Stochastic Mutual Information Gradient Estimation for Dimensionality Reduction Networks (2021-05-01T00:00:00.000000Z)

TL;DR

This work presents a dimensionality reduction network (MMINet) training procedure based on the stochastic estimate of the mutual information gradient and introduces emerging information theoretic feature transformation protocols as an end-to-end neural network training approach.

Authors

Ozan Ozdenizci

1 papers

Deniz Erdoğmuş

2 papers

TL;DR

Authors

References51 items

Mutual Information Gradient Estimation for Representation Learning

Generative Adversarial Regularized Mutual Information Policy Gradient Framework for Automatic Diagnosis

Learning Invariant Representations From EEG via Adversarial Inference

Learning Disentangled Representations via Mutual Information Estimation

Data and Task Offloading in Collaborative Mobile Fog-Based Networks

Information Theoretic Feature Transformation Learning for Brain Interfaces

Deep Learning for Channel Coding via Neural Mutual Information Estimation

Learning deep representations by mutual information estimation and maximization

Mutual Information Neural Estimation

Estimating Mutual Information for Discrete-Continuous Mixtures

Methods for interpreting and understanding deep neural networks

Machine Learning Paradigms for Next-Generation Wireless Networks

On Pixel-Wise Explanations for Non-Linear Classifier Decisions by Layer-Wise Relevance Propagation

Mutual Information between Discrete and Continuous Data Sets

A Survey on Filter Techniques for Feature Selection in Gene Expression Microarray Analysis

Dimensionality reduction based on non-parametric mutual information

Introduction to machine learning for brain imaging

An Information Theoretic Linear Discriminant Analysis Method

Group lasso with overlap and graph lasso

Machine Learning in Bioinformatics

Adaptive filtering under maximum mutual information criterion

Information Discriminant Analysis: Feature Extraction with an Information-Theoretic Objective

Feature extraction using information-theoretic learning

Comparison of linear, nonlinear and feature selection methods for EEG signal classification

1-norm Support Vector Machines

Feature selection based on mutual information criteria of max-dependency, max-relevance, and min-redundancy

Comparison of linear, nonlinear, and feature selection methods for EEG signal classification

Online entropy manipulation: stochastic information gradient

Gene expression-based classification of malignant gliomas correlates better with survival than histological classification.

Feature Extraction by Non-Parametric Mutual Information Maximization

Input Feature Selection by Mutual Information Based on Parzen Window

Gene Selection for Cancer Classification using Support Vector Machines

Classification of human lung carcinomas by mRNA expression profiling reveals distinct adenocarcinoma subclasses

Nonparametric multivariate density estimation: a comparative study

Using mutual information for selecting features in supervised neural net learning

The MONK''s Problems-A Performance Comparison of Different Learning Algorithms, CMU-CS-91-197, Sch

Density Estimation for Statistics and Data Analysis

Probability of error, equivocation, and the Chernoff bound

On Estimation of a Probability Density Function and Mode

Transmission of Information: A Statistical Theory of Communications.

UCI machine learning repository

Chainer : a Next-Generation Open Source Framework for Deep Learning

Gene Selection for Cancer Classification using Support Vector Machines

Pattern Classiﬁcation

Reducing the Dimensionality of Data with Neural

Information Theoretic Feature Selection and Projection

Information-Theoretic Methods

Supporting Online Material for Reducing the Dimensionality of Data with Neural Networks

Information Theoretic Learning

An Introduction to Variable and Feature Selection

On the momentum term in gradient descent learning algorithms

Field of Study

Journal Information

Name

Page

Volume

Venue Information

Name

Type

URL

Alternate Names