abstraction stack
Are High Level APIs Dumbing Down Machine Learning?
Implementing fully connected nets, convnets, RNNs, backprop and SGD from scratch (using pure python, numpy, or even JS) and training these models on small datasets is a great way to learn how neural nets work. Invest time to gain valuable intuition before jumping onto frameworks. This elicited a series of response tweets from François Chollet (@fchollet), creator of Keras, which, when considered collectively, presents a different point of view. Grad students knew how to implement neural nets in C in 2000. And they didn't have good intuition about them.