中文
相关论文

相关论文: FlowNIB: An Information Bottleneck Analysis of Bid…

200 篇论文

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

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

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) 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

The Information Bottleneck (IB) objective uses information theory to formulate a task-performance versus robustness trade-off. It has been successfully applied in the standard discriminative classification setting. We pose the question…

机器学习 · 计算机科学 2021-01-13 Lynton Ardizzone , Radek Mackowiak , Carsten Rother , Ullrich Köthe

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 Bottleneck (IB) is a widely used framework that enables the extraction of information related to a target random variable from a source random variable. In the objective function, IB controls the trade-off between data…

机器学习 · 计算机科学 2025-08-13 Sota Kudo , Naoaki Ono , Shigehiko Kanaya , Ming Huang

Efficient communication requires balancing informativity and simplicity when encoding meanings. The Information Bottleneck (IB) framework captures this trade-off formally, predicting that natural language systems cluster near an optimal…

计算与语言 · 计算机科学 2026-04-07 Antoine Taroni , Ludovic Moncla , Frederique Laforest

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

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 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

Learning effective joint embedding for cross-modal data has always been a focus in the field of multimodal machine learning. We argue that during multimodal fusion, the generated multimodal embedding may be redundant, and the discriminative…

机器学习 · 计算机科学 2022-12-06 Sijie Mai , Ying Zeng , Haifeng Hu

The Information Bottleneck (IB) method is an information theoretical framework to design a parsimonious and tunable feature-extraction mechanism, such that the extracted features are maximally relevant to a specific learning or inference…

信号处理 · 电气工程与系统科学 2024-04-17 Francesco Binucci , Paolo Banelli , Paolo Di Lorenzo , Sergio Barbarossa

The task of identifying multimodal image-text representations has garnered increasing attention, particularly with models such as CLIP (Contrastive Language-Image Pretraining), which demonstrate exceptional performance in learning complex…

计算机视觉与模式识别 · 计算机科学 2025-02-24 Zhiyu Zhu , Zhibo Jin , Jiayu Zhang , Nan Yang , Jiahao Huang , Jianlong Zhou , Fang Chen

Compact neural networks are essential for affordable and power efficient deep learning solutions. Binary Neural Networks (BNNs) take compactification to the extreme by constraining both weights and activations to two levels, $\{+1, -1\}$.…

机器学习 · 计算机科学 2020-06-16 Vishnu Raj , Nancy Nayak , Sheetal Kalyani

Normalization is fundamental to deep learning, but existing approaches such as BatchNorm, LayerNorm, and RMSNorm are variance-centric by enforcing zero mean and unit variance, stabilizing training without controlling how representations…

机器学习 · 计算机科学 2026-01-30 Xiandong Zou , Jia Li , Xiaotong Yuan , Pan Zhou

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

Effective adaptation to distribution shifts in training data is pivotal for sustaining robustness in neural networks, especially when removing specific biases or outdated information, a process known as machine unlearning. Traditional…

机器学习 · 计算机科学 2024-05-24 Ling Han , Hao Huang , Dustin Scheinost , Mary-Anne Hartley , María Rodríguez Martínez

Maintaining efficient semantic representations of the environment is a major challenge both for humans and for machines. While human languages represent useful solutions to this problem, it is not yet clear what computational principle…

计算与语言 · 计算机科学 2018-08-13 Noga Zaslavsky , Charles Kemp , Terry Regier , Naftali Tishby

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
‹ 上一页 1 2 3 10 下一页 ›