Blog
Notes on usage of the classic sigmoid and tanh activation functions
Sat, Jan 18, 2025
We never achieved satisfactory results in training neural networks containing ONLY sigmoid and tanh activation functions. However, by exposing a "slope" parameter of the functions and making it a learnable parameter of the network changed the situation.
Learning trading rules with MLP with enforced sparsity condition
Publication date: Tue, 11 Feb, 2025
In this post we explain how zero cost tweak of the fully connected MLP can better fit to your trading rule original design.