This class is part four in a series. It’s designed as a follow up to the first three classes, but it is appropriate for anyone familiar with Supervised Machine Learning and in particular Deep Learning, who wants to expand their knowledge of Machine Learning to Human-in-the-Loop strategies for annotating data and creating the feedback loop between the human and AