Open TreeinRandomForest opened 3 years ago
Do this with MNIST (or a simple dataset) before the retinopathy data.
Goal: to learn an architecture that gives maximal validation score
Techniques:
Make the following plot: x-axis: train time y-axis: validation score
Inspect the architectures learned. Use a small set of primitives (conv layers, pool layers, a few fixed kernel sizes etc.)
Do this with MNIST (or a simple dataset) before the retinopathy data.
Goal: to learn an architecture that gives maximal validation score
Techniques:
Make the following plot: x-axis: train time y-axis: validation score
Inspect the architectures learned. Use a small set of primitives (conv layers, pool layers, a few fixed kernel sizes etc.)