Supervised Learning
Describes a problem where parameters of a function approximator are optimized such that they minimize a given Loss Function. The user provides Training Data and Validation Data for cross-validation.
Usage
e["Problem"]["Type"] = "SupervisedLearning"
Variable-Specific Settings
These are settings required by this module that are added to each of the experiment’s variables when this module is selected.
- Name
Usage: e[“Variables”][index][“Name”] = string
Description: Defines the name of the variable.
Configuration
These are settings required by this module.
- Training Batch Size
Usage: e[“Problem”][“Training Batch Size”] = unsigned integer
Description: Stores the batch size of the training dataset.
- Testing Batch Size
Usage: e[“Problem”][“Testing Batch Size”] = unsigned integer
Description: Stores the batch size of the testing dataset.
- Max Timesteps
Usage: e[“Problem”][“Max Timesteps”] = unsigned integer
Description: Stores the length of the sequence for recurrent neural networks.
- Input / Data
Usage: e[“Problem”][“Input”][“Data”] = List of Lists of List of float
Description: Provides the input data with layout T*N*IC, where T is the sequence length, N is the batch size and IC is the vector size of the input.
- Input / Size
Usage: e[“Problem”][“Input”][“Size”] = unsigned integer
Description: Indicates the vector size of the input (IC).
- Solution / Data
Usage: e[“Problem”][“Solution”][“Data”] = List of Lists of float
Description: Provides the solution for one-step ahead prediction with layout N*OC, where N is the batch size and OC is the vector size of the output.
- Solution / Size
Usage: e[“Problem”][“Solution”][“Size”] = unsigned integer
Description: Indicates the vector size of the output (OC).
Default Configuration
These following configuration will be assigned by default. Any settings defined by the user will override the given settings specified in these defaults.
{ "Input": { "Data": [] }, "Max Timesteps": 1, "Solution": { "Data": [] } }