1 min readDec 4, 2019
Because stacking linear functions is useless / redundunt. Check my second blog post about this topic: https://medium.com/datathings/linear-layers-explained-in-a-simple-way-2319a9c2d1aa
(last section)
Written by Assaad MOAWAD
Interested in artificial intelligence, machine learning, neural networks, data science, blockchain, technology, astronomy. Co-founder of Datathings, Luxembourg