The Startup
Published in

The Startup

Meta-Learning and Neuroevolution

Machine Learning is a field of study whose aim is training statistical model on input data so that they can optimize themselves and make predictions on new, unseen data. Basically, we are asking our algorithm to learn from data.

But what happens if we ask our algorithm to learn…how to learn? This is exactly the kind of task that Meta-Learning aims at resolving. The key idea of this subfield of ML is that your algorithm, instead of being fed with raw data, takes as input the metadata resulting from the training process of a former algorithm: what the new algorithm is aiming…




Get smarter at building your thing. Follow to join The Startup’s +8 million monthly readers & +756K followers.

Recommended from Medium

How a simple mix of object-oriented programming can sharpen your deep learning prototype

Training neural networks for dummies — 04 pt 1 — train/validate/test split

End to End Recipe Cuisine Classification

The future of mapping is learned

The Concept of Error Analysis

A Machine Learning Approach to Predict Diabetic Patient Hospital Readmissions (contd..) — Part 10

Lightning Tutorials in collaboration with the University of Amsterdam (UvA)

Exploring new AI methods for road mapping

Get the Medium app

A button that says 'Download on the App Store', and if clicked it will lead you to the iOS App store
A button that says 'Get it on, Google Play', and if clicked it will lead you to the Google Play store
Valentina Alto

Valentina Alto

Cloud Specialist at @Microsoft | MSc in Data Science | Machine Learning, Statistics and Running enthusiast

More from Medium


Machine Learning for Neurodegenerative Diseases — What’s Next?

The severity of Airplane Accidents: Predictions using ML techniques

Techniques to Combat Class Imbalance in Machine Learning