Machine Learning, Data Science and Deep Learning with Python
4.5 (21,828 ratings)
Course Ratings are calculated from individual students’ ratings and a variety of other signals, like age of rating and reliability, to ensure that they reflect course quality fairly and accurately.
130,695 students enrolled

Machine Learning, Data Science and Deep Learning with Python

Complete hands-on machine learning tutorial with data science, Tensorflow, artificial intelligence, and neural networks
4.5 (21,819 ratings)
Course Ratings are calculated from individual students’ ratings and a variety of other signals, like age of rating and reliability, to ensure that they reflect course quality fairly and accurately.
130,695 students enrolled
Last updated 7/2020
English, Italian [Auto], 2 more
  • Polish [Auto]
  • Portuguese [Auto]
Current price: $132.99 Original price: $189.99 Discount: 30% off
5 hours left at this price!
30-Day Money-Back Guarantee
This course includes
  • 14 hours on-demand video
  • 6 articles
  • Full lifetime access
  • Access on mobile and TV
  • Certificate of Completion
Training 5 or more people?

Get your team access to 4,000+ top Udemy courses anytime, anywhere.

Try Udemy for Business
What you'll learn
  • Build artificial neural networks with Tensorflow and Keras
  • Classify images, data, and sentiments using deep learning
  • Make predictions using linear regression, polynomial regression, and multivariate regression
  • Data Visualization with MatPlotLib and Seaborn
  • Implement machine learning at massive scale with Apache Spark's MLLib
  • Understand reinforcement learning - and how to build a Pac-Man bot
  • Classify data using K-Means clustering, Support Vector Machines (SVM), KNN, Decision Trees, Naive Bayes, and PCA
  • Use train/test and K-Fold cross validation to choose and tune your models
  • Build a movie recommender system using item-based and user-based collaborative filtering
  • Clean your input data to remove outliers
  • Design and evaluate A/B tests using T-Tests and P-Values
Course content
Expand all 111 lectures 14:14:31
+ Getting Started
11 lectures 01:00:23

What to expect in this course, who it's for, and the general format we'll follow.

Preview 02:41
Installation: Getting Started
[Activity] WINDOWS: Installing and Using Anaconda & Course Materials
[Activity] MAC: Installing and Using Anaconda & Course Materials
[Activity] LINUX: Installing and Using Anaconda & Course Materials

In a crash course on Python and what's different about it, we'll cover the importance of whitespace in Python scripts, and how to import Python modules.

Python Basics, Part 1 [Optional]

In part 2 of our Python crash course, we'll cover Python data structures including lists, tuples, and dictionaries.

Preview 05:17

In this lesson, we'll see how functions work in Python.

[Activity] Python Basics, Part 3 [Optional]

We'll wrap up our Python crash course covering Boolean expressions and looping constructs.

[Activity] Python Basics, Part 4 [Optional]

Pandas is a library we'll use throughout the course for loading, examining, and manipulating data. Let's see how it works with some examples, and you'll have an exercise at the end too.

Introducing the Pandas Library [Optional]
+ Statistics and Probability Refresher, and Python Practice
13 lectures 02:02:16

We cover the differences between continuous and discrete numerical data, categorical data, and ordinal data.

Preview 06:58

A refresher on mean, median, and mode - and when it's appropriate to use each.

Mean, Median, Mode

We'll use mean, median, and mode in some real Python code, and set you loose to write some code of your own.

[Activity] Using mean, median, and mode in Python

We'll cover how to compute the variation and standard deviation of a data distribution, and how to do it using some examples in Python.

Preview 11:12

Introducing the concepts of probability density functions (PDF's) and probability mass functions (PMF's).

Probability Density Function; Probability Mass Function

We'll show examples of continuous, normal, exponential, binomial, and poisson distributions using iPython.

Common Data Distributions

We'll look at some examples of percentiles and quartiles in data distributions, and then move on to the concept of the first four moments of data sets.

[Activity] Percentiles and Moments

An overview of different tricks in matplotlib for creating graphs of your data, using different graph types and styles.

[Activity] A Crash Course in matplotlib
[Activity] Advanced Visualization with Seaborn

The concepts of covariance and correlation used to look for relationships between different sets of attributes, and some examples in Python.

