Skip to main content
from onyxengine.modeling import MLPConfig

config = MLPConfig(
    outputs: List[Output],
    inputs: List[Input],
    dt: float,
    sequence_length: int = 1,
    hidden_layers: int = 2,
    hidden_size: int = 32,
    activation: Literal['relu', 'gelu', 'tanh', 'sigmoid'] = 'relu',
    dropout: float = 0.0,
    bias: bool = True
)
Configuration class for Multi-Layer Perceptron models.

​
Parameters

​
outputs
List[Output]
required
List of output feature definitions.
​
inputs
List[Input]
required
List of input feature definitions.
​
dt
float
required
Time step in seconds. Must match your dataset’s sampling rate.
​
sequence_length
int
default:"1"
Length of the input sequence (history window). Range: 1-100.
​
hidden_layers
int
default:"2"
Number of hidden layers. Range: 1-10.
​
hidden_size
int
default:"32"
Number of neurons per hidden layer. Range: 1-1024.
​
activation
Literal
default:"relu"
Activation function. Options: 'relu', 'gelu', 'tanh', 'sigmoid'.
​
dropout
float
default:"0.0"
Dropout rate for regularization. Range: 0.0-1.0.
​
bias
bool
default:"True"
Whether to include bias terms in linear layers.

​
Example

from onyxengine.modeling import MLPConfig, Input, Output

outputs = [Output(name='acceleration')]
inputs = [
    Input(name='velocity', parent='acceleration', relation='derivative'),
    Input(name='position', parent='velocity', relation='derivative'),
    Input(name='control_input'),
]

config = MLPConfig(
    outputs=outputs,
    inputs=inputs,
    dt=0.01,
    sequence_length=8,
    hidden_layers=3,
    hidden_size=64,
    activation='relu',
    dropout=0.2,
    bias=True
)

​
Architecture

The MLP flattens the input sequence and passes it through fully-connected layers: 
Input: (batch, sequence_length, num_inputs)
  ↓ Flatten to (batch, sequence_length * num_inputs)
  ↓ Linear(in, hidden_size) → LayerNorm → Activation → Dropout
  ↓ Linear(hidden_size, hidden_size) → LayerNorm → Activation → Dropout
  ↓ ... (hidden_layers times)
  ↓ Linear(hidden_size, num_outputs)
Output: (batch, num_outputs)

​
MLPOptConfig

For hyperparameter optimization, use MLPOptConfig: 
from onyxengine.modeling import MLPOptConfig

mlp_opt = MLPOptConfig(
    outputs=outputs,
    inputs=inputs,
    dt=0.01,
    sequence_length={"select": [1, 4, 8, 12]},
    hidden_layers={"range": [2, 5, 1]},
    hidden_size={"select": [32, 64, 128]},
    activation={"select": ['relu', 'gelu', 'tanh']},
    dropout={"range": [0.0, 0.4, 0.1]},
    bias=True
)