12 PM EST*

Save 30% : Register Now

Price: $147

Regular price $210 , discounted 30%

  • 4 hour immersive session

  • Hands-on training with Q&A

  • Recording available on-demand

  • Certification of Completion

10% Discount Ends in:

Subscribe and get an additional 10% to 35% off ALL live training session

View Plans

Meet Your Instructor

Ankur Patel

Ankur Patel is the co-founder & Head of Data at Glean, an AI-powered spend intelligence solution for managing vendor spend, and the co-founder of Mellow, a fully managed machine learning platform for SMBs. He is an applied machine learning specialist in both unsupervised learning and natural language processing, and he is the author of Hands-on Unsupervised Learning Using Python: How to Build Applied Machine Learning Solutions from Unlabeled Data and Applied Natural Language Processing in the Enterprise: Teaching Machines to Read, Write, and Understand. Prior to founding Glean and Mellow, Ankur led data science and machine learning teams at several startups including 7Park Data, ThetaRay, and R-Squared Macro and was the lead emerging markets trader at Bridgewater Associates. He is a graduate of Princeton University and currently resides in New York City.

Why Enroll?

By the end of the course, participants will be able to:

  • Understand the basic of semi-supervised learning and how supervised and unsupervised learning complement each other

  • Build unsupervised, supervised, and semi-supervised learning fraud detection solutions and evaluate results

  • Understand Deep Unsupervised Learning and Generative Models 

Course Overview

In this course, we will explore one of the core concepts in unsupervised learning, autoencoders, and introduce semi-supervised learning. Autoencoders are a shallow neural network that learn representations of the original input data and output the newly learned representations. In other words, autoencoders perform automatic feature engineering, limiting the need for manual feature engineering and accelerating the build of machine learning systems. Autoencoders are also a means to leverage information in a partially labeled dataset. With autoencoders, we are able to turn unsupervised machine learning problems into semi- supervised ones. In this course, we build unsupervised, supervised, and semi-supervised (using autoencoders) credit card fraud detection systems. First, we will employ a pure unsupervised approach, without the use of any labels. Next, we will employ a supervised approach on a partially labeled dataset. Finally, we will apply autoencoders to the partially labeled dataset (an unsupervised learning technique) and combine this with a supervised approach, building a semi-supervised solution. To conclude, we will compare and contrast the results of all three approaches.” We will also introduce deep unsupervised learning and explore one of the hottest areas of unsupervised learning today: generative modeling using GANs (short for generative adversarial networks). We will conclude with a demonstration of text and image-based GANs in action.

Course Outline

Lesson 1. Introduction to Semi-Supervised Learning

  • Motivation for representation learning and refresher on neural networks and automatic feature engineering
  • Intro to semi-supervised learning and how supervised and unsupervised learning complement each other
  • Autoencoders and the variants (undercomplete vs. overcomplete autoencoders, dense vs. sparse autoencoders, denoising autoencoder, and variational autoencoder)

Lesson 2. Application: Semi-supervised Fraud Detection using Autoencoders

  • Introduce use case: credit card fraud detection
  • Explore and prepare the data
  • Define evaluation function
  • Build unsupervised learning fraud detection solution and evaluate results
  • Build supervised learning fraud detection solution and evaluate results
  • Build semi-supervised learning fraud detection solution and evaluate results
  • Compare and contrast results

Lesson 3. Deep Unsupervised Learning and Generative Models

  • Intro to deep unsupervised learning
  • Intro to generative modeling and synthetic data
  • GANs and the variants
  • Demonstration of GANs in action using code

Key Details





MAY 18TH, 2021





Python coding experience and familiarity with pandas, numpy, and scikit-learn would be helpful.

Understanding of basic machine learning concepts, including supervised learning and experience with deep learning and frameworks such as TensorFlow or PyTorch is a plus.

Upcoming Live Training

May 27th

Part 1: Computer Science

Through the measured exposition of theory paired with interactive examples, you’ll develop a working understanding of all of the essential data structures across the list, dictionary, tree, and graph families. 

learn more
Open Data Science

Ai+ | ODSC
One Broadway, 14th Floor
Cambridge, MA 02142

Privacy Settings
We use cookies to enhance your experience while using our website. If you are using our Services via a browser you can restrict, block or remove cookies through your web browser settings. We also use content and scripts from third parties that may use tracking technologies. You can selectively provide your consent below to allow such third party embeds. For complete information about the cookies we use, data we collect and how we process them, please check our Privacy Policy
Consent to display content from - Youtube
Consent to display content from - Vimeo
Google Maps
Consent to display content from - Google