[Activity] Covariance and Correlation

We cover the concepts and equations behind conditional probability, and use it to try and find a relationship between age and purchases in some fabricated data using Python.

[Exercise] Conditional Probability

Here we'll go over my solution to the exercise I challenged you with in the previous lecture - changing our fabricated data to have no real correlation between ages and purchases, and seeing if you can detect that using conditional probability.

Exercise Solution: Conditional Probability of Purchase by Age

An overview of Bayes' Theorem, and an example of using it to uncover misleading statistics surrounding the accuracy of drug testing.

Preview 05:23
+ Predictive Models
4 lectures 35:07

We introduce the concept of linear regression and how it works, and use it to fit a line to some sample data using Python.

Preview 11:01

We cover the concepts of polynomial regression, and use it to fit a more complex page speed - purchase relationship in Python.

Preview 08:04

Multivariate models let us predict some value given more than one attribute. We cover the concept, then use it to build a model in Python to predict car prices based on their number of doors, mileage, and number of cylinders. We'll also get our first look at the statsmodels library in Python.

[Activity] Multiple Regression, and Predicting Car Prices

We'll just cover the concept of multi-level modeling, as it is a very advanced topic. But you'll get the ideas and challenges behind it.

Multi-Level Models
+ Machine Learning with Python
16 lectures 01:39:00

The concepts of supervised and unsupervised machine learning, and how to evaluate the ability of a machine learning model to predict new values using the train/test technique.

Supervised vs. Unsupervised Learning, and Train/Test

We'll apply train test to a real example using Python.

[Activity] Using Train/Test to Prevent Overfitting a Polynomial Regression

We'll introduce the concept of Naive Bayes and how we might apply it to the problem of building a spam classifier.

Bayesian Methods: Concepts

We'll actually write a working spam classifier, using real email training data and a surprisingly small amount of code!

Preview 08:05

K-Means is a way to identify things that are similar to each other. It's a case of unsupervised learning, which could result in clusters you never expected!

K-Means Clustering

We'll apply K-Means clustering to find interesting groupings of people based on their age and income.

[Activity] Clustering people based on income and age

Entropy is a measure of the disorder in a data set - we'll learn what that means, and how to compute it mathematically.

Measuring Entropy
[Activity] WINDOWS: Installing Graphviz
[Activity] MAC: Installing Graphviz
[Activity] LINUX: Installing Graphviz

Decision trees can automatically create a flow chart for making some decision, based on machine learning! Let's learn how they work.

Preview 08:43

We'll create a decision tree and an entire "random forest" to predict hiring decisions for job candidates.

[Activity] Decision Trees: Predicting Hiring Decisions

Random Forests was an example of ensemble learning; we'll cover over techniques for combining the results of many models to create a better result than any one could produce on its own.

Ensemble Learning

XGBoost is perhaps the most powerful machine learning algorithm today, and it's really easy to use. We'll cover how it works, how to tune it, and run an example on the Iris data set showing how powerful XGBoost is.

[Activity] XGBoost

Support Vector Machines are an advanced technique for classifying data that has multiple features. It treats those features as dimensions, and partitions this higher-dimensional space using "support vectors."

Support Vector Machines (SVM) Overview

We'll use scikit-learn to easily classify people using a C-Support Vector Classifier.

[Activity] Using SVM to cluster people using scikit-learn
+ Recommender Systems
6 lectures 49:10

One way to recommend items is to look for other people similar to you based on their behavior, and recommend stuff they liked that you haven't seen yet.

Preview 07:57

The shortcomings of user-based collaborative filtering can be solved by flipping it on its head, and instead looking at relationships between items instead of relationships between people.

Item-Based Collaborative Filtering

We'll use the real-world MovieLens data set of movie ratings to take a first crack at finding movies that are similar to each other, which is the first step in item-based collaborative filtering.

[Activity] Finding Movie Similarities

Our initial results for movies similar to Star Wars weren't very good. Let's figure out why, and fix it.

[Activity] Improving the Results of Movie Similarities

We'll implement a complete item-based collaborative filtering system that uses real-world movie ratings data to recommend movies to any user.

