PyTorch is gaining popularity specially among students since it’s much more developer friendly. PyTorch helps to focus more on core concepts of deep learning unlike TensorFlow which is more focused on running optimized model on production system. In this tutorial we will Implement Neural Network using PyTorch and understand some of the core concepts of PyTorch.

## Implement Neural Network using TensorFlow

In the previous article we have implemented the Neural Network using Python from scratch. However for real implementation we mostly use a framework, which generally provides faster computation and better support for best practices. In this article we will Implement Neural Network using TensorFlow. At present, TensorFlow probably is the most popular deep learning framework available.

## Understand and Implement the Backpropagation Algorithm From Scratch In Python

It’s very important have clear understanding on how to implement a simple Neural Network from scratch. In this Understand and Implement the Backpropagation Algorithm From Scratch In Python tutorial we go through step by step process of understanding and implementing a Neural Network. We will start from Linear Regression and use the same concept to build a 2-Layer Neural Network.Then we will code a N-Layer Neural Network using python from scratch.As prerequisite, you need to have basic understanding of Linear/Logistic Regression with Gradient Descent.

Let’s see how we can slowly move towards building our first neural network.

## Implement Viterbi Algorithm in Hidden Markov Model using Python and R

The 3rd and final problem in Hidden Markov Model is the **Decoding Problem**. In this article we will implement Viterbi Algorithm in Hidden Markov Model using Python and R. Viterbi Algorithm is dynamic programming and computationally very efficient. We will start with the formal definition of the Decoding Problem, then go through the solution and finally implement it. This is the 4th part of the Introduction to Hidden Markov Model tutorial series. This one might be the easier one to follow along.

## Derivation and implementation of Baum Welch Algorithm for Hidden Markov Model

The most important and complex part of Hidden Markov Model is the `Learning Problem`

. Even though it can be used as Unsupervised way, the more common approach is to use Supervised learning just for defining number of hidden states. In this Derivation and implementation of Baum Welch Algorithm for Hidden Markov Model article we will go through step by step derivation process of the `Baum Welch Algorithm`

(a.k.a `Forward-Backward`

Algorithm) and then implement is using both Python and R.

- 1
- 2
- 3
- …
- 11
- Next Page »