Deep Learning: Recurrent Neural Networks with Python

Description

This course starts with the basics of Recurrent Neural Networks (RNNs) with Python and then teaches you how to build them by taking you through various exercises and projects. You will be able to test your skills by completing two exciting projects: creating an automatic book writer and a stock price prediction application.

With the exponential growth of user-generated data, there is a strong need to move beyond standard neural networks in order to perform tasks such as classification and prediction. Here, architectures such as RNNs, Gated Recurrent Units (GRUs), and Long Short Term Memory (LSTM) are the go-to options. Hence, for any deep learning engineer, mastering RNNs is a top priority. This course begins with the basics and will gradually equip you with not only the theoretical know-how but also the practical skills required to successfully build, train, and implement RNNs. This course contains several exercises on topics such as gradient descents in RNNs, GRUs, LSTM, and so on. This course also introduces you to implementing RNNs using TensorFlow. The course culminates in two exciting and realistic projects: creating an automatic book writer and a stock price prediction application. By the end of this course, you will be equipped with all the skills required to confidently use and implement RNNs in your applications. The code bundle for this course is available at https://github.com/AISCIENCES/mastering_recurrent_neural_networks

Gain an overview of deep neural networks
Understand the fundamentals of RNN architectures
Train real-world datasets using different RNN architectures
Implement RNNs, LSTM, and GRUs through hands-on exercises
Create and compile RNN models in TensorFlow
Perform text classification using RNNs and TensorFlow

As this course begins with the basics, no prior knowledge in RNNs is required. However, prior experience in Python would be beneficial. Whether you are a beginner, a seasoned data scientist looking to get started with RNNs, business analysts, or if you simply want to implement RNNs in your projects, this course is for you.

Through carefully designed modules, a simple-to-understand theory, engaging hands-on exercises, and realistic implementations of RNNs in projects, this course will help you master RNNs.

Understand and apply fundamentals of recurrent neural networks * Implement RNNs and related architectures on real-world datasets * Train RNNs for real-world applications-automatic book writer and stock price prediction

https://github.com/AISCIENCES/mastering_recurrent_neural_networks

AI Sciences are experts, PhDs, and artificial intelligence practitioners, including computer science, machine learning, and Statistics. Some work in big companies such as Amazon, Google, Facebook, Microsoft, KPMG, BCG, and IBM. AI sciences produce a series of courses dedicated to beginners and newcomers on techniques and methods of machine learning, statistics, artificial intelligence, and data science. They aim to help those who wish to understand techniques more easily and start with less theory and less extended reading. Today, they publish more comprehensive courses on specific topics for wider audiences. Their courses have successfully helped more than 100,000 students master AI and data science.

1. Introduction

2. Applications of RNN

3. Deep Neural Network (DNN) Overview

4. RNN Architecture

5. Gradient Descent in RNN

6. RNN Implementation

7. Sentiment Classification Using RNN

8. Vanishing Gradients in RNN

9. TensorFlow

10. Project 1: Book Writer

11. Project 2: Stock Price Prediction

12. Further Reading and Resources