Adaptive evolutionary algorithm for creating a deep learning architecture on the example of HAR

Deep learning is a powerful tool for solving complex problems such as image and speech recognition. However, finding the right architecture for a deep learning model can be a difficult and time-consuming task. That's where the adaptive evolutionary algorithm comes in.

The algorithm uses a combination of evolutionary techniques to automatically search for the best deep learning architecture for a given task. The algorithm goes through three optimization stages, each with a different set of techniques. The first stage uses techniques that make big changes to the model, while the last stage focuses on fine-tuning.

The algorithm also has an adaptive process built in. If the model's accuracy reaches a certain threshold, the algorithm switches to a stage with more fine-tuning techniques. If the algorithm cannot find a new best model within a certain time frame, it goes back to a stage with techniques that make bigger changes to the model.

This adaptive process helps the algorithm find the right balance between exploration and exploitation, resulting in a more efficient search for the best deep learning architecture.

In an example of Human activity recognition, the algorithm went through a fascinating process of finding an architecture to optimize the model's accuracy.

This algorithm is an exciting new tool that can save time and resources in the development of deep learning models. Try it out and see the results for yourself!

Open Source - Github