Description

In this self-paced course, you will learn how to use TensorFlow 2 to build recurrent neural networks (RNNs). You will learn about sequence data, forecasting, Elman Unit, GRU, and LSTM. You will also learn how to work with image classification and how to get stock return predictions using LSTMs. We will also cover Natural Language Processing (NLP) and learn about text preprocessing and classification.

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.

Approach

In this self-paced course, you will learn how to use TensorFlow 2 to build recurrent neural networks. The course is well-balanced with theory that explains the RNN concepts and hands-on coding exercises for practical understanding. The course includes video presentations, coding lessons, hands-on exercises, and links to further resources.

Key Features

Build your own RNNs with TensorFlow 2 * Explains RNNs, time series, and sequence data * Preform text preprocessing and text classification with LSTMs

About the Author

Lazy Programmer

The Lazy Programmer, a distinguished online educator, boasts dual master's degrees in computer engineering and statistics, with a decade-long specialization in machine learning, pattern recognition, and deep learning, where he authored pioneering courses. His professional journey includes enhancing online advertising and digital media, notably increasing click-through rates and revenue. As a versatile full-stack software engineer, he excels in Python, Ruby on Rails, C++, and more. His expansive knowledge covers areas like bioinformatics and algorithmic trading, showcasing his diverse skill set. Dedicated to simplifying complex topics, he stands as a pivotal figure in online education, adeptly navigating students through the nuances of data science and AI.

Course Outline

1. Welcome

1. Introduction

In this video, we will get introduced to recurrent neural networks and understand the course learning objective.

2. Outline

In this video, we will understand the course learning approach and what is required to start with this course. Then we will also understand what is covered in this course.

2. Recurrent Neural Networks (RNNs), Time Series, and Sequence Data

1. Sequence Data

In this video, you will learn about sequence data.

2. Forecasting

In this video, we will discuss about forecasting.

3. Autoregressive Linear Model for Time Series Prediction

In this video, we will dive into coding and learn about the autoregressive linear model for time series prediction.

4. Proof That the Linear Model Works

In this video, you will learn how the linear model is about to forecast for a sine wave.

5. Recurrent Neural Networks (Elman Unit Part 1)

In this video, we will get introduced to simple recurrent neural networks also called as Elman Unit.

6. Recurrent Neural Networks (Elman Unit Part 2)

In this video, you will learn how to use the simple RNN to solve many-to-one tasks and many-to-many problems.

7. RNN Code Preparation

In this video, we will understand how to write code in TensorFlow 2 for a simple RNN.

8. RNN for Time Series Prediction

In this video, we will do the same forecasting exercise that we did with an autoregressive liner model, but with a simple RNN instead.

9. Paying Attention to Shapes

In this video, we will work on shapes in RNN.

10. GRU and LSTM (Part 1)

In this video, you will learn about modern RNN units called GRU.

11. GRU and LSTM (Part 2)

In this video, you will learn about modern RNN units called LSTM.

12. A More Challenging Sequence

In this video, you will learn how to preform time series prediction with a complex signal.

13. Demo of the Long-Distance Problem

In this video, we will understand how LSTMs work for resolving a long-distance problem.

14. RNN for Image Classification (Theory)

In this video, we will understand how to apply RNN for image classification.

15. RNN for Image Classification (Code)

In this video, you will learn how to preform RNN for image classification on the MNIST dataset.

16. Stock Return Predictions Using LSTMs (Part 1)

In this video, we will understand why one-step prediction on stock price is misleading and unconventional.

17. Stock Return Predictions Using LSTMs (Part 2)

In this video, we will work on a more conventional prediction called stock return.

18. Stock Return Predictions Using LSTMs (Part 3)

In this video, we will make use of all the data and try to predict whether the price will go up or down.

19. Other Ways to Forecast

In this video, we will discuss some other ways that might generate multi-step forecast.

20. Suggestion Box

In this video, the author shares how you can get in touch with him through the suggestion box.

3. Natural Language Processing (NLP)

1. Embeddings

In this video, we will understand what embedding is.

2. Code Preparation (NLP)

In this video, you will learn how to write the code to turn a sequence of words into an acceptable format such that they can be converted into a matrix of numbers.

3. Text Preprocessing

In this video, we will work on text preprocessing.

4. Text Classification with LSTMs

In this video, we will work on text classification with LSTMs.

Course Images

Deep Learning - Recurrent Neural Networks with TensorFlow

By Packt

Booking options

Highlights

Description

What You Will Learn

Audience

Approach

Key Features

About the Author

Lazy Programmer

Course Outline

1. Welcome

2. Recurrent Neural Networks (RNNs), Time Series, and Sequence Data

3. Natural Language Processing (NLP)

Course Content

About The Provider

Tags

Reviews