中文
相关论文

相关论文: Layer-wise Learning of Stochastic Neural Networks …

200 篇论文

In the past decade, deep neural networks have seen unparalleled improvements that continue to impact every aspect of today's society. With the development of high performance GPUs and the availability of vast amounts of data, learning…

机器学习 · 计算机科学 2021-05-12 Mohammad Ali Alomrani

Information bottleneck (IB) is a technique for extracting information in one random variable $X$ that is relevant for predicting another random variable $Y$. IB works by encoding $X$ in a compressed "bottleneck" random variable $M$ from…

信息论 · 计算机科学 2022-11-22 Artemy Kolchinsky , Brendan D. Tracey , David H. Wolpert

The Information Bottleneck (IB) principle offers an information-theoretic framework for analyzing the training process of deep neural networks (DNNs). Its essence lies in tracking the dynamics of two mutual information (MI) values: between…

机器学习 · 计算机科学 2024-05-10 Ivan Butakov , Alexander Tolmachev , Sofia Malanchuk , Anna Neopryatnaya , Alexey Frolov , Kirill Andreev

The information bottleneck (IB) principle has been suggested as a way to analyze deep neural networks. The learning dynamics are studied by inspecting the mutual information (MI) between the hidden layers and the input and output. Notably,…

机器学习 · 计算机科学 2022-02-15 Stephan Sloth Lorenzen , Christian Igel , Mads Nielsen

Inference capabilities of machine learning (ML) systems skyrocketed in recent years, now playing a pivotal role in various aspect of society. The goal in statistical learning is to use data to obtain simple algorithms for predicting a…

机器学习 · 计算机科学 2020-05-04 Ziv Goldfeld , Yury Polyanskiy

The information bottleneck (IB) method is a technique designed to extract meaningful information related to one random variable from another random variable, and has found extensive applications in machine learning problems. In this paper,…

信息论 · 计算机科学 2025-07-29 Lingyi Chen , Shitong Wu , Sicheng Xu , Huihui Wu , Wenyi Zhang

Information bottleneck is an information-theoretic principle of representation learning that aims to learn a maximally compressed representation that preserves as much information about labels as possible. Under this principle, two…

信息论 · 计算机科学 2023-11-08 Yuyan Ni , Yanyan Lan , Ao Liu , Zhiming Ma

Information Theory (IT) has been used in Machine Learning (ML) from early days of this field. In the last decade, advances in Deep Neural Networks (DNNs) have led to surprising improvements in many applications of ML. The result has been a…

机器学习 · 计算机科学 2019-04-09 Hassan Hafez-Kolahi , Shohreh Kasaei

The Information Bottleneck (IB) principle has emerged as a promising approach for enhancing the generalization, robustness, and interpretability of deep neural networks, demonstrating efficacy across image segmentation, document clustering,…

信息论 · 计算机科学 2025-04-18 Hanzhe Yang , Youlong Wu , Dingzhu Wen , Yong Zhou , Yuanming Shi

Deep Neural Networks (DNNs) are analyzed via the theoretical framework of the information bottleneck (IB) principle. We first show that any DNN can be quantified by the mutual information between the layers and the input and output…

机器学习 · 计算机科学 2015-03-10 Naftali Tishby , Noga Zaslavsky

The Information Bottleneck (IB) principle offers a compelling theoretical framework to understand how neural networks (NNs) learn. However, its practical utility has been constrained by unresolved theoretical ambiguities and significant…

机器学习 · 计算机科学 2026-02-02 Charles Westphal , Stephen Hailes , Mirco Musolesi

In this work, we generalize the information bottleneck (IB) approach to the multi-view learning context. The exponentially growing complexity of the optimal representation motivates the development of two novel formulations with more…

信息论 · 计算机科学 2022-09-20 Teng-Hui Huang , Aly El Gamal , Hesham El Gamal

In this theory paper, we investigate training deep neural networks (DNNs) for classification via minimizing the information bottleneck (IB) functional. We show that the resulting optimization problem suffers from two severe issues: First,…

机器学习 · 计算机科学 2020-08-10 Rana Ali Amjad , Bernhard C. Geiger

Although deep neural networks have been immensely successful, there is no comprehensive theoretical understanding of how they work or are structured. As a result, deep networks are often seen as black boxes with unclear interpretations and…

机器学习 · 计算机科学 2022-02-22 Ravid Shwartz-Ziv

Deep Neural Nets (DNNs) learn latent representations induced by their downstream task, objective function, and other parameters. The quality of the learned representations impacts the DNN's generalization ability and the coherence of the…

机器学习 · 计算机科学 2024-02-13 Nir Weingarten , Zohar Yakhini , Moshe Butman , Ran Gilad-Bachrach

The information bottleneck (IB) approach is popular to improve the generalization, robustness and explainability of deep neural networks. Essentially, it aims to find a minimum sufficient representation $\mathbf{t}$ by striking a trade-off…

机器学习 · 计算机科学 2024-04-30 Shujian Yu , Xi Yu , Sigurd Løkse , Robert Jenssen , Jose C. Principe

The Information Bottleneck (IB) framework is a general characterization of optimal representations obtained using a principled approach for balancing accuracy and complexity. Here we present a new framework, the Dual Information Bottleneck…

信息论 · 计算机科学 2020-06-09 Zoe Piran , Ravid Shwartz-Ziv , Naftali Tishby

The information bottleneck (IB) method is a technique for extracting information that is relevant for predicting the target random variable from the source random variable, which is typically implemented by optimizing the IB Lagrangian that…

机器学习 · 计算机科学 2020-12-23 Ziqi Pan , Li Niu , Jianfu Zhang , Liqing Zhang

The information bottleneck (IB) principle has been adopted to explain deep learning in terms of information compression and prediction, which are balanced by a trade-off hyperparameter. How to optimize the IB principle for better robustness…

机器学习 · 计算机科学 2021-03-04 Penglong Zhai , Shihua Zhang

The Information Bottleneck principle offers both a mechanism to explain how deep neural networks train and generalize, as well as a regularized objective with which to train models. However, multiple competing objectives are proposed in the…

机器学习 · 计算机科学 2021-01-06 Andreas Kirsch , Clare Lyle , Yarin Gal
‹ 上一页 1 2 3 10 下一页 ›