What is the AutoML?

• A trial-and-error process means that even experts require substantial resources and time to create well-performing models. To solve repetitive and experimental learning, automated machine learning (AutoML) is a promising solution for building a DL system without human assistance.

  

• Selected the review paper on the state of the art in AutoML field, published in 2021

  • Paper: https://arxiv.org/pdf/1908.00709v6.pdf

  • It covers the 4 categories such as data preparation, feature engineering, model generation and model estimation

    

AutoML

1. AutoML-Zero: Evolving Machine Learning Algorithms From Scratch
2. Auto-Classifier: A Robust Defect Detector Based on an AutoML Head
3. AutoSmart: An Efficient and Automatic Machine Learning framework for Temporal Relational Data
4. LightAutoML: AutoML Solution for a Large Financial Services Ecosystem

NAS (Neural Architecture Search)

1. Auto-Keras: An Efficient Neural Architecture Search System
2. Single-Path Mobile AutoML: Efficient ConvNet Design and NAS Hyperparameter Optimization

SOTA Paper for training model

1. Offsite-Tuning: Transfer Learning without Full Model
2. The Forward-Forward Algorithm: Some Preliminary Investigations