WRITE · TRACE · UNDERSTAND
Adam Optimizer
Follow first and second moment estimates, then correct their initial bias.
Your experiment
adam_step(w, gradient, m, v, t, lr, beta1, beta2, epsilon) returns (new_w, new_m, new_v). t starts at 1 and epsilon > 0. Apply bias correction to both moments.
Python runs in your browser. Your draft stays on this device.
What to look for
Follow first and second moment estimates, then correct their initial bias. This is a scalar teaching implementation with epsilon outside the square root.
Watch your code work
Ready to experimentWrite a solution or load the worked answer, then choose Trace & check.
Step through arrays, variables and training curves produced by your own Python.