Book Image

Deep Learning with TensorFlow 2.0 in 7 Steps [Video]

By : Robert Thas John
Book Image

Deep Learning with TensorFlow 2.0 in 7 Steps [Video]

By: Robert Thas John

Overview of this book

Image classification and language modelling are two fields of computing that are difficult for computers to tackle without implementing deep neural networks. How do you recognize the difference or similarity between two fruits or two words? This is required for various applications, ranging from e-commerce sites to educational software. While these tasks are non-trivial, TensorFlow provides a gentle introduction to solving them. In this course, you will learn how to get started with TensorFlow 2.0 in a unique and enticing way, using an ambitious approach that's perfect for learning and implementing deep learning models. You will learn how to start building and training your own models to classify images and also differentiate between different text. Using TensorFlow at a high level, you will learn to implement Convolutional Neural Networks (CNN), as well as sequence networks such as Long Short-Term Memory (LSTM) and Recurrent Neural Networks (RNN). By the end of this course, you will be confident about building and implementing deep learning models effectively and easily with TensorFlow 2.0, collecting image data, splitting it into training, validation and test sets, and training a model to classify images. All the code and supporting files for this course are available on GitHub at https://github.com/PacktPublishing/Deep-Learning-with-TensorFlow-2.0-in-7-Steps
Table of Contents (7 chapters)
Chapter 2
Why Deep Learning?
Content Locked
Section 1
Limit of Classification with Logistic Regression
Logistic regression relies on finding a threshold or separating hyperplane in data. Some problems require identifying so many features, simple logistic regression is unable to find such a plane. We explore that limitation by applying logistic regression to images.