training -> loss -> (gradient + optimiser) -> parameters
model
loss function
eg cross_entropy
gradients
optimise parameters
We need an optimizer that can make use of the gradients to update the parameters. In complex cases, we might need more than one optimizer (e.g. GANs).
Bias
??
Lingo
tensor = array
Tooling
run jupyter on all ports:
./venv/bin/python3 venv/bin/jupyter-lab --ip=0.0.0.0