English
Related papers

Related papers: Principled Weight Initialization for Hypernetworks

200 papers

Modern iterations of deep learning models contain millions (billions) of unique parameters, each represented by a b-bit number. Popular attempts at compressing neural networks (such as pruning and quantisation) have shown that many of the…

Machine Learning · Computer Science 2022-10-26 Christopher Subia-Waud , Srinandan Dasmahapatra

Convergence rate of training algorithms for neural networks is heavily affected by initialization of weights. In this paper, an original algorithm for initialization of weights in backpropagation neural net is presented with application to…

Machine Learning · Computer Science 2020-04-07 Nadir Murru , Rosaria Rossini

The effectiveness of training neural networks directly impacts computational costs, resource allocation, and model development timelines in machine learning applications. An optimizer's ability to train the model adequately (in terms of…

Machine Learning · Computer Science 2024-08-06 Andriy Miranskyy , Adam Sorrenti , Viral Thakar

Deep Neural Networks (DNNs) have become increasingly popular in computer vision, natural language processing, and other areas. However, training and fine-tuning a deep learning model is computationally intensive and time-consuming. We…

Machine Learning · Computer Science 2018-07-04 Jiayi Liu , Samarth Tripathi , Unmesh Kurup , Mohak Shah

Informed by the basic geometry underlying feed forward neural networks, we initialize the weights of the first layer of a neural network using the linear discriminants which best distinguish individual classes. Networks initialized in this…

Machine Learning · Computer Science 2020-08-19 Marissa Masden , Dev Sinha

Tensorial Convolutional Neural Networks (TCNNs) have attracted much research attention for their power in reducing model parameters or enhancing the generalization ability. However, exploration of TCNNs is hindered even from weight…

Machine Learning · Computer Science 2022-07-26 Yu Pan , Zeyong Su , Ao Liu , Jingquan Wang , Nannan Li , Zenglin Xu

Standard practice in training neural networks involves initializing the weights in an independent fashion. The results of recent work suggest that feature "diversity" at initialization plays an important role in training the network.…

Machine Learning · Computer Science 2020-07-06 Yaniv Blumenfeld , Dar Gilboa , Daniel Soudry

Deep neural networks have been shown to easily overfit to biased training data with label noise or class imbalance. Meta-learning algorithms are commonly designed to alleviate this issue in the form of sample reweighting, by learning a meta…

Machine Learning · Computer Science 2020-12-11 Hongxin Wei , Lei Feng , Rundong Wang , Bo An

A new design methodology for neural networks that is guided by traditional algorithm design is presented. To prove our point, we present two heuristics and demonstrate an algorithmic technique for incorporating additional weights in their…

Machine Learning · Computer Science 2018-06-07 Abhejit Rajagopal , Shivkumar Chandrasekaran , Hrushikesh N. Mhaskar

Optimizing deep neural networks (DNNs) often suffers from the ill-conditioned problem. We observe that the scaling-based weight space symmetry property in rectified nonlinear network will cause this negative effect. Therefore, we propose to…

Machine Learning · Computer Science 2017-10-09 Lei Huang , Xianglong Liu , Bo Lang , Bo Li

Training deep neural networks results in strong learned representations that show good generalization capabilities. In most cases, training involves iterative modification of all weights inside the network via back-propagation. In Extreme…

Machine Learning · Computer Science 2018-02-06 Amir Rosenfeld , John K. Tsotsos

This paper tackles the problem of training a deep convolutional neural network of both low-bitwidth weights and activations. Optimizing a low-precision network is very challenging due to the non-differentiability of the quantizer, which may…

Computer Vision and Pattern Recognition · Computer Science 2021-06-07 Bohan Zhuang , Jing Liu , Mingkui Tan , Lingqiao Liu , Ian Reid , Chunhua Shen

We study Bayesian hypernetworks: a framework for approximate Bayesian inference in neural networks. A Bayesian hypernetwork $\h$ is a neural network which learns to transform a simple noise distribution, $p(\vec\epsilon) = \N(\vec 0,\mat…

Machine Learning · Statistics 2018-04-26 David Krueger , Chin-Wei Huang , Riashat Islam , Ryan Turner , Alexandre Lacoste , Aaron Courville

Probabilistic neural networks are typically modeled with independent weight priors, which do not capture weight correlations in the prior and do not provide a parsimonious interface to express properties in function space. A desirable class…

Machine Learning · Statistics 2020-02-12 Theofanis Karaletsos , Thang D. Bui

In recent years significant progress has been made in successfully training recurrent neural networks (RNNs) on sequence learning problems involving long range temporal dependencies. The progress has been made on three fronts: (a)…

Neural and Evolutionary Computing · Computer Science 2016-06-24 Sachin S. Talathi , Aniket Vartak

Currently, deep neural networks are deployed on low-power portable devices by first training a full-precision model using powerful hardware, and then deriving a corresponding low-precision model for efficient inference on such systems.…

Machine Learning · Computer Science 2017-11-15 Hao Li , Soham De , Zheng Xu , Christoph Studer , Hanan Samet , Tom Goldstein

Optimization of Binarized Neural Networks (BNNs) currently relies on real-valued latent weights to accumulate small update steps. In this paper, we argue that these latent weights cannot be treated analogously to weights in real-valued…

Machine Learning · Computer Science 2019-11-07 Koen Helwegen , James Widdicombe , Lukas Geiger , Zechun Liu , Kwang-Ting Cheng , Roeland Nusselder

A common method in training neural networks is to initialize all the weights to be independent Gaussian vectors. We observe that by instead initializing the weights into independent pairs, where each pair consists of two identical Gaussian…

Machine Learning · Computer Science 2022-06-28 Alexander Munteanu , Simon Omlor , Zhao Song , David P. Woodruff

Physics-Informed Neural Networks (PINNs) are a powerful deep learning method capable of providing solutions and parameter estimations of physical systems. Given the complexity of their neural network structure, the convergence speed is…

Machine Learning · Computer Science 2025-01-28 Sirui Li , Federica Bragone , Matthieu Barreau , Kateryna Morozovska

Recurrent Neural Networks (RNNs) produce state-of-art performance on many machine learning tasks but their demand on resources in terms of memory and computational power are often high. Therefore, there is a great interest in optimizing the…

Neural and Evolutionary Computing · Computer Science 2017-02-28 Joachim Ott , Zhouhan Lin , Ying Zhang , Shih-Chii Liu , Yoshua Bengio