Supervised Learning - Classification Week 9 Challenge

Ques1.

A Neural Network is a computational model inspired by the human brain. It's made up of layers of interconnected nodes (neurons), where each neuron performs a simple computation. These networks learn patterns from data and are the foundation of many machine learning and deep learning systems.

Ques2.

Deep Learning is a subset of machine learning that uses neural networks with many hidden layers (hence deep). It’s particularly good at handling unstructured data like images, audio, and text.

Ques3.

An activation function introduces non-linearity into the neural network. Without activation functions, neural networks would just behave like linear regressions, no matter how many layers you add — they wouldn’t be able to capture complex patterns.

Ques4.

Sigmoid

Tanh

ReLU

Leaky ReLU

Softmax

Swish

GELU

Ques5.

Backpropagation is the algorithm used to train neural networks.

How it works:

Forward Pass: Calculate predicted output

Loss Calculation: Compare prediction to actual (using a loss function)

Backward Pass: Use chain rule to compute gradients of loss with respect to weights

Update Weights: Use optimization algorithm (like Gradient Descent)