggle with…

Machine Learning · Statistics 2024-03-19 Aidan Scannell , Riccardo Mereu , Paul Chang , Ella Tamir , Joni Pajarinen , Arno Solin

Significant success has been reported recently using deep neural networks for classification. Such large networks can be computationally intensive, even after training is over. Implementing these trained networks in hardware chips with a…

Machine Learning · Statistics 2013-10-25 Daniel Soudry , Ron Meir

Deep learning is a machine learning methodology using multi-layer neural network. A multi-layer neural network can be regarded as a chain of complete bipartite graphs. The nodes of the first partita is the input layer and the last is the…

Combinatorics · Mathematics 2020-05-11 Shoko Chisaki , Ryoh Fuji-Hara , Nobuko Miyamoto

In deep learning, a central issue is to understand how neural networks efficiently learn high-dimensional features. To this end, we explore the gradient descent learning of a general Gaussian Multi-index model…

Machine Learning · Statistics 2026-02-06 Bohan Zhang , Zihao Wang , Hengyu Fu , Jason D. Lee

Gradient-based saliency maps have been widely used to explain the decisions of deep neural network classifiers. However, standard gradient-based interpretation maps, including the simple gradient and integrated gradient algorithms, often…

Computer Vision and Pattern Recognition · Computer Science 2024-04-09 Shizhan Gong , Qi Dou , Farzan Farnia

Efforts to understand the generalization mystery in deep learning have led to the belief that gradient-based optimization induces a form of implicit regularization, a bias towards models of low "complexity." We study the implicit…

Machine Learning · Computer Science 2019-10-29 Sanjeev Arora , Nadav Cohen , Wei Hu , Yuping Luo

The first part of this work established the foundations of a radial duality between nonnegative optimization problems, inspired by the work of (Renegar, 2016). Here we utilize our radial duality theory to design and analyze projection-free…

Optimization and Control · Mathematics 2022-11-15 Benjamin Grimmer

Deep neural networks have achieved impressive supervised classification performance in many tasks including image recognition, speech recognition, and sequence to sequence learning. However, this success has not been translated to…

Machine Learning · Computer Science 2016-08-05 Arvind Neelakantan , Quoc V. Le , Ilya Sutskever

Artificial neural networks (ANNs) have achieved significant success in tackling classical and modern machine learning problems. As learning problems grow in scale and complexity, and expand into multi-disciplinary territory, a more modular…

Machine Learning · Computer Science 2019-04-30 Mohammed Amer , Tomás Maul

Training of deep models for classification tasks is hindered by local minima problems and vanishing gradients, while unsupervised layer-wise pretraining does not exploit information from class labels. Here, we propose a new regularization…

Machine Learning · Computer Science 2019-11-07 Pavel Sulimov , Elena Sukmanova , Roman Chereshnev , Attila Kertesz-Farkas

Using weight decay to penalize the L2 norms of weights in neural networks has been a standard training practice to regularize the complexity of networks. In this paper, we show that a family of regularizers, including weight decay, is…

Machine Learning · Computer Science 2022-06-09 Ziquan Liu , Yufei Cui , Antoni B. Chan

We construct custom regularization functions for use in supervised training of deep neural networks. Our technique is applicable when the ground-truth labels themselves exhibit internal structure; we derive a regularizer by learning an…

Computer Vision and Pattern Recognition · Computer Science 2018-04-09 Mohammadreza Mostajabi , Michael Maire , Gregory Shakhnarovich

Deep neural networks are highly effective at a range of computational tasks. However, they tend to be computationally expensive, especially in vision-related problems, and also have large memory requirements. One of the most effective…

Computer Vision and Pattern Recognition · Computer Science 2018-04-10 Ameya Prabhu , Vishal Batchu , Sri Aurobindo Munagala , Rohit Gajawada , Anoop Namboodiri

In recent years Deep Neural Networks (DNNs) have been rapidly developed in various applications, together with increasingly complex architectures. The performance gain of these DNNs generally comes with high computational costs and large…

Machine Learning · Computer Science 2017-12-05 Yiren Zhou , Seyed-Mohsen Moosavi-Dezfooli , Ngai-Man Cheung , Pascal Frossard

This tutorial paper surveys provably optimal alternatives to end-to-end backpropagation (E2EBP) -- the de facto standard for training deep architectures. Modular training refers to strictly local training without both the forward and the…

Machine Learning · Computer Science 2022-08-10 Shiyu Duan , Jose C. Principe

Deep learning uses neural networks which are parameterised by their weights. The neural networks are usually trained by tuning the weights to directly minimise a given loss function. In this paper we propose to re-parameterise the weights…

Neural and Evolutionary Computing · Computer Science 2022-03-14 Michael Fairbank , Spyridon Samothrakis , Luca Citi

This paper proposes the method to optimize restriction and prolongation operators in the two-grid method. The proposed method is straightforwardly extended to the geometric multigrid method (GMM). GMM is used in solving discretized partial…

Numerical Analysis · Mathematics 2018-06-18 Alexandr Katrutsa , Talgat Daulbaev , Ivan Oseledets