On information plane analyses of neural network classifiers—A review
BC Geiger - IEEE Transactions on Neural Networks and …, 2021 - ieeexplore.ieee.org
We review the current literature concerned with information plane (IP) analyses of neural
network (NN) classifiers. While the underlying information bottleneck theory and the claim …
network (NN) classifiers. While the underlying information bottleneck theory and the claim …
The information bottleneck problem and its applications in machine learning
Z Goldfeld, Y Polyanskiy - IEEE Journal on Selected Areas in …, 2020 - ieeexplore.ieee.org
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 …
playing a pivotal role in various aspect of society. The goal in statistical learning is to use …
Hrel: Filter pruning based on high relevance between activation maps and class labels
This paper proposes an Information Bottleneck theory based filter pruning method that uses
a statistical measure called Mutual Information (MI). The MI between filters and class labels …
a statistical measure called Mutual Information (MI). The MI between filters and class labels …
Averaging is probably not the optimum way of aggregating parameters in federated learning
P Xiao, S Cheng, V Stankovic, D Vukobratovic - Entropy, 2020 - mdpi.com
Federated learning is a decentralized topology of deep learning, that trains a shared model
through data distributed among each client (like mobile phones, wearable devices), in order …
through data distributed among each client (like mobile phones, wearable devices), in order …
Information flow in deep neural networks
R Shwartz-Ziv - arXiv preprint arXiv:2202.06749, 2022 - arxiv.org
Although deep neural networks have been immensely successful, there is no
comprehensive theoretical understanding of how they work or are structured. As a result …
comprehensive theoretical understanding of how they work or are structured. As a result …
Performance evaluation of deep learning models for image classification over small datasets: Diabetic foot case study
A Hernandez-Guedes, I Santana-Perez… - IEEE …, 2022 - ieeexplore.ieee.org
Data scarcity is a common and challenging issue when working with Artificial Intelligence
solutions, especially those including Deep Learning (DL) models for tasks such as image …
solutions, especially those including Deep Learning (DL) models for tasks such as image …
On the information plane of autoencoders
NI Tapia, PA Estévez - 2020 International Joint Conference on …, 2020 - ieeexplore.ieee.org
The training dynamics of hidden layers in deep learning are poorly understood in theory.
Recently, the Information Plane (IP) was proposed to analyze them, which is based on the …
Recently, the Information Plane (IP) was proposed to analyze them, which is based on the …
Bottleneck problems: An information and estimation-theoretic view
Information bottleneck (IB) and privacy funnel (PF) are two closely related optimization
problems which have found applications in machine learning, design of privacy algorithms …
problems which have found applications in machine learning, design of privacy algorithms …
Real-world graph convolution networks (rw-gcns) for action recognition in smart video surveillance
Action recognition is a key algorithmic part of emerging on-the-edge smart video
surveillance and security systems. Skeleton-based action recognition is an attractive …
surveillance and security systems. Skeleton-based action recognition is an attractive …
Information flows of diverse autoencoders
S Lee, J Jo - Entropy, 2021 - mdpi.com
Deep learning methods have had outstanding performances in various fields. A fundamental
query is why they are so effective. Information theory provides a potential answer by …
query is why they are so effective. Information theory provides a potential answer by …