![]() |
OpenANN
1.1.0
An open source library for artificial neural networks.
|
Represents the action space in a reinforcement learning problem | |
| A (learning) agent in a reinforcement learning problem | |
| Loads the CIFAR-10 dataset | |
| Creates several types of matrices for compression | |
| A helper class for specifying weight constrains in a higher-order neural network Derive a new class from this interface and simple reimplement the function call operator for the corresponding higher-order term | |
| Data set interface | |
| Streams training data for online training | |
| Creates distorted images | |
| Evaluates a Learner | |
| STL class | |
| Wraps a value and its precision for logging | |
| Interface that has to be implemented by all layers of a neural network that can be trained with backpropagation | |
| Global logger | |
| A local logger that can redirect messages to several targets | |
| Provides information about the OpenANN library | |
| Represents an optimizable object | |
| The common interface of all optimization algorithms | |
| Provides information about the output of a layer | |
| A utility class that simplifies the generation of random numbers | |
| Holds all information related to regularization terms in an error function | |
Represents the state space in a reinforcement learning problem | |
| Stopping criteria for optimization algorithms | |
| A system-independent interface for checking interrupts that can signals the end of the optimization process externally | |
| Common base for all transformations | |
1.8.4