Preview 10:22

As a student exercise, try some of my ideas - or some ideas of your own - to make the results of our item-based collaborative filter even better.

[Exercise] Improve the recommender's results
+ More Data Mining and Machine Learning Techniques
9 lectures 01:17:39

KNN is a very simple supervised machine learning technique; we'll quickly cover the concept here.

K-Nearest-Neighbors: Concepts

We'll use the simple KNN technique and apply it to a more complicated problem: finding the most similar movies to a given movie just given its genre and rating information, and then using those "nearest neighbors" to predict the movie's rating.

[Activity] Using KNN to predict a rating for a movie

Data that includes many features or many different vectors can be thought of as having many dimensions. Often it's useful to reduce those dimensions down to something more easily visualized, for compression, or to just distill the most important information from a data set (that is, information that contributes the most to the data's variance.) Principal Component Analysis and Singular Value Decomposition do that.

Dimensionality Reduction; Principal Component Analysis

We'll use sckikit-learn's built-in PCA system to reduce the 4-dimensions Iris data set down to 2 dimensions, while still preserving most of its variance.

[Activity] PCA Example with the Iris data set

Cloud-based data storage and analysis systems like Hadoop, Hive, Spark, and MapReduce are turning the field of data warehousing on its head. Instead of extracting, transforming, and then loading data into a data warehouse, the transformation step is now more efficiently done using a cluster after it's already been loaded. With computing and storage resources so cheap, this new approach now makes sense.

Data Warehousing Overview: ETL and ELT

We'll describe the concept of reinforcement learning - including Markov Decision Processes, Q-Learning, and Dynamic Programming - all using a simple example of developing an intelligent Pac-Man.

Preview 12:44
[Activity] Reinforcement Learning & Q-Learning with Gym

What's a confusion matrix, and how do I read it?

Understanding a Confusion Matrix
Measuring Classifiers (Precision, Recall, F1, ROC, AUC)
+ Dealing with Real-World Data
10 lectures 01:11:47

Bias and Variance both contribute to overall error; understand these components of error and how they relate to each other.

Bias/Variance Tradeoff

We'll introduce the concept of K-Fold Cross-Validation to make train/test even more robust, and apply it to a real model.

[Activity] K-Fold Cross-Validation to avoid overfitting

Cleaning your raw input data is often the most important, and time-consuming, part of your job as a data scientist!

Preview 07:10

In this example, we'll try to find the top-viewed web pages on a web site - and see how much data pollution makes that into a very difficult task!

[Activity] Cleaning web log data

A brief reminder: some models require input data to be normalized, or within the same range, of each other. Always read the documentation on the techniques you are using.

Normalizing numerical data

A review of how outliers can affect your results, and how to identify and deal with them in a principled manner.

[Activity] Detecting outliers
Feature Engineering and the Curse of Dimensionality
Imputation Techniques for Missing Data
Handling Unbalanced Data: Oversampling, Undersampling, and SMOTE
Binning, Transforming, Encoding, Scaling, and Shuffling
+ Apache Spark: Machine Learning on Big Data
12 lectures 01:32:59
Warning about Java 11 and Spark 3!
Spark installation notes for MacOS and Linux users

We'll present an overview of the steps needed to install Apache Spark on your desktop in standalone mode, and get started by getting a Java Development Kit installed on your system.

[Activity] Installing Spark - Part 1

We'll install Spark itself, along with all the associated environment variables and ancillary files and settings needed for it to function properly.

[Activity] Installing Spark - Part 2

A high-level overview of Apache Spark, what it is, and how it works.

Spark Introduction

We'll go in more depth on the core of Spark - the RDD object, and what you can do with it.

Spark and the Resilient Distributed Dataset (RDD)

A quick overview of MLLib's capabilities, and the new data types it introduces to Spark.

Introducing MLLib

We'll walk through an example of coding up and running a decision tree using Apache Spark's MLLib! In this exercise, we try to predict if a job candidate will be hired based on their work and educational history, using a decision tree that can be distributed across an entire cluster with Spark.

Preview 16:15

We'll take the same example of clustering people by age and income from our earlier K-Means lecture - but solve it in Spark!

[Activity] K-Means Clustering in Spark

We'll introduce the concept of TF-IDF (Term Frequency / Inverse Document Frequency) and how it applies to search problems, in preparation for using it with MLLib.

Preview 06:44

Let's use TF-IDF, Spark, and MLLib to create a rudimentary search engine for real Wikipedia pages!

[Activity] Searching Wikipedia with Spark

Spark 2.0 introduced a new API for MLLib based on DataFrame objects; we'll look at an example of using this to create and use a linear regression model.

[Activity] Using the Spark 2.0 DataFrame API for MLLib
+ Experimental Design / ML in the Real World
6 lectures 41:58

High-level thoughts on various ways to deploy your trained models to production systems including apps and websites.

Deploying Models to Real-Time Systems

Running controlled experiments on your website usually involves a technique called the A/B test. We'll learn how they work.

A/B Testing Concepts

How to determine significance of an A/B tests results, and measure the probability of the results being just from random chance, using T-Tests, the T-statistic, and the P-value.

T-Tests and P-Values

We'll fabricate A/B test data from several scenarios, and measure the T-statistic and P-Value for each using Python.

[Activity] Hands-on With T-Tests

Some A/B tests just don't affect customer behavior one way or another. How do you know how long to let an experiment run for before giving up?

Determining How Long to Run an Experiment

There are many limitations associated with running short-term A/B tests - novelty effects, seasonal effects, and more can lead you to the wrong decisions. We'll discuss the forces that may result in misleading A/B test results so you can watch out for them.

Preview 09:26
+ Deep Learning and Neural Networks
19 lectures 03:03:19

If you skipped ahead, I'll show you where to get the course materials for just this section. And we'll cover some pre-requisite concepts for understanding how neural networks operate: gradient descent, autodiff, and softmax.

Deep Learning Pre-Requisites

We'll cover the evolution of artificial neural networks from 1943 to modern-day architectures, which is a great way to understand how they work.

Preview 11:14

Google's Tensorflow Playground lets you experiment with deep neural networks and understand them - without writing a line of code!

[Activity] Deep Learning in the Tensorflow Playground

Let's dive into the details on how modern multi-level perceptrons are trained and tuned.

Deep Learning Details

We'll cover Google's open-source Tensorflow Python library, and see how it can help you create and train neural networks.

Introducing Tensorflow
Important note about Tensorflow 2

We'll use Tensorflow to create a neural network that classifies handwritten numerals from the MNIST data set. Part 1 of 2.

[Activity] Using Tensorflow, Part 1

We'll use Tensorflow to create a neural network that classifies handwritten numerals from the MNIST data set. Part 2 of 2.

[Activity] Using Tensorflow, Part 2

The Tensorflow 1.9 offers a higher-level API called Keras, and makes it easier to construct your neural networks. We'll use Keras to solve the same handwriting recognition problem - but with much less code.

[Activity] Introducing Keras

As another hands-on example, we'll use Keras to build a neural network that learns how to determine if a politician is Republican on Democrat just based on their votes.

[Activity] Using Keras to Predict Political Affiliations

CNN's mimic your visual cortex, and can find features in one, two, or three-dimensional data even if you're not sure where exactly that feature is.

Convolutional Neural Networks (CNN's)

CNN's are better suited to image data, and we'll prove that by using a CNN in Keras on the MNIST data.

[Activity] Using CNN's for handwriting recognition

RNN's can handle sequences of data, like events over time or words in a sentence. Learn what's different about how they work, how they are trained, and ways to optimize them.

Recurrent Neural Networks (RNN's)

Let's implement a RNN in Keras to determine positive or negative sentiments for real movie reviews from IMDb!

[Activity] Using a RNN for sentiment analysis

We'll see how transfer learning makes it trivially easy to use pre-trained models for common AI tasks.

[Activity] Transfer Learning
Tuning Neural Networks: Learning Rate and Batch Size Hyperparameters
Deep Learning Regularization with Dropout and Early Stopping

As with any new technology, sometimes we can become overzealous in how we use it. A few cautionary tales to make sure your deep learning work does more good than harm.

Preview 11:02

Some suggested resources for continuing your education on deep learning, artificial intelligence, and neural networks.

Learning More about Deep Learning
  • You'll need a desktop computer (Windows, Mac, or Linux) capable of running Anaconda 3 or newer. The course will walk you through installing the necessary free software.
  • Some prior coding or scripting experience is required.
  • At least high school level math skills will be required.

New! Updated for Winter 2019 with extra content on feature engineering, regularization techniques, and tuning neural networks - as well as Tensorflow 2.0!

Machine Learning and artificial intelligence (AI) is everywhere; if you want to know how companies like Google, Amazon, and even Udemy extract meaning and insights from massive data sets, this data science course will give you the fundamentals you need. Data Scientists enjoy one of the top-paying jobs, with an average salary of $120,000 according to Glassdoor and Indeed. That's just the average! And it's not just about money - it's interesting work too!

If you've got some programming or scripting experience, this course will teach you the techniques used by real data scientists and machine learning practitioners in the tech industry - and prepare you for a move into this hot career path. This comprehensive machine learning tutorial includes over 100 lectures spanning 14 hours of video, and most topics include hands-on Python code examples you can use for reference and for practice. I’ll draw on my 9 years of experience at Amazon and IMDb to guide you through what matters, and what doesn’t.

Each concept is introduced in plain English, avoiding confusing mathematical notation and jargon. It’s then demonstrated using Python code you can experiment with and build upon, along with notes you can keep for future reference. You won't find academic, deeply mathematical coverage of these algorithms in this course - the focus is on practical understanding and application of them. At the end, you'll be given a final project to apply what you've learned!

The topics in this course come from an analysis of real requirements in data scientist job listings from the biggest tech employers. We'll cover the machine learning, AI, and data mining techniques real employers are looking for, including:

  • Deep Learning / Neural Networks (MLP's, CNN's, RNN's) with TensorFlow and Keras

  • Data Visualization in Python with MatPlotLib and Seaborn

  • Transfer Learning

  • Sentiment analysis

  • Image recognition and classification

  • Regression analysis

  • K-Means Clustering

  • Principal Component Analysis

  • Train/Test and cross validation

  • Bayesian Methods

  • Decision Trees and Random Forests

  • Multiple Regression

  • Multi-Level Models

  • Support Vector Machines

  • Reinforcement Learning

  • Collaborative Filtering

  • K-Nearest Neighbor

  • Bias/Variance Tradeoff

  • Ensemble Learning

  • Term Frequency / Inverse Document Frequency

  • Experimental Design and A/B Tests

  • Feature Engineering

  • Hyperparameter Tuning

...and much more! There's also an entire section on machine learning with Apache Spark, which lets you scale up these techniques to "big data" analyzed on a computing cluster. And you'll also get access to this course's Facebook Group, where you can stay in touch with your classmates.

If you're new to Python, don't worry - the course starts with a crash course. If you've done some programming before, you should pick it up quickly. This course shows you how to get set up on Microsoft Windows-based PC's, Linux desktops, and Macs.

If you’re a programmer looking to switch into an exciting new career track, or a data analyst looking to make the transition into the tech industry – this course will teach you the basic techniques used by real-world industry data scientists. These are topics any successful technologist absolutely needs to know about, so what are you waiting for? Enroll now!

  • "I started doing your course in 2015... Eventually I got interested and never thought that I will be working for corporate before a friend offered me this job. I am learning a lot which was impossible to learn in academia and enjoying it thoroughly. To me, your course is the one that helped me understand how to work with corporate problems. How to think to be a success in corporate AI research. I find you the most impressive instructor in ML, simple yet convincing." - Kanad Basu, PhD

Who this course is for:
  • Software developers or programmers who want to transition into the lucrative data science and machine learning career path will learn a lot from this course.
  • Technologists curious about how deep learning really works
  • Data analysts in the finance or other non-tech industries who want to transition into the tech industry can use this course to learn how to analyze data using code instead of tools. But, you'll need some prior experience in coding or scripting to be successful.
  • If you have no prior coding or scripting experience, you should NOT take this course - yet. Go take an introductory Python course first.