![]() |
Fido
|
![]() ![]() | |
![]() ![]() ![]() | Genetic algorithms used to produce fit neural networks |
![]() ![]() | |
![]() ![]() ![]() | An adaptive learning rate Trainer (Zeiler) |
![]() ![]() ![]() | A classic SGDTrainer |
![]() ![]() ![]() | A layer in a NeuralNet |
![]() ![]() ![]() | A neural network |
![]() ![]() ![]() | A neuron in a Layer of a NeuralNet |
![]() ![]() ![]() | Removes unnecessary neurons from a NeuralNet |
![]() ![]() ![]() | A classic backpropagation SGD Trainer |
![]() ![]() ![]() | Trains neural networks |
![]() ![]() | |
![]() ![]() ![]() | A highly effective reinforcement learning control system (Truell and Gruenstein) |
![]() ![]() ![]() ![]() | |
![]() ![]() ![]() | A multi-dimensional data point |
![]() ![]() ![]() | An interpolator of multi-dimensional data points |
![]() ![]() ![]() | A reinforcement learning system |
![]() ![]() ![]() | A least squares wire fitted Interpolator |
![]() ![]() ![]() | |
![]() ![]() ![]() | A Learner that follows the Q-Learning algorithm |
![]() ![]() ![]() | A Learner using Q-learning that works with continous state action spaces (Gaskett et al.) |
![]() ![]() | |
![]() ![]() | |
![]() ![]() | |
![]() ![]() | A robotic simulator |
![]() ![]() |