Components¶
Here is a list of classes in the package.
Overview:
- class neural_network.Edge(left_neuron: Neuron, right_neuron: Neuron)[source]¶
Class to represent an Edge joining two Nodes of a network
- class neural_network.Layer(_id: int, num_neurons: int)[source]¶
Class to represent one Layer of a network
- class neural_network.Network(num_features: int, num_hidden_layers: int, neuron_counts: List[int], num_classes: int = 2, regression: bool = False, leak: float = 0.01, learning_rate: float = 0.01, adaptive: bool = False, gamma: float = 0.9, he_weights: bool = False)[source]¶
Class to represent the whole Network
- __init__(num_features: int, num_hidden_layers: int, neuron_counts: List[int], num_classes: int = 2, regression: bool = False, leak: float = 0.01, learning_rate: float = 0.01, adaptive: bool = False, gamma: float = 0.9, he_weights: bool = False)[source]¶
Constructor method
- Parameters:
num_features (int) – The number of features for the network
num_hidden_layers (int) – The total number of hidden Layers in the Network
neuron_counts (List[int]) – A list of numbers of Neurons for each hidden Layer
num_classes (int) – The number of classes for the classification task
regression (bool) – Whether we are performing regression or not (if False we are performing classification)
leak (float) – The leak rate of LeakyReLU
learning_rate (float) – The learning rate of the network
adaptive (bool) – Whether we wish to have an adaptive learning rate or not
gamma (float) – The adaptive learning rate parameter
he_weights (bool) – Whether we wish to initialise the weights according to He or not
- _activate_output_layer(z_list: List[float]) List[float][source]¶
Activates the values from the output_layer using the Softmax activation function.
- Returns:
The List of softmax probabilities
- Return type:
List[float]
- _calculate_pre_activated_value(left_layer: Layer, right_neuron: Neuron) float[source]¶
Given a left_layer and a right_neuron, this calculates the activation function and value from the left_layer and propagates this value to the right_neuron
- back_propagate_bias(neuron: Neuron)[source]¶
Uses the bias gradients of all datapoints (for this specific neuron) to perform gradient descent and calculate a new bias for this neuron.
- neuronNeuron
The Neuron whose bias we are interested in updating
- back_propagate_weight(edge: Edge)[source]¶
Uses the loss gradients of all datapoints (for this specific edge) to perform gradient descent and calculate a new weight for this edge.
- edgeEdge
The Edge whose weight we are interested in updating
- forward_pass_one_datapoint(x: array) List[float][source]¶
Performs a forward pass for one datapoint, excluding the ground truth value. This method returns the predicted value in the final neuron in the output layer.
- Parameters:
x (np.array) – The input value, with all features
- Returns:
The softmax probabilities of each class (for classification) or the predicted regression value (for regression)
- Return type:
List[float]
- get_edges() List[List[List[Edge]]][source]¶
Getter method for edges
- Returns:
A list of Edges
- Return type:
List[List[List[Edge]]]
- get_layers() List[Layer][source]¶
Getter method for layers
- Returns:
A list of Layers
- Return type:
List[Layer]
- get_neuron_counts() List[int][source]¶
Getter method for neuron_counts.
- Returns:
A list of numbers of neurons per layer
- Return type:
List[int]
- is_regressor() bool[source]¶
Getter method for regression.
- Returns:
Whether we do regression or classification
- Return type:
bool
- store_gradient_of_loss(edge: Edge, target: float, first: bool)[source]¶
Calculates the gradient of the loss function with respect to one weight (assigned to the edge) based on the values at edges of future layers. One part of the back propagation process.
- edgeEdge
The Edge containing the weight we are interested in
- targetint
The target value for the final output node for this specific datapoint
- firstbool
Determines whether we find the bias gradient or not