Deep Learning with TensorFlow 2.0

Machine and deep learning are some of those quantitative analysis skills that differentiate the data scientist from the other members of the team. 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 from this powerful tool for the purposes of data science. The technology we employ is TensorFlow 2.0 which is the state-of-the-art deep learning framework.

Sign up to
preview the course
for FREE!

Create a free account and start learning data science today.

create free account
Our graduates work at exciting places:
walmart
tesla
paypal
citibank
booking.com

Section 1

Introduction

What is machine learning, deep learning and AI? How is it useful and is it really as important as people tend to believe?

Premium course icon Welcome to Machine Learning
Premium course icon What does the course cover

Section 2

Neural networks Intro

Neural networks are more or less what we mean by 'deep learning' nowadays. In this section we explain the main rationale behind simple feed-forward neural networks.

Premium course icon Introduction to neural networks
Premium course icon Training the model
Premium course icon Types of machine learning
Premium course icon The linear model
Premium course icon Graphical representation
Premium course icon The objective function
Premium course icon L2-norm loss
Premium course icon Cross-entropy loss
Show all lessons
Premium course icon One-parameter gradient descent
Premium course icon N-parameter gradient descent
Show fewer lessons

Section 3

Setting up the environment

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 2.0.

Premium course icon Setting up the environment - Do not skip, please!
Premium course icon Why Python and why Jupyter
Premium course icon Installing Anaconda
Premium course icon Jupyter Dashboard - Part 1
Premium course icon Jupyter Dashboard - Part 2
Premium course icon Installing TensorFlow 2.0

Section 4

Minimal example

To understand the inner workings of Neural Networks we start with a very simple example (called 'minimal example'). It is a very naïve network, basically equivalent to a linear regression.

Premium course icon Outline
Premium course icon Generating the data (optional)
Premium course icon Initializing the variables
Premium course icon Training the model

Section 5

Introduction to TensorFlow 2

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.

Premium course icon TensorFlow outline
Premium course icon TensorFlow 2 intro
Premium course icon A note on coding in TensorFlow
Premium course icon Types of file formats in TensorFlow and data handling
Premium course icon Model layout - inputs, outputs, targets, weights, biases, optimizer and loss
Premium course icon Interpreting the result and extracting the weights and bias
Premium course icon Customizing your model

Section 6

Deep nets overview

To have 'deep learning' we need 'deep' neural networks. In this section, we explain what exactly it means to be deep and focus on other important characteristics like width and activation functions. Finally, we explore the backpropagation algorithm.

Premium course icon The layer
Premium course icon What is a deep net
Premium course icon Really understand deep nets
Premium course icon Why do we need non-linearities
Premium course icon Activation functions
Premium course icon Softmax activation
Premium course icon Backpropagation
Premium course icon Backpropagation - intuition

Section 7

Overfitting

Neural networks are extremely good at modeling the data at hand. That's why we can often 'learn the data TOO WELL'. This is called overfitting. Of course, there are numerous ways to prevent this from happening which we explore in that section.

Premium course icon Underfitting and overfitting
Premium course icon Underfitting and overfitting. A classification example
Premium course icon Train vs validation
Premium course icon Train vs validation vs test
Premium course icon N-fold cross validation
Premium course icon Early stopping - motivation and types

Section 8

Initializaiton

When the model is learning, it is searching for better and better solutions to the problem at hand. However, it starts from some initial values for its parameters. It actually matters what our starting point is and that's what initialization is all about.

Premium course icon Initializaiton
Premium course icon Types of simple initializations
Premium course icon Xavier's initialization

Section 9

Optimizers

There is a trade-off between having a fast model and an accurate model. In this section we explore different optimization algorithms, based on the gradient descent logic, as well as learning rate schedules and batching.

Premium course icon SGD&Batching
Premium course icon Local minima pitfalls
Premium course icon Momentum
Premium course icon Learning rate schedules
Premium course icon Learning rate schedules. A picture
Premium course icon Adaptive learning schedules
Premium course icon Adaptive moment estimation

Section 10

Preprocessing

Preprocessing is a crucial step relevant to any modeling problem. While there are dozens of different preprocessing techniques, there are several that are commonly employed for almost all neural networks.

Premium course icon Preprocessing
Premium course icon Basic preprocessing
Premium course icon Standardization
Premium course icon Dealing with categorical data
Premium course icon One-hot vs binary

Section 11

Deeper example

Once we have learned all the relevant theory, we are ready to jump into the 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).

Premium course icon The dataset
Premium course icon How to tackle the MNIST
Premium course icon Importing the relevant libraries and loading the data
Premium course icon Preprocess the data - create a validation dataset and scale the data
Premium course icon Preprocess the data - shuffle and batch the data
Premium course icon Outline the model
Premium course icon Select the loss and the optimizer
Premium course icon Learning
Show all lessons
Premium course icon Testing the model
Show fewer lessons

Section 12

Business case

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.

Premium course icon Exploring the dataset and identifying predictors
Premium course icon Outlining the business case solution
Premium course icon Balancing the dataset
Premium course icon Preprocessing the data
Premium course icon Load the preprocessed data
Premium course icon Learning and interpreting the result
Premium course icon Setting an early stopping mechanism
Premium course icon Testing the model
MODULE 3

Machine and Deep Learning

This course is part of Module 3 of the 365 Data Science Program. The complete training consists of four modules, each building up on your knowledge from the previous one. Expanding on your statistical and programming skills from Modules 1 and 2, Module 3 is designed to improve your programming skills and develop your advanced statistical thinking. You will learn how to build complete linear and logistic regression models, how to cluster data, and how to build deep learning models with TensorFlow 2.0.

See All Modules

Trust the other 276,000 students

Ready to start?
Sign up today for FREE!

Whether you want to scale your career or transition into a new field, data science is the number one skillset employers look for. Grow your analytics expertise and get hired as a data scientist!