TensorFlow in Practice

If you are a software developer who wants to build scalable AI-powered algorithms, you need to understand how to use the tools to build them. This Specialization will teach you best practices for using TensorFlow, a popular open-source framework for machine learning. In these courses you will:

Learn how to build machine learning models in TensorFlow
Build image recognition algorithms with deep neural networks and convolutional neural networks
Understand how to deploy your models on mobile and the web
Go beyond image recognition into object detection, text recognition, and more
Expand the basic APIs for custom learning/training

The Machine Learning course and Deep Learning Specialization teach the most important and foundational principles of Machine Learning and Deep Learning. This new deeplearning.ai TensorFlow Specialization teaches you how to use TensorFlow to implement those principles so that you can start building and applying scalable models to real-world problems. To develop a deeper understanding of how neural networks work, we recommend that you take the Deep Learning Specialization.

Course 1

Introduction to TensorFlow for AI, ML and DL

Course 2

Convolutional Neural Networks in TensorFlow

Course 3

Natural Language Processing in TensorFlow

Course 4

Sequences, Time Series, and Prediction

Enroll in the deeplearning.ai TensorFlow Specialization

Course 1: Introduction to TensorFlow for AI, ML and DL

This first course introduces you to TensorFlow, a popular machine learning framework. You will learn how to build a basic neural network for computer vision and use convolutions to improve your neural network.

Week 1: A New Programming Paradigm

Introduction: A conversation with Andrew Ng
A primer in machine learning

The “Hello World” of neural networks
Working through “Hello World” in TensorFlow and Python

Week 2: Introduction to Computer Vision

A conversation with Andrew Ng
An introduction to computer vision
Writing code to load training data
Coding a computer vision neural network

Walk through a notebook for computer vision
Using callbacks to control training
Walk through a notebook with callbacks

Week 3: Enhancing Vision with Convolutional Neural Networks

A conversation with Andrew Ng
What are convolutions and pooling?
Implementing convolutional layers

Implementing pooling layers
Improving the fashion classifier with convolutions
Walking through convolutions

Week 4: Using Real-World Images

A conversation with Andrew Ng
Understanding ImageGenerator
Defining a ConvNet to use complex images
Training the ConvNet with fit_generator
Walking through developing a ConvNet

Walking through training the ConvNet with fit_generator
Adding automatic validation to test accuracy
Exploring the impact of compressing images
Outro: Conversation with Andrew

Enroll in Course 1 of the deeplearning.ai TensorFlow Specialization

Course 2: Convolutional Neural Networks in TensorFlow

This second course teaches you advanced techniques to improve the computer vision model you built in Course 1. You will explore how to work with real-world images in different shapes and sizes, visualize the journey of an image through convolutions to understand how a computer “sees” information, plot loss and accuracy, and explore strategies to prevent overfitting, including augmentation and dropouts. Finally, Course 2 will introduce you to transfer learning and how learned features can be extracted from models.

Week 1: Exploring a Larger Dataset

Introduction: A conversation with Andrew Ng
Training with the cats vs. dogs dataset
Working through the notebook

Fixing through cropping
Looking at accuracy and loss

Week 2: Augmentation, a Technique to Avoid Overfitting

A conversation with Andrew Ng
Introducing augmentation
Coding augmentation with ImageDataGenerator

Demonstrating overfitting in cats vs. dogs dataset
Adding augmentation to cats vs. dogs dataset
Exploring augmentation with horses vs. humans dataset

Week 3: Transfer Learning

A conversation with Andrew Ng
Understanding transfer learning: the concepts
Coding your own model with transferred features

Exploring dropouts
Exploring transfer learning with inception

Week 4: Multi-class Classifications

A conversation with Andrew Ng
Moving from binary to multi-class classification
Exploring multi-class classification with the rock paper scissors dataset

Training a classifier with the rock paper scissors dataset
Testing the rock paper scissors classifier

Enroll in Course 2 of the deeplearning.ai TensorFlow Specialization

Course 3: Natural Language Processing in TensorFlow

In this third course, you’ll learn how to apply neural networks to solve natural language processing problems using TensorFlow. You’ll learn how to process and represent text through tokenization so that it’s recognizable by a neural network. You’ll be introduced to new types of neural networks, including RNNs, GRUs and LSTMs, and how you can train them to understand the meaning of text. Finally, you’ll learn how to train LSTMs on existing text to create original poetry and more!

Week 1: Sentiment in Text

Introduction: A conversation with Andrew Ng
Word-based encodings
Using APIs

Text to sequence
Sarcasm, really?
Working with the Tokenizer

Week 2: Word Embeddings

A conversation with Andrew Ng
The IMDB dataset
Looking into the details
How can we use vectors?
More into the details

Remember the sarcasm dataset?
Building a classifier for the sarcasm dataset
Let’s talk about the loss function
Pre-tokenized datasets
Diving into the code

Week 3: Sequence Models

A conversation with Andrew Ng
LSTMs
Implementing LSTMs in code
A word from Laurence

Accuracy and Loss
Using a convolutional network
Going back to the IMDB dataset
Tips from Laurence

Week 4: Sequence Models and Literature

A conversation with Andrew Ng
Training the data
Finding what the next word should be

Predicting a word
Poetry!
Laurence the poet

Enroll in Course 3 of the deeplearning.ai TensorFlow Specialization

Course 4: Sequences, Time Series, and Prediction

In this fourth course, you will learn how to solve time series and forecasting problems in TensorFlow. You’ll first implement best practices to prepare data for time series learning. You’ll also explore how RNNs and ConvNets can be used for predictions. Finally, you’ll apply everything you’ve learned throughout the Specialization to build a sunspot prediction model using real-world data!

Week 1: Sequences and Prediction

Introduction: a conversation with Andrew Ng
Time series examples
Machine learning applied to time series
Common patterns in time series
Introduction to time series

Train, validation, and test sets
Metrics for evaluating performance
Moving average and differencing
Trailing versus centered windows
Forecasting

Week 2: Deep Neural Networks for Time Series

A conversation with Andrew Ng
Preparing features and labels
Feeding a windowed dataset into a neural network
Single layer neural network

Machine learning on time windows
Prediction
More on single-layer network
Deep neural network training, tuning, and prediction

Week 3: Recurrent Neural Networks for Time Series

A conversation with Andrew Ng
Shape of the inputs to the RNN
Outputting a sequence
Lambda layers
Adjusting the learning rate dynamically

RNNs
LSTMs
Coding LSTMs
More on LSTMs

Week 4: Real-world Time Series Data

A conversation with Andrew Ng
Convolutions
Bi-directional LSTMs
Real data – sunspots

Train and tune the model
Prediction
Sunspots
Combining our tools for analysis

Enroll in Course 4 of the deeplearning.ai TensorFlow Specialization

Frequently Asked Questions

Who is the deeplearning.ai TensorFlow Specialization for?

The deeplearning.ai TensorFlow Specialization is for anyone who has basic experience coding in Python and wants to learn how to best use TensorFlow to start building AI applications.

What will I learn in the Specialization?

There are four courses in the Specialization. Each course builds on top of the skills you learned in the previous one.

Course 1: Build a basic neural network for computer vision within TensorFlow, as well as how to use convolutions to improve your neural network.
Course 2: Learn advanced techniques like augmentation, dropout, and transfer learning to improve your computer vision model.
Course 3: Apply neural networks to solve natural language processing problems using TensorFlow.
Course 4: Solve time series and forecasting problems in TensorFlow.

Are there any prerequisites?

You should be comfortable coding in Python and understand high school-level math. Prior machine learning or deep learning knowledge is helpful but not required.

How do I take the Specialization?

You can enroll in the Specialization on Coursera’s platform. You will watch videos and complete assignments on Coursera as well.

How long is the Specialization?

It typically takes 4 weeks, 4-5 hours per week to complete each course. There are four courses in the Specialization.

How much does the Specialization cost?

The Specialization costs $49/month. You can also purchase each course for $49.

How do I audit the Specialization?

You can audit the TensorFlow Specialization for free by going to the homepage of the course, clicking “Enroll,” and clicking “audit” at the bottom of the window. Note that you will not receive a certificate at the end of the course if you choose to audit.

Can I apply for financial aid?

Yes, Coursera provides financial aid to learners who cannot afford the fee. You can apply for it by going to the Coursera course page and clicking on the Financial Aid link beneath the “Enroll” button on the left.

Will I receive a certificate at the end of the Specialization?

You will receive a certificate at the end of each course if you pay for the courses and complete the programming assignments. There is a limit of 180 days of certificate eligibility, after which you would have to re-purchase the course. If you audit the course for free, you will not receive a certificate.

If you complete all four courses in the Specialization and are subscribed to the Specialization, you will also receive a certificate showing that you completed the entire Specialization.

Can I transition to paying for the full Specialization if I already paid for one of the courses?

Yes, if you paid a one-time $49 payment for one or more of the courses, you can still subscribe to the Specialization for $49/month. If you pay for one course, you will have access to it for 180 days, or until you complete the course. If you subscribe to the Specialization, you will have access to all four courses until you end your subscription.

Is this a stand-alone course or a Specialization?

This is a deeplearning.ai Specialization made up of four courses.

Enroll in the deeplearning.ai TensorFlow Specialization

About the Instructors

Laurence Moroney is a Developer Advocate at Google working on Artificial Intelligence with TensorFlow. As the author of more programming books than he can count, he’s excited to be working with deeplearning.ai and Coursera in producing video training.

When not working with technology, he’s a member of the Science Fiction Writers of America, having authored several science fiction novels, a produced screenplay and comic books, including the prequel to the movie ‘Equilibrium’ starring Christian Bale. Laurence is based in Washington State, where he drinks way too much coffee.

Andrew Ng is a global leader in AI and co-founder of Coursera. Dr. Ng is also the CEO and founder of deeplearning.ai and founder of Landing AI. He is an Adjunct Professor in the Computer Science Department at Stanford University.

He was until recently Chief Scientist at Baidu, where he was responsible for driving the company’s global AI strategy and infrastructure. He was also the founding lead of the Google Brain team. Dr. Ng has authored or co-authored over 100 research papers in machine learning, robotics and related fields. He holds degrees from Carnegie Mellon University, MIT and the University of California, Berkeley.