AutoML

Survery

Taking Human out of Learning Applications: A Survey on Automated Machine Learning

Automated model selection

Simple Search

• Grid search
• Random search

Derivative-Free Optimization

• Heuristic Search
• Model-Based Derivative-Free Optimization
  • Bayesian Optimization: builds a probabilistic model
    • Gaussian process
    • Tree-based model
    • Deep network

Neural Architecture serach

Automated Feature Engineering

Feature Enhancing Methods

Dimension reduction

• PCA -Principal components analysis [On lines and planes of closest fit to systems of points in space (1901)]
• LDA -Linear Discriminant Analysis [The use of multiple measurements in taxonomic problems]
• Auto-encoders Extracting and composing robust features with denoising autoencoders

Feature generation

Feature encoding

Papers

MnasNet (CVPR 2019)

MnasNet: Platform-Aware Neural Architecture Search for Mobile by Google

NAS-FPN (CVPR 2019)

NAS-FPN: Learning Scalable Feature Pyramid Architecture for Object Detection

EfficientNet (ICML 2019)

EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks by Google Brain
Blog | Code: tensorflow/tpu/models/official/efficientnet
如何评价谷歌大脑的EfficientNet？ - 知乎
used in EfficientDet

Others

Google’s AutoML: Cutting Through the Hype Neural architecture search vs. transfer learning: two opposite approaches

~[D] Google’s AutoML: Cutting Through the Hype grad student descent lol~