Deep Learning with TensorFlow

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. We will be doing this with TensorFlow.

Sign up to
preview the program
for FREE!

Create a free account and start learning data science today.

create free account
Our graduates work at exciting places:

Section 1


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.

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

Section 2

Neural networks Intro

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.

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.

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 the TensorFlow package

Section 4

Minimal example

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.

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

In this section, we will introduce the TensorFlow framework – a deep learning library developed by Google. It allows you to construct fairly sophisticated models with little coding. This intro section teaches you what tensors are and why the TensorFlow framework is one of the preferred tools of data scientists in 2019.

Premium course icon TensorFlow outline
Premium course icon TensorFlow introduction
Premium course icon Types of file formats used in TensorFlow
Premium course icon Laying down the model
Premium course icon Laying down the optimizers
Premium course icon Output

Section 6

Deep nets overview

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!

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


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).

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


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.

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

Section 9


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.

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


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.

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

All the lessons so far will have given you a solid preparation for what we're about to start doing: writing code. The problem we will solve here is the “Hello, world” of machine learning. It is called MNIST classification and consists of 70,000 handwritten digits. Together, we will create an algorithm that takes an image as input and then correctly determines which number is shown in that image.

Premium course icon MNIST dataset
Premium course icon How to tackle the MNIST dataset
Premium course icon MNIST - Importing libraries and data
Premium course icon MNIST - Outlining the model
Premium course icon MNIST - Declaring the loss
Premium course icon Accuracy of a model
Premium course icon Early stopping and batching preparation
Premium course icon Optimization
Show all lessons
Premium course icon Commenting on the results
Show fewer lessons

Section 12

Business case

In this section, we will solve a real-life business case, such as the ones data scientists solve on the job. You will build a model that will determine how likely it is that a specific client will come back and buy another product from a company selling audiobooks. This is a great example of how machine learning can help a company optimize its marketing efforts and ultimately grow its bottom line results.

Premium course icon The dataset
Premium course icon Outlining the solution
Premium course icon Balancing a dataset
Premium course icon Preprocessing the data
Premium course icon Creating the batching class
Premium course icon Outlining the model
Premium course icon Optimizing the algorithm
Premium course icon Running the code
Show all lessons
Premium course icon Test
Premium course icon Homework
Show fewer lessons

Section 13


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.

Premium course icon Summary
Premium course icon Whats more out there
Premium course icon An overview of CNNs
Premium course icon An overview of RNNs
Premium course icon Non-NN approaches

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 upon 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 500,000 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!
Complete Data Science Education
Get 50% OFF