Supervised Learning - Classification Week 9 Challenge
Q1) A neural network is a computational model inspired by the human brain. It consists of layers of interconnected nodes (neurons) that process data. During training, the network adjusts connections (weights) to learn patterns and make predictions or classifications. It's widely used in tasks like image recognition, language processing, and more.
Q2) Deep learning is a subset of machine learning that uses neural networks with many layers (deep networks) to automatically learn and extract complex patterns from large amounts of data. It excels in tasks like image and speech recognition, where traditional methods might struggle.
Q3) The activation function in a neural network introduces non-linearity into the model, allowing it to learn and represent complex patterns. It determines whether a neuron should be activated or not based on its input, helping the network to make more accurate predictions.
Q4)
1. **Sigmoid**: Maps input values to a range between 0 and 1, often used in binary classification.
2. **ReLU (Rectified Linear Unit)**: Outputs the input directly if positive, otherwise zero, commonly used in hidden layers for its simplicity and effectiveness.
3. **Tanh**: Maps input values to a range between -1 and 1, centering the data, which can help with convergence.
4. **Leaky ReLU**: Similar to ReLU but allows a small, non-zero gradient when the input is negative, addressing the "dying ReLU" problem.
5. **Softmax**: Converts a vector of values into probabilities that sum to 1, commonly used in the output layer for multi-class classification problems.
Q5) Backpropagation is a training algorithm for neural networks that involves:
1. **Forward Pass**: Passing input data through the network to obtain predictions.
2. **Loss Calculation**: Measuring the error between predictions and actual outcomes.
3. **Backward Pass**: Calculating the gradient of the loss function with respect to each weight by applying the chain rule, and updating the weights to minimize the error.