Multi-layer Perceptron classifier

[PondiB]

No description provided.

[soxofaan]

some small notes

[jonas-hurst]

This might need some minor corrections. We cannot specify a specific activation function per layer. A choice might be more appropriate

• a single string: activation function applied to all layers
• an array of strings: one string to specify the activation function for each layer

It might also be helpful to include softmax here, commonly used on the output layer, helpful for uncertainty quantification.

This could be the schema then:

{
  "oneOf": [
    {
      "type": "string",
      "enum": ["relu", "tanh", "sigmoid", "softmax"]
    },
    {
      "type": "array",
      "items": {
        "type": "string",
        "enum": ["relu", "tanh", "sigmoid", "softmax"]
      }
    }
  ],
  "default"="relu"
}

[jonas-hurst]

We define the shape of hidden layers here. But where do we define the shape of input and output layers?
Suggestion: Rename this parameter to layers to include input and output.

[jonas-hurst]

Could be helpful to somehow divide training data into train/test to get training statistics independently from the training data, e.g.

{
  "name": "train_test_split",
  "description": "defines the ration by which data is split into training and test samples",
  "schema": {
    "type": "number",
    "minimum": 0.0,
    "maximum": 1.0,
    "default": 0.8
  }
}