Research

I wrote my first neural networks in pure C, then in Matlab, then in NumPy, before eventually upgrading to Theano. Since then I have seen and…

I wrote my first neural networks in pure C, then in Matlab, then in NumPy, before eventually upgrading to Theano. Since then I have seen and tried pretty much every NN framework ever developed. Some a

DGX agentx-post
researchfrancois-chollet--x

I wrote my first neural networks in pure C, then in Matlab, then in NumPy, before eventually upgrading to Theano. Since then I have seen and tried pretty much every NN framework ever developed. Some are bad, some are good. The good ones understand API design principles.

Source: Francois Chollet (X) | 2026-06-08

Loading related sources…