AutoML: Automatic Machine Learning

     Automated Machine Learning provides methods and processes to make Machine Learning available for non-Machine Learning experts, to improve efficiency of Machine Learning and to accelerate research on Machine Learning.

    

       Machine learning (ML) has achieved considerable successes in recent years and an ever-growing number of disciplines rely on it. However, this success crucially relies on human machine learning experts to perform the following tasks:

• Preprocess and clean the data.
• Select and construct appropriate features.
• Select an appropriate model family.
• Optimize model hyperparameters.
• Design the topology of neural networks (if deep learning is used).
• Postprocess machine learning models.
• Critically analyze the results obtained.

    As the complexity of these tasks is often beyond non-ML-experts, the rapid growth of machine learning applications has created a demand for off-the-shelf machine learning methods that can be used easily and without expert knowledge. We call the resulting research area that targets progressive automation of machine learning AutoML.

    AutoML helps to make machine learning less of a black box by making it more accessible. This process automates parts of the machine learning process that apply the algorithm to real-world scenarios. A human performing this task would need an understanding of the algorithm's internal logic and how it relates to the real-world scenarios. It learns about learning and makes choices that would be too time-consuming or resource-intensive for humans to do with efficiency at scale.

   

    With automated ML you provide the training data to train ML models, and you can specify what type of model validation to perform. Automated ML performs model validation as part of training. That is, automated ML uses validation data to tune model hyperparameters based on the applied algorithm to find the best combination that best fits the training data. However, the same validation data is used for each iteration of tuning, which introduces model evaluation bias since the model continues to improve and fit to the validation data.

    To help confirm that such bias isn't applied to the final recommended model, automated ML supports the use of test data to evaluate the final model that automated ML recommends at the end of your experiment. When you provide test data as part of your AutoML experiment configuration, this recommended model is tested by default at the end of your experiment (preview).

    Auto-ML is in development so it can give efficient results, but it needs some improvements, because now it’s very limited to supervised learning and it has a lot of difficulties in case unsupervised and reinforcement learning.

References consulted during research:

https://towardsdatascience.com/automl-for-predictive-modeling-32b84c5a18f6

https://medium.com/@miloudbelarebia/does-auto-machine-learning-auto-ml-really-exists-64fa538eb7a6

https://www.techtarget.com/searchenterpriseai/definition/automated-machine-learning-AutoML