Transfer Learning
2 long-form posts on Transfer Learning: machine-learning research by Taha Bouhsine, each built around live, in-browser interactive visualizations.
-
Constructing the Fashion-MNIST Network, in JAX/Flax NNX
Train a small backbone and place its prototype head, then remove training entirely: implement fixed Sobel orientation channels, pool them into 343 named features, and classify with a constructed Yat head.
-
How Much of a Fashion-MNIST Network Can You Build by Hand?
Construct the prototype head on random and learned features, then replace the backbone with named edge and corner measurements. On Fashion-MNIST the zero-training pipeline reaches 83.3%, versus 85.7% for the matched trained model.