Supervised Learning - Classification Week 9 Challenge

1. What is a Neural Network?

ans: A Neural Network is a network or circuit of artificial neurons which works together to understand or solve multiple situations by mimicing the functions of an actaul brain.it takes input and, in conjunction with information from other nodes, develop output without programmed rules. Essentially, they solve problems through trial and error.

2. What is deep learning?

ans: Deep learning, also known as deep neural networks or neural learning, is a form of artificial intelligence (AI) that seeks to replicate the workings of a human brain. it teaches computers to do what humans do best, learn by trail and error.

3. What is the role of the activation function?

ans: Activation function decides, whether a neuron should be activated or not by calculating weighted sum and further adding bias with it. The purpose of the activation function is to introduce non-linearity into the output of a neuron. it makes back-propagation possible since the gradients are supplied along with the error to update the weights and biases.

4. What are the different types of activation functions?

ans: the diffferent types of Activation Functions are:

• Sigmoid Function.
• Hyperbolic Tangent Function.
• Rectified Linear Unit Function (ReLU).
• Softmax Function.
• Exponential linear units Function(ELUs).
• Softsign Function.

5. What do you understand by backpropagation?

ans: Backpropagation (backward propagation) is an important mathematical tool for improving the accuracy of predictions in data mining and machine learning. When training a neural network by gradient descent, a Loss function is calculated, which represents how far the network's predictions are from the true labels. Backpropagation allows us to calculate the gradient of the loss function with respect to each of the weights of the network. This enables every weight to be updated individually to gradually reduce the loss function over many training iterations. Backpropagation involves the calculation of the gradient proceeding backwards through the feedforward network from the last layer through to the first. To calculate the gradient at a particular layer, the gradients of all following layers are combined via the chain rule of calculus.