What is forward propagated in a neural network?1 pointWeights and biasesSumming weightInputActivation function

In a neural network, the input and the activation function are forward propagated. Here's a step-by-step explanation:

1. The process begins with the input data. This is the information that you feed into the neural network for processing.

2. Each input is then multiplied by a weight. Weights are parameters within the network that transform the input data to get the output in the desired form. They are usually initialized randomly and get updated as the network learns.

3. The weighted inputs are then summed together, often with a bias (another parameter of the network) added to the sum. The bias allows the network to shift the activation function to the left or right, which can be critical for successful learning.

4. This sum is then passed through an activation function. The activation function is used to introduce non-linearity into the output of a neuron. This transformed sum is the output of the neuron.

5. This output is then used as input to the next layer in the network, and the process repeats.

So, in summary, what is forward propagated in a neural network is the input data and the transformations of that data as it passes through each layer of the network, including the weights, biases, and activation functions.