Neural Networks:

• Definition: Computational models inspired by the human brain, composed of layers of interconnected nodes (neurons) that process data.
• Purpose: Used for various tasks including classification, regression, and pattern recognition.

Basic Components:

• Neuron: The fundamental unit that receives input, processes it and passes it to the next layer.
• Layers:
  • Input Layer: The first layer that receives input data.
  • Hidden Layers: Intermediate layers that transform input into meaningful patterns.
  • Output Layer: The final layer that produces the output.

Activation Functions:

• Functions applied to neurons’ outputs to introduce non-linearity, enabling the network to learn complex patterns.
• Common activation functions: Sigmoid, Tanh, ReLU (Rectified Linear Unit).

1. Artificial Neural Networks (ANNs)

2. Convolutional Neural Networks (CNNs)

3. Recurrent Neural Networks (RNNs)

4. Long Short-Term Memory Networks (LSTMs)

5. Gated Recurrent Units (GRUs)

Summary

• Neural Networks (NNs): A basic framework for building models that can learn from data.
• Artificial Neural Networks (ANNs): Basic NNs with fully connected layers, suitable for general tasks.
• Convolutional Neural Networks (CNNs): Specialized for spatial data, especially images, using convolutional layers to detect patterns.
• Recurrent Neural Networks (RNNs): Specialized for sequential data, maintaining context across steps.
• LSTMs and GRUs: Advanced RNNs designed to handle long-term dependencies more effectively than standard RNNs.