Google Brain -Automating Machine Learning (AutoML)
AutoML stands for automated machine learning, and basically refers to an algorithm autonomously building the best machine learning model for a given problem.
This task of selecting the best ML model is difficult as it is. There are many different ML algorithms to choose from, and each of these has many different settings ([hyper]parameters) you can change to optimalize the model’s predictions.
In their new paper, the Google Brain scholars display how they managed to automatically discover complete machine learning algorithms just using basic mathematical operations as building blocks. Using evolutionary principles, they have developed an AutoML framework that tailors its own algorithms and architectures to best fit the data and problem at hand.
This is AI research at its finest, and the results are truly remarkable!
Ideally, AutoML would cover the complete pipeline, from raw datasets to deployable ML models, to totally automate the process of applying ML to real-world problems. This is the ultimate goal — achieving high-level automation that would enable even non-experts to make use of ML models and techniques.
Automating the process of applying ML end-to-end can not only boost model performance but also produce simpler solutions and accelerate the creation of these solutions.
The Man behind Google’s AutoML
In 2011, Quoc Le co-founded Google Brain, together with his Ph.D. advisor Andrew Ng, Google Fellow Jeff Dean and Google Researcher Greg Corrado. The goal was exploring deep learning in the context of Google’s gigantic data. Before that, Le has done some pioneering work at Stanford on unsupervised deep learning.
AutoML: Neural Network Learns to Improve Itself
Training a deep neural network requires a large amount of labeled data and back-and-forth experiments: You choose an architecture, build hidden layers, and adjust weights based on outputs. For people with limited machine learning expertise, the training process is somehow painstaking and time-consuming.
The new approach can help researchers design a novel network architecture that matches the best human-invented architecture in test set accuracy on the CIFA-10 dataset. One year later, Le and Zoph took their study to the next level by proposing NASNet-A, a transferable architecture for large-scale image datasets.
Google launched AutoML Vision earlier this year. Last month at Google’s Cloud Next conference, the company released tools of translation and natural language.
Conclusion
Automated machine learning is an emerging research field within computer science that has the potential to help non-experts use machine learning off-the-shelf. We have reviewed the literature on a wide array of AutoML techniques, including hyperparameter optimization, automated feature engineering, pipeline optimization, and neural architecture search.