This document provides an overview of soft computing techniques and neural networks. It introduces artificial neural networks and their basic components, including neurons, weights, biases, and activation functions. Common neural network architectures like single layer perceptrons, multi-layer feedforward networks, and recurrent networks are described. Learning algorithms for training neural networks, including backpropagation for multi-layer networks, are summarized. Examples are provided to illustrate how perceptrons and multi-layer networks can learn non-linear functions like XOR.