Online Course
Deep Learning with TensorFlow 2

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

with Iskren Vankov and Iliya Valchanov

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

4.8

862 reviews on

Start for free

18,451 students already enrolled

Skill level:

Advanced

Duration:

5 hours

Lessons (5 hours)

Practice exams (16 minutes)

CPE credits:

11.5

CPE stands for Continuing Professional Education and represents the mandatory credits a wide range of professionals must earn to maintain their licenses and stay current with regulations and best practices. One CPE credit typically equals 50 minutes of learning. For more details, visit NASBA's official website: www.nasbaregistry.org

Accredited

certificate

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.

Topics & tools

PythonTheoryMachine LearningProgrammingMathematicsDeep LearningTensorflowNeural NetworksMachine and Deep Learning

Your instructor

Iskren Vankov

Oxford Graduate | Quantum Computing Researcher | AI & Machine Learning Expert

Track record

Bringing real-world expertise from leading global companies

Academic background

Master's degree, Computer Science

Media and recognition

Published in Quantum Science and Technology
Microsoft Research Award: Best Informatics Dissertation
BSc CompSci & Physics Prize---top mark in program
Graduate of Oxford, Caltech & Edinburgh, First Class Honors

Ask Iskren a question

Iliya Valchanov

CEO of Team-GPT | AI Educator | Co-founder of 365 Data Science & 3veta

Track record

Bringing real-world expertise from leading global companies

Academic background

Bachelor's degree, International Economics, Management, and Finance

Ask Iliya a question

Course overview

Accredited certificates

Course OVERVIEW

Description

CPE Credits: 11.5 Field of Study: Information Technology
Delivery Method: QAS Self Study

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.

Prerequisites

Python (version 3.8 or later), TensorFlow 2 library, and a code editor or IDE (e.g., Jupyter Notebook, VS Code, or Google Colab)
Intermediate Python and machine learning knowledge is required.
Familiarity with NumPy and neural network fundamentals is recommended.

Advanced preparation

Curriculum

93 lessons 122 exercises 4 exams

1. Introduction

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.

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 Free

Exercise Free
2. Neural networks Intro

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.

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 Free

Exercise Free

Training the model theory Free

Exercise Free

Types of machine learning Free

Exercise Free

The linear model Free

Exercise Free

The linear model. Multiple inputs. Free

Exercise Free

The linear model. Multiple inputs and multiple outputs Free

Exercise Free

Graphical representation Free

Exercise Free

The objective function Free

Exercise Free

L2-norm loss Free

Exercise Free

Cross-entropy loss Free

Exercise Free

One-parameter gradient descent Free

Exercise Free

N-parameter gradient descent Free

Exercise Free
3. Setting up the environment

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.

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!

Why Python and why Jupyter

Exercise

Installing Anaconda

Jupyter Dashboard - Part 1

Jupyter Dashboard - Part 2

Exercise

Installing the TensorFlow package

Installing the packages
4. Minimal example

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.

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

Generating the data (optional)

Exercise

Initializing the variables

Training the model

Exercise

Minimal Example - Exercises.txt
5. Introduction to TensorFlow 2

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.

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

TensorFlow 2 Intro

Exercise

A note on coding in TensorFlow

Types of file formats in Tensorflow and data handling

Exercise

Model layout - inputs, outputs, targets, weights, bias, optimizer, and loss

Exercise

Interpreting the result and extracting the weights and bias

Exercise

Customizing your model

Introduction to TensorFlow - Exercises

Practice exam
6. Deep nets overview

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!

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

Exercise

What is a deep net

Exercise

Really understand deep nets

Exercise

Why do we need non-linearities

Exercise

Activation functions

Exercise

Softmax activation

Exercise

Backpropagation

Backpropagation - intuition

Exercise
7. Backpropagation (optional)

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.

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
8. Overfitting

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).

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

Underfitting and overfitting. A classification example

Exercise

Train vs validation

Exercise

Train vs validation vs test

Exercise

N-fold cross validation

Exercise

Early stopping - motivation and types

Exercise
9. Initialization

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.

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

Exercise

Types of simple initializations

Exercise

Xavier's initialization

Exercise

Practice exam
10. Optimizers

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.

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

Exercise

Local minima pitfalls

Exercise

Momentum

Exercise

Learning rate schedules

Exercise

Learning rate schedules. A picture

Adaptive learning schedules

Adaptive moment estimation

Exercise
11. Preprocessing

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.

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

Exercise

Basic preprocessing

Exercise

Standardization

Exercise

Dealing with categorical data

One hot vs binary

Exercise
12. Deeper example

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).

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

How to tackle the MNIST dataset

MNIST - Importing libraries and data

Preprocess the data - create a validation dataset and scale the data

Preprocess the data - scale the test data

Preprocess the data - shuffle and batch

Preprocess the data - shuffle and batch Exercise

Outline the model

Select the loss and the optimizer

Learning

MNIST - Exercises

Testing the model

Practice exam
13. Business case

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.

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

Outlining the business case solution

Balancing a dataset

Preprocessing the data

Preprocessing Exercise

Load the preprocessed data

Load the preprocessed data Exercise

Learning and interpreting the result

Setting an early stopping mechanism

Setting an early stopping mechanism Exercise

Testing the business model

Homework
14. Conclusion

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.

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

What's more out there

An overview of CNNs

How DeepMind uses deep learning

An overview of RNNs

Non-NN approaches
15. Course exam

20 min

20 min

Course exam

Free lessons

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

Start for free

Coming from a biology background, I had no prior experience in coding or data analysis when I began my master’s in Bioinformatics and Neuroinformatics. The learning curve was steep, but discovering 365 Data Science changed everything. Their comprehensive courses—complete with theory, notes, assessments, and real projects—helped me build skills and confidence. I fell in love with data analysis and chose it as my career path. Even after landing a job, I’ll continue learning with 365!

Kleio T.

After 365: Bioinformatics and Neuroinformatics student

See all reviews

4.8

Based on 862 reviews

#1 most reviewed

AI and data learning platform on Trustpilot.

365 Data Science gave me a strong foundation in SQL, Python, Excel, Power BI, and Tableau, turning abstract concepts into practical skills. These skills have been invaluable in my role at Expeditors, where I provide insights to improve efficiency and decision-making. The structured courses, real-world projects, and hands-on learning bridged the gap between theory and practice, giving me the confidence to apply data-driven solutions in a corporate environment. With 365, I’ve moved forward in my career—and I keep learning every day.

Eugene G. A.

Before 365: Environmental science | Ecological Nest

After 365: Logistics analyst | Expeditors

See all reviews

$29,000

average salary increase

after moving to an AI and data science career

Coming from a non-data background, I was overwhelmed by the scattered content online. 365 Data Science stood out with its structured courses, knowledgeable instructors, and in-depth coverage. After enrolling in the one-year program and completing the Data Science Bootcamp, I gained the skills and confidence to ace tough coding tests and interviews—landing an analyst role at Meesho. The platform made learning clear, practical, and effective, and I’m deeply grateful for the journey.