A basic neural network using tensorflow and without to implement a feedforward neural network in python Run convolutional.py to run it without tensorflow and simple convulutional net.ipynb to run it with tensorflow.
Feedforward
Deep feedforward networks, also often called feedforward neural networks, or multilayer perceptrons(MLPs), are the quintessential deep learning models. The goal of a feedforward network is to approximate some function f*. For example, for a classifier, y = f*(x) maps an input x to a category y. A feedforward network defines a mapping y = f(x;θ) and learns the value of the parameters θ that result in the best function approximation.
References:
Deep Learning Book” by Goodfellow, Bengio, and Courville.