Skip to content

Summarize ,share and spread neural network training experiences for reducing trial and error

Notifications You must be signed in to change notification settings

pku-H2R/AI-Alchemy

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

90 Commits
 
 
 
 
 
 
 
 

Repository files navigation

The goal of this project is to summarize the various experiences in the neural network training process. When we train the network, we always have to face two major problems. One is the design of the network structure, and the other is the training configuration of the network, which is hyperparameter tuning

Content

Pipeline

  • Vectorization
  • Preprocessing
    • Data Normalization
      • zero mean
      • unit variance
    • Feature Scaling
    • Imbalanced Data
    • Missing Data
  • Problem
    • Overfitting
      • Data
        • Collect more Data
        • Dimensionality Reduction
        • Data Augmentation
      • Model
        • Dropout
        • Early Stopping
        • Batch Normalization
        • Weight Regularizers
        • Reducing network size
    • Gradient Vanishing/Exploding
      • Vanishing
        • Initialization Weight
        • ReLU
      • Exploding
        • Gradient Clipping
    • Reproducible Results

Neural-Architecture-Search

Picture

  • Automatic
    • NASnet
    • MNASnet
    • SNAS
    • EAT-NAS
    • Genetic CNN
    • Hierarchical Representations
  • Manual

Hyperparameter-Tuning/Optimization

Website

About

Summarize ,share and spread neural network training experiences for reducing trial and error

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published