In this project, I will use TensorFlow to create a Recurrent Neural Network (RNN), to predict the next character in a string. Training the network is performed using CPUs and GPUs.

This code implements a Recurrent Neural Network with LSTM units for training/sampling from character-level language models. In other words, the model takes a text file as input and trains the RNN network that learns to predict the next character in a sequence.

The RNN can then be used to generate text character by character that will look like the original training data. This code is based on this blog, and the code is an step-by-step implementation of the character-level implimentation. Dataset can be downloaded from the following link.

The details about the project can be found on Deep learning course.

The project has been completed using LSTM method. A brief and concise report as been compiled and can be accessed on my github rpository.

Report https://github.com/AmitVSingh/Deep-learning-RNN/blob/master/report.pdf

A html version can also be downloaded from this repository.

The code has been written in Python using Jupyter notebook. This complex problem has been broken down into small manageable tasks. Then by creating a new python class all the small code snippets are put together.

Python Code https://github.com/AmitVSingh/Deep-learning-RNN/blob/master/Project-LSTM-CharacterModelling.ipynb

Skills developed through this deep learning course

• Fundamental concepts of Deep Learning, including various Neural Networks for supervised and unsupervised learning.
• Use of popular Deep Learning librarary Tensorflow applied to industry problems.
• Build, train, and deploy different types of Deep Architectures, including Convolutional Networks, Recurrent Networks, and Autoencoders.
• Application of Deep Learning to real-world scenarios such as object recognition and Computer Vision, image and video processing, text analytics, Natural Language Processing, recommender systems, and other types of classifiers.
• Master Deep Learning at scale with accelerated hardware and GPUs.

Certificate:
Tensorflow: See certificate