Correct option is A
The process of training a
Neural Network follows these steps:
1.
Weight Initialization: Initialize the weights of the network randomly.
2.
Feed Forward: The input data is passed through the network to produce an output.
3.
Loss Calculation: The difference between the predicted output and the actual value is computed (e.g., using Mean Squared Error).
4.
Back Propagation: The error is propagated back through the network, updating the weights.
5.
Weight Update: The weights are updated based on the gradient of the error to minimize the loss function.
Information Booster:
1.
Neural Network Training: The goal is to adjust the weights to minimize the error (loss) over the training data.
2.
Back Propagation: This algorithm adjusts the weights in the direction that reduces the error, using the gradient descent method.
Additional Knowledge:
·
Feed Forward Neural Networks: Data flows in one direction from input to output without any feedback loops.
·
Loss Function: Common loss functions include Mean Squared Error (MSE) for regression tasks and Cross Entropy for classification tasks.