Cover Image
Read Now

Information Theory and Machine Learning

The recent successes of machine learning, especially regarding systems based on deep neural networks, have encouraged further research activities and raised a new set of challenges in understanding and designing complex machine learning algorithms. New applications require learning algorithms to be...

Full description

Bibliographic Details
Main Author: Zheng, Lizhong
Other Authors: Tian, Chao
Format: eBook
Language:English
Published: MDPI - Multidisciplinary Digital Publishing Institute 2022
Subjects:
Model Compression
Hgr Maximal Correlation
Merging Mixture Components
Information Theory
Rate Distortion Theory
Model-based Clustering
Independent And Non-identically Distributed Features
Fairness
Reservoir Computers
Rate Reduction
Empirical Risk
History Of Engineering And Technology / Bicssc
Deep Neural Network
Population Risk
Information Theoretic Learning
Technology: General Issues / Bicssc
Lempel-ziv Algorithm
Hidden Markov Models
Feature Extraction
Separation Criterion
Finite State Machines
Closed-loop Transcription
Atypicality
Information-theoretic Bounds
Spiking Neural Network
Linear Discriminative Representation
Analytical Error Probability
Overfitting
Recurrent Neural Networks
K-means Clustering
Distribution And Federated Learning
Information Criteria
Time Series Prediction
Vector Quantization
Minimum Error Entropy
Component Overlap
Long Short-term Memory
Entropy
Local Information Geometry
Pattern Dictionary
Artificial General Intelligence
Minimax Game
Meta-learning
Anomaly Detection
Independence Criterion
Generalization Error
Lossless Compression
Supervised Classification
Interpretability
Online Access:
Collection: Directory of Open Access Books - Collection details see MPG.ReNa
Description
Summary:The recent successes of machine learning, especially regarding systems based on deep neural networks, have encouraged further research activities and raised a new set of challenges in understanding and designing complex machine learning algorithms. New applications require learning algorithms to be distributed, have transferable learning results, use computation resources efficiently, convergence quickly on online settings, have performance guarantees, satisfy fairness or privacy constraints, incorporate domain knowledge on model structures, etc. A new wave of developments in statistical learning theory and information theory has set out to address these challenges. This Special Issue, "Machine Learning and Information Theory", aims to collect recent results in this direction reflecting a diverse spectrum of visions and efforts to extend conventional theories and develop analysis tools for these complex machine learning systems.
Item Description:Creative Commons (cc), https://creativecommons.org/licenses/by/4.0/
Physical Description:1 electronic resource (254 p.)
ISBN:books978-3-0365-5308-5
9783036553078
9783036553085

Similar Items