Deep Learning with TensorFlow 2

Name: Deep Learning with TensorFlow 2 Course
Price: 36 USD

with Iskren Vankov and Iliya Valchanov

4.8/5

(977)

Master deep learning in Python with TensorFlow 2: Apply neural networks to solve real-world data science challenges

5 hours of content 17606 students

Start for Free

What you get:

5 hours of content
122 Interactive exercises
44 Downloadable resources
World-class instructor
Closed captions
Q&A support
Future course updates
Course exam
Certificate of achievement

Deep Learning with TensorFlow 2

A course by Iskren Vankov and Iliya Valchanov

Start for Free

What you get:

5 hours of content
122 Interactive exercises
44 Downloadable resources
World-class instructor
Closed captions
Q&A support
Future course updates
Course exam
Certificate of achievement

Start for Free

What you get:

5 hours of content
122 Interactive exercises
44 Downloadable resources
World-class instructor
Closed captions
Q&A support
Future course updates
Course exam
Certificate of achievement

What You Learn

Master the math behind deep learning algorithms.
Build and customize machine learning algorithms from scratch.
Understand key deep learning concepts to optimize neural networks.
Prevent overfitting with early stopping and improve generalizability.
Solve complex real-world problems using TensorFlow 2.

Top Choice of Leading Companies Worldwide

Industry leaders and professionals globally rely on this top-rated course to enhance their skills.

Course Description

Machine and deep learning are some of those quantitative analysis skills that differentiate the data scientist from the other members of the team. Not to mention that the field of machine learning is the driving force of artificial intelligence. This course will teach you how to leverage deep learning and neural networks for the purposes of data science. The technology we employ is TensorFlow 2.0, which is the state-of-the-art deep learning framework.

Learn for Free

1.1 Why machine learning

7 min

2.1 Introduction to neural networks

4 min

2.3 Training the model theory

3 min

2.5 Types of machine learning

4 min

2.7 The linear model

3 min

2.9 The linear model. Multiple inputs.

2 min

Curriculum

1. Introduction

1 Lesson 7 Min

In this introductory part of the course, we will discuss why you will need machine learning when working as a data scientist, what you will see in the following chapters of this training, and what the best way to take the course is.

Why machine learning
7 min
2. Neural networks Intro

12 Lessons 42 Min

The basic logic behind training an algorithm involves four ingredients: data, model, objective function, and an optimization algorithm. In this part of the course, we describe each of them and build a solid foundation that allows you to understand the idea behind using neural networks. After completing this chapter, you will know what the various types of machine learning are, how to train a machine learning model, and understand terms like objective function, L2-norm loss, cross-entropy loss, one gradient descent, and n-parameter gradient descent.

Introduction to neural networks
4 min
Training the model theory
3 min
Types of machine learning
4 min
The linear model
3 min
The linear model. Multiple inputs.
2 min
The linear model. Multiple inputs and multiple outputs
4 min
Graphical representation
2 min
The objective function
1 min
L2-norm loss
2 min
Cross-entropy loss
4 min
One-parameter gradient descent
7 min
N-parameter gradient descent
6 min
3. Setting up the environment

7 Lessons 24 Min

Here, we will show you how to install the Jupyter Notebook (the environment we will use to code in Python) and how to import the relevant libraries. Because this course is based in Python, we will be working with several popular libraries: NumPy, SciPy, scikit-learn and TensorFlow.

Setting up the environment - Do not skip, please!
1 min
Why Python and why Jupyter
5 min
Installing Anaconda
3 min
Jupyter Dashboard - Part 1
3 min
Jupyter Dashboard - Part 2
6 min
Installing the TensorFlow package
5 min
Installing the packages Read now
1 min
4. Minimal example

5 Lessons 20 Min

It is time to build your first machine learning algorithm. We will show you how to import the relevant libraries, how to generate random input data for the model to train on, how to create the targets the model will aim at, and how to plot the training data. The mechanics of this model exemplify how all regressions you’ve run in different packages (scikit-learn) or software (Excel) work. This is an iterative method aiming to find the best-fitting line.

Outline
3 min
Generating the data (optional)
5 min
Initializing the variables
3 min
Training the model
8 min
Minimal Example - Exercises.txt Read now
1 min
5. Introduction to TensorFlow 2

8 Lessons 24 Min

Having created the simple net, we 'translate' it to TensorFlow. This is our way of taking a simple, well-understood problem to introduce the syntax and logic of TensorFlow.

TensorFlow Outline
3 min
TensorFlow 2 Intro
3 min
A note on coding in TensorFlow
1 min
Types of file formats in Tensorflow and data handling
3 min
Model layout - inputs, outputs, targets, weights, bias, optimizer, and loss
6 min
Interpreting the result and extracting the weights and bias
4 min
Customizing your model
3 min
Introduction to TensorFlow - Exercises Read now
1 min
6. Deep nets overview

8 Lessons 25 Min

From this section on, we will explore deep neural networks. Most real-life dependencies cannot be modelled with a simple linear combination (as we have done so far). And because we want to be better forecasters, we need better models. Most of the time, this means working with a model that is more sophisticated than a liner model. In this section, we will talk about concepts like deep nets, non-linearities, activation functions, softmax activation, and backpropagation. Sounds a bit complex, but we have made it easy for you!

The layer
2 min
What is a deep net
2 min
Really understand deep nets
5 min
Why do we need non-linearities
3 min
Activation functions
4 min
Softmax activation
3 min
Backpropagation
3 min
Backpropagation - intuition
3 min
7. Backpropagation (optional)

1 Lesson 1 Min

Тo get a truly deep understanding of deep neural networks, one will have to look at the mathematics of it. As backpropagation is at the core of the optimization process, we wanted to introduce you to it. This is not a necessary part of the course, as in TensorFlow, sklearn, or any other machine learning package (as opposed to simply NumPy), will have backpropagation methods incorporated.

Backpropagation mathematics Read now
1 min
8. Overfitting

6 Lessons 20 Min

Some of the most common pitfalls you can have when creating predictive models, and especially in deep learning, is to either underfit or overfit your data. This means to either take less advantage of the machine learning algorithm than you could have due to insufficient training (underfitting), or alternatively create a model that fits the training data too much (overtrain the model) which makes it unsuitable for a different sample (overfitting).

Underfitting and overfitting. A regression example
4 min
Underfitting and overfitting. A classification example
2 min
Train vs validation
3 min
Train vs validation vs test
3 min
N-fold cross validation
3 min
Early stopping - motivation and types
5 min
9. Initialization

3 Lessons 9 Min

Initialization is the process in which we set the initial values of weights, and it's an important aspect of building a machine learning model. In this section, you will learn how to initialize the weights of your model and how to apply Xavier initialization.

Initialization
3 min
Types of simple initializations
3 min
Xavier's initialization
3 min
10. Optimizers

7 Lessons 21 Min

The gradient descent iterates the whole training set before updating the weights. Every iteration updates the weights in a relatively small way. Here, you will learn common pitfalls related to this method and how to boost them, using stochastic gradient descent, momentum, learning rate schedules, and adaptive learning rates.

SGD&Batching
3 min
Local minima pitfalls
2 min
Momentum
3 min
Learning rate schedules
4 min
Learning rate schedules. A picture
2 min
Adaptive learning schedules
4 min
Adaptive moment estimation
3 min
11. Preprocessing

5 Lessons 15 Min

A large part of the effort data scientists make when creating a new model is related to preprocessing. This process refers to any manipulation we apply to the dataset before running it and training the model. Learning how to preprocess data is fundamental for anyone who wants to be able to create machine learning models, as no meaningful framework can simply take raw data and provide an answer. In this part of the course, we will show you how to prepare your data for analysis and modeling.

Preprocessing
3 min
Basic preprocessing
1 min
Standardization
5 min
Dealing with categorical data
2 min
One hot vs binary
4 min
12. Deeper example

12 Lessons 40 Min

Once we have learned all the relevant theory, we are ready to jump into deep waters. We explore the 'Hello world' of deep learning - the MNIST dataset, where we classify 60,000 images into 10 classes (the 10 digits: 0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10).

MNIST dataset
2 min
How to tackle the MNIST dataset
3 min
MNIST - Importing libraries and data
2 min
Preprocess the data - create a validation dataset and scale the data
5 min
Preprocess the data - scale the test data Read now
1 min
Preprocess the data - shuffle and batch
7 min
Preprocess the data - shuffle and batch Exercise Read now
1 min
Outline the model
5 min
Select the loss and the optimizer
2 min
Learning
6 min
MNIST - Exercises Read now
2 min
Testing the model
4 min
13. Business case

12 Lessons 43 Min

Data science without an application is nothing but research. Since we at 365 believe that the skills you acquire should be relevant for your work, we finish the course with a business case, where we implement all the deep learning knowledge you've acquired.

Exploring the dataset and identifying predictors
8 min
Outlining the business case solution
2 min
Balancing a dataset
4 min
Preprocessing the data
12 min
Preprocessing Exercise Read now
1 min
Load the preprocessed data
3 min
Load the preprocessed data Exercise Read now
1 min
Learning and interpreting the result
4 min
Setting an early stopping mechanism
5 min
Setting an early stopping mechanism Exercise Read now
1 min
Testing the business model
1 min
Homework Read now
1 min
14. Conclusion

6 Lessons 19 Min

This section is designed to help you continue your specialization and data science journey. In this section, we discuss what is further out there in the machine learning world, how Google’s DeepMind uses machine learning, what are RNNs, and what non-NN approaches are there.

Summary
4 min
What's more out there
2 min
An overview of CNNs
5 min
How DeepMind uses deep learning Read now
1 min
An overview of RNNs
3 min
Non-NN approaches
4 min

Topics

PythonTheoryMachine LearningProgrammingMathematicsDeep LearningTensorflowNeural NetworksMachine and Deep Learning

Tools & Technologies

Course Requirements

You need to complete an introduction to Python before taking this course
Basic skills in statistics, probability, and linear algebra are required
It is highly recommended to take the Machine Learning in Python course first
You will need to install the Anaconda package, which includes Jupyter Notebook

Who Should Take This Course?

Level of difficulty: Advanced

Aspiring data scientists, ML engineers, and AI developers
Existing data scientists, ML engineers, and AI developers who want to improve their technical skills

Exams and Certification

A 365 Data Science Course Certificate is an excellent addition to your LinkedIn profile—demonstrating your expertise and willingness to go the extra mile to accomplish your goals.

Meet Your Instructor

Iskren Vankov

Winner of Award

3 Courses

1504 Reviews

26711 Students

A top-of-class graduate from Edinburgh, Caltech, and Oxford, Iskren is a true academic force with over 8 years of industry experience, from Junior Developer to Head of Research and Development. He holds numerous prestigious awards, including the Microsoft Research Award for best Informatics dissertation and the BSc Computer Science and Physics Class Prize for the highest mark in his degree program. Iskren’s research background in Quantum Computation and experience in machine learning have contributed greatly to 365’s Deep Learning and CNNs courses, as well as the upcoming RNNs course.