Machine Learning | Artificial Intelligence

963 readers

5 users here now

Welcome to Machine Learning – a versatile digital hub where Artificial Intelligence enthusiasts unite. From news flashes and coding tutorials to ML-themed humor, our community covers the gamut of machine learning topics. Regardless of whether you're an AI expert, a budding programmer, or simply curious about the field, this is your space to share, learn, and connect over all things machine learning. Let's weave algorithms and spark innovation together.

founded 2 years ago

MODERATORS

Hopps

A newbie question on neural network (sopuli.xyz)

submitted 2 years ago by [email protected] to c/machinelearning

4 comments fedilink hide all child comments

In the hidden layer, the activation function will decide what is being determined by the neural network, is it possible for an AI to generate activation function for itself so it can improve upon itself?

you are viewing a single comment's thread
view the rest of the comments

[–] model_tar_gz 4 points 2 years ago

The ‘swish’ activation function is f(x) = x.sigmoid(B.x).

B is typically set to 1, but it doesn’t have to be. You can use it as a parameter for the model to learn if you want. I’ve played with it and not really seen any significant benefit though; I’ve found that allowing the learning rate and/or batch size to vary are more impactful than a learned activation function. Also you can end up with vanishing or exploding gradients if you don’t constrain B; and even then B might saturate depending on what happens during training.

The choice of activation function itself is more impactful than allowing it to be dynamic/learned.

Happy learning!