Optimize Neural nets

This post is quite smaller than previous ones as it just states the optimization techniques required to train a neural network. I thought of including a example but many resources are available free online and therefore it is not necessary to reinvent the wheel. So coming straight to the point, Optimization techniques are those which facilitate our model to converge faster and providing much more efficiency and makes our model more accurate. Continue reading

Code a Neural Network

Though the underlying concepts that are required to build and train a neural network are difficult, It is very easy to implement it in code. So in this post, let’s

  • Code a neural network by hand
  • Use keras to build a neural network

Firstly let’s see how can we build our own neural network with just raw python code. For this let’s assume our task is to build a model that just XOR the input. It might seem very easy but believe me, it is the first difficult step in training any neural network as the XOR itself is not linear i.e it is non-linear. Continue reading

Multi Layer Perceptron

I know, you think that Multi Layer Perceptron seems to be very similar to the Perceptron. And yeah, it is but wait ! It’s not completely only that but lots of things are to be going under hood. To be frank, it is some what difficult to understand the underlying concepts in the Neural Networks at the beginning. But learning how they work really saves you from lots of bottleneck problems you may face later. Continue reading

Perceptron

Perceptron is the most basic and primary implementation of a biological neuron in machine intelligence. Moreover the concept of perceptron can be leveraged to build more complex neural networks which we will see later. These are used mainly for supervised learning and can be modified to work with unsupervised learning also. The implementation of perceptron is inspired from the actual neuron which can be seen below.

Biological Neuron

Biological Neuron

Continue reading