Generic Multi Layered Perceptron, via chatGPT

MLP.py

class MultiLayeredPerceptron:
  def __init__(self, *layers):
    self.layers = layers
    
  def forward(self, input):
    # Perform a forward pass through the layers of the network
    for layer in self.layers:
      output = layer.forward(input)
      input = output
    return output

  def train(self, input, expected_output, learning_rate):
    # Perform a forward pass through the network to get the actual output
    actual_output = self.forward(input)
    
    # Calculate the error by subtracting the expected output from the actual output
    error = expected_output - actual_output

    # Backpropagate the error through the layers of the network
    for layer in self.layers[::-1]:
      error = layer.backpropagate(error, learning_rate)

class Layer:
  def __init__(self, weights, biases):
    self.weights = weights
    self.biases = biases
    
  def forward(self, input):
    # Calculate the output using the weights, biases, and sigmoid function
    output = 1 / (1 + math.exp(-(self.weights * input + self.biases)))
    return output

  def backpropagate(self, error, learning_rate):
    # Update the weights and biases based on the error and learning rate
    self.weights += learning_rate * error
    self.biases += learning_rate * error

    # Calculate the error for the previous layer
    previous_layer_error = error * self.weights
    
    return previous_layer_error