One-variable function approximation with four-layer DNN

Overview

In order to understand Chainer's Optimizer, I wrote a one-variable function approximation program with 4-layer DNN, referring to this. For some reason, this program did not perform forward calculation with the call function that inherited Chain, so I decided to fix it. I put the program I fixed on my github. I tried sin, exp, sqrt, abs, sqrt (abs (sin (exp (x))).

result

exp Good vibes. DALP1ntVoAAs5fb.jpg sin There is a place that is blurry. DALP2fQVYAAwK2x.jpg sqrt Good vibes. DALP3N4VoAAHNdd.jpg abs It feels good contrary to expectations. DALQFWsUAAAtzuW.jpg sqrt(abs(sin(exp(x))) I feel motivated. DALSLzHV0AQOL3L.jpg

What I thought

The development environment is terribly difficult to build (due to Python's packaging system). Not only the first time, but it is troublesome to start every time.

Recommended Posts

One-variable function approximation with four-layer DNN
Try function optimization with Optuna
Implement login function with django-allauth
Approximate sin function with TensorFlow
Zura with softmax function implemented