My first keras experiments:
simplest.py— A single neuron with no activation function and no bias (so just input→weight→output, can learn y=mx functions only). Show the function for a few random weights. (Doesn't learn anything.)
linear with bias.py— A single neuron with no activation function but with bias (so it can learn y=mx+b functions, such as relationship between Celsius and Fahrenheit).
single_neuron_buffer.py— A single neuron with sigmoid activation and no bias, trained to learn a digital logic buffer.
single_neuron_inverter.py— A single neuron with sigmoid activation and no bias, trained to learn an inverting analog amplifier.