

N1H111SM's Miniverse

Learning Representations by Maximizing Mutual Information Across Views

N1H111SM's Miniverse

Learning Representations by Maximizing Mutual Information Across Views

MI

字数统计: 11阅读时长: 1 min

 2020/06/24   Share

• 
• 
• 
• 
• 

Materials

• paper “Learning Representations by Maximizing Mutual Information Across Views”

Motivation

原文作者：Haizhou Shi

原文链接：http://www.shihaizhou.com/2020/06/24/Learning-Representations-by-Maximizing-Mutual-Information-Across-Views/

发表日期：June 24th 2020, 2:13:07 pm

更新日期：June 24th 2020, 2:45:22 pm

版权声明：本文采用知识共享署名-非商业性使用 4.0 国际许可协议进行许可

• Next Post
  Bagging
• Previous Post
  Momentum Contrast for Unsupervised Visual Representation Learning

Powered by Hexotheme Archer

PV: :)

CATALOG

1. 1. Motivation



• Archive
• Tag
• Cate

Total : 55

2020

• 10/20RAFT, solving the Puzzle of BYOL
• 07/24EM Algorithm
• 07/19RL environment & stable-baselines
• 06/28Bias-Variance Decompostion
• 06/27Bagging
• 06/24Learning Representations by Maximizing Mutual Information Across Views
• 06/23Momentum Contrast for Unsupervised Visual Representation Learning
• 06/22Bootstrap Your Own Latent: A New Approach to Self-Supervised Learning
• 06/20Lipschitz Continuity
• 06/17Legendre Transform and Fenchel Conjugate
• 06/16Generative Adversarial Networks
• 06/14Manifold Learning
• 06/10Disentangled Representation Learning via Mutual Information Estimation
• 06/09InfoAE - Unpublished
• 06/08InfoGAN
• 06/04Discriminative Clustering by Regularized Information Maximization
• 05/28Pytorch Techniques
• 05/27Information Competing Process for Learning Diversified Representations
• 05/26InfoBal - Ideas (failed)
• 05/26What Makes for Good Views for Contrastive Learning
• 05/25Contrastive Multiview Coding
• 05/22On MI Maximization for Representation Learning
• 05/22Variational Auto-Encoders
• 05/21Deep InfoMax
• 05/20SGD Optimizers
• 05/19Pytorch - Batch Sparse Matrix on GPU
• 05/17InfoGraph - Experiments
• 05/17Pytorch - nn.ModuleList vs nn.Sequential
• 05/17Sparse Matrix
• 05/16GCN - Code Explanation
• 05/13Mutual Information Maximization - Experiments
• 05/10Mutual Information Maximization - Theory
• 05/09InfoGraph
• 05/08Graph-Level Representation Learning via Graph-Graph Proximity
• 05/03BERT
• 05/03ELMo - Deep Contextualized Word Representations
• 03/06RSA Algorithm
• 03/03Subgraph Related
• 02/29How Powerful are GNNs?
• 02/28Graph Neural Networks - Survey
• 02/28Visual Exploration
• 02/28Graph Attention Networks
• 02/25Graph Convolutional Neural Networks
• 02/24Transformer Basics
• 02/23Grammar of Java
• 02/22Graph Neural Networks - Basics
• 02/17Information Theory
• 02/11Metric Space

2019

• 09/04RL(4) - Value Function Approximation
• 08/15RL(3) - Model-Free Control
• 08/13Emergent Communication Through Negotiation
• 07/15RL(2) - Model-Free Policy Evaluation
• 07/10RL(1) - MP, MRP, MDP
• 06/12Google Research Football - RL Environment

Invalid date

• Invalid dateGoogle Football Warm Start

Code Representation Learning NLP Basics MI Contrastive GNN RL GAN Manifold Negotiation CV poker FL overview



缺失模块。
1、请确保node版本大于6.2
2、在博客根目录（注意不是archer根目录）执行以下命令：
npm i hexo-generator-json-content --save
3、在根目录_config.yml里添加配置：

jsonContent:
  meta: false
  pages: false
  posts:
    title: true
    date: true
    path: true
    text: false
    raw: false
    content: false
    slug: false
    updated: false
    comments: false
    link: false
    permalink: false
    excerpt: false
    categories: true
    tags: true

