Module Question 6 -BD107-Amelia Nurul Mupty-2581499006

1. Draw a simple diagram of a neuron and label its components (inputs, weights, bias, activation function).
2. What is the purpose of an activation function (like Sigmoid or ReLU)?
3. What is the purpose of an activation function (like Sigmoid or ReLU)?
4. What is the difference between an input layer, a hidden layer, and an output layer?

The Answer

1. Draw a simple diagram of a neuron and label its components.
   
   2. The purpose of an activation function is to introduce non-linearity into a neural network. This allows the network to learn complex patterns and relationships in data. Sigmoid produces values between 0 and 1, while ReLU outputs zero for negative inputs and keeps positive inputs unchanged.

   3. An activation function determines the output of a neuron based on its weighted inputs and bias. It helps neural networks recognize complex patterns and solve problems that cannot be solved using only linear calculations.

   4.

   • Input Layer: Receives the initial data or features and passes them to the next layer.

   • Hidden Layer: Processes the data using weights, biases, and activation functions to identify patterns and relationships.

   • Output Layer: Produces the final result or prediction, such as a classification or numerical value.

   In conclusion, the input layer receives information, the hidden layer processes it, and the output layer generates the final prediction.