MP4 | Video: h264, 1920x1080 | Audio: AAC, 44.1 KHz, 2 Ch

May 28, 2020 | ISBN: 9781789953947 | English

Duration: Lessons (1h 25m) | Size: 303.3 MB

Hands-on implementation with the power of TensorFlow 2.0

Learn

Build your own image classification application using Convolutional Neural Networks and TensorFlow 2.0

Improve any image classification system by leveraging the power of transfer learning on Convolutional Neural Networks, in only a few lines of code

Discover how users feel about IMDB movies by building a Sentiment Analysis system utilizing the power of Recurrent Neural Networks and the TensorFlow 2.0 high-level API

Learn how to perform transfer learning on Recurrent Neural Networks and powerfully improve any text-based system

Learn how to use TensorFlow Hub to make transfer learning much easier

About

Transfer learning involves using a pre-trained model on a new problem. It is currently very popular in the field of Deep Learning because it enables you to train Deep Neural Networks with comparatively little data. In Transfer learning, knowledge of an already trained Machine Learning model is applied to a different but related problem.

The general idea is to use knowledge, which a model has learned from a task where a lot of labeled training data is available, in a new task where we don't have a lot of data. Instead of starting the learning process from scratch, you start from patterns that have been learned by solving a related task.

In this course, learn how to implement transfer learning to solve a different set of machine learning problems by reusing pre-trained models to train other models. Hands-on examples with transfer learning will get you started, and allow you to master how and why it is extensively used in different reinforcement learning domains.

You will implement practical use cases of transfer learning in CNN and RNN such as using image classifiers, text classification, text clustering, sentimental analysis, collaborative filtering, and much more. You'll be shown how to train models and how a pre-trained model is used to train similar untrained models in order to apply the transfer learning process even further. Allowing you to implement advanced use cases and learn how transfer learning is gaining momentum when it comes to solving real-world problems in deep learning.

By the end of this course, you will not only able to build machine learning models, but have mastered transferring what you've learned from one domain to another.

The code bundle for this course is available at

Features

Refresh your knowledge of CNN with in-depth explanations of how transfer learning works

Use transfer learning for both image and text classification, as opposed to the training from scratch approach

Learn new features of TensorFlow, tf.keras, and TensorFlow Hub