Deep Learning - Recurrent Neural Networks with TensorFlow

Recurrent Neural Networks are a type of deep learning architecture designed to process sequential data, such as time series, text, speech, and video. RNNs have a memory mechanism, which allows them to preserve information from past inputs and use it to inform their predictions.

TensorFlow 2 is a popular open-source software library for machine learning and deep learning. It provides a high-level API for building and training machine learning models, including RNNs.

In this compact course, you will learn how to use TensorFlow 2 to build RNNs. We will study the Simple RNN (Elman unit), the GRU, and the LSTM, followed by investigating the capabilities of the different RNN units in terms of their ability to detect nonlinear relationships and long-term dependencies. We will apply RNNs to both time series forecasting and NLP. Next, we will apply LSTMs to stock “price” predictions, but in a different way compared to most other resources. It will mostly be an investigation about what not to do and how not to make the same mistakes that most blogs and courses make when predicting stocks.

By the end of this course, you will be able to build your own build RNNs with TensorFlow 2.

What You Will Learn

• Learn about simple RNNs (Elman unit)
• Covers GRU (gated recurrent unit)
• Learn how to use LSTM (long short-term memory unit)
• Learn how to preform time series forecasting
• Learn how to predict stock price and stock return with LSTM
• Learn how to apply RNNs to NLP

Audience

This course is designed for anyone interested in deep learning and machine learning or for anyone who wants to implement recurrent neural networks in TensorFlow 2. One must have decent Python programming skills, should know how to build a feedforward ANN in TensorFlow 2, and must have experience with data science libraries such as NumPy and Matplotlib.

About The Author

Lazy Programmer: The Lazy Programmer is an AI and machine learning engineer with a focus on deep learning, who also has experience in data science, big data engineering, and full-stack software engineering. With a background in computer engineering and specialization in machine learning, he holds two master’s degrees in computer engineering and statistics with applications to financial engineering. His expertise in online advertising and digital media includes work as both a data scientist and big data engineer.

He has created deep learning models for prediction and has experience in recommendation systems using reinforcement learning and collaborative filtering. He is a skilled instructor who has taught at universities including Columbia, NYU, Hunter College, and The New School. He has web programming expertise, with experience in technologies such as Python, Ruby/Rails, PHP, and Angular, and has provided his services to multiple businesses.