README bug?

[hjm-aws]

The first code snippet in the README file contains the following fundtion:

def predict(params, inputs):
  for W, b in params:
    outputs = jnp.dot(inputs, W) + b
    inputs = jnp.tanh(outputs)
  return outputs

Did you folks intend to say outputs = jnp.tanh(outputs)?

[jakevdp]

Thanks for the question! This is a bit confusing, but it's correct as written. The idea is that the outputs of the current iteration become the inputs of the next iteration.

[hjm-aws]

Oh I missed the for loop. Thanks for the clarification!