In a feedforward neural network, the output from one layer is used as input to the next layer. Forward propagation means movement happens only from input to the output. This means there are no loops in the network and information is always fed forward.

Input data passes into a layer where calculations are performed. The new values become the new input values that feed the next layer. This continues through all the layers and determines the output.

First, we need to train a model and assign specific weights to each of those inputs. Initially, we do not know the specific weight required by those inputs. The value of the weight depends on the priority of the feature in the dataset. The higher the weight, the greater the importance. At first, we assign some random weights to our inputs. , and our model calculates the error in prediction.

First, we need to train a model and assign specific weights to each of those inputs. Initially, we do not know the specific weight required by those inputs. The value of the weight depends on the priority of the feature in the dataset. The higher the weight, the greater the importance. At first, we assign some random weights to our inputs. , and our model calculates the error in prediction.

The weight matrix between layer 0 (the input layer) and the first hidden layer is denoted by W1. The dot product between W1 and the input xi along with the bias b, W1.xi+b, acts as the input to layer 1. The activation function is applied to this input to compute the output of the first layer. These random weights will get optimized during backward propagation.

Based on the weights and transfer function, the activation value passes to the next node. Each of the nodes sums the activation values that it receives (**weighted sum**) and modifies that sum based on its transfer function. Then it applies an activation function. An activation function is a function that’s applied to this particular neuron. From that, the neuron understands if it needs to pass along a signal or not. The activation runs through the network until it reaches the output nodes.

A feedforward network is a network that contains inputs, random weights, bias, outputs, and hidden layers. The signals can only travel in one direction (forward).