This project is about building a artificial neural network using pytorch library. I am sharing the code and output for my project. Though there are many libraries out there that can be used for deep learning i like the pytorch most. As a python programmer, one of the reasons behind my liking is pythonic behaviour of pytorch. It mostly uses the style and power of python which is easy to understand and use. What is Neural Network? Neural networks are a set of algorithms, modeled loosely after the human brain, that are designed to recognize patterns. The networks are built from individual parts approximating neurons, typically called units or simply “neurons.” Each unit has some number of weighted inputs. These weighted inputs are summed together (a linear combination) then passed through an activation function to get the unit’s output. Types of nodes in a neural network:
- Input units — provides information from the outside world to the network and are together referred to as the “input layer”. These nodes do not perform any computation, they just pass on the information to the hidden nodes.
- Hidden units — these nodes do not have any direct connection with the outside world. They perform computations and transfer information from input nodes to output nodes. A collection of hidden nodes forms a “hidden layer”. While a feed-forward network will only have a single input layer and a single output layer, it can have zero or multiple hidden layers.
- Output units — the output nodes are collectively referred to as the “output layer” and are responsible for computations and transferring information from the network to the outside world.