How to build a simple neural network in 9 lines of Python code
Milo Spencer-Harper
5.6K50

Nice try but small revision is required:

(1) all outputs are binary {0;1} so sigmoid activation is doubtedly a proper choice. It can’t produce binary output but instead outputs in range (0,1) exclusively. So the correct outputs will never be produced (only close-to-binary outputs like 0.99 or 1e-3). This may confuse beginner who is trying to understand the basics.

(2) 10K iterations for 4(!) binary samples are definitely too much

Good try to explain how a neuron works (but I would argue this is a NN).

Keep rocking!

One clap, two clap, three clap, forty?

By clapping more or less, you can signal to us which stories really stand out.