ml.optimizer

class tinychain.ml.optimizer.Adam(*args, **kwargs)

Bases: Optimizer, Dynamic

Adam optimizer, an adaptive learning rate optimization algorithm designed to handle sparse gradients and noisy data.

Based on “Adam: A Method for Stochastic Optimization” by Kingma & Ba, 2014: https://arxiv.org/abs/1412.6980

train = <tinychain.reflect.stub.StateFunctionStub object>

class tinychain.ml.optimizer.GradientDescent(*args, **kwargs)

Bases: Optimizer, Dynamic

A simple gradient descent optimizer with a configurable learning rate.

train = <tinychain.reflect.stub.StateFunctionStub object>

class tinychain.ml.optimizer.Optimizer(*args, **kwargs)

Bases: Model

An optimizer for a Differentiable Model

train = <tinychain.reflect.stub.StateFunctionStub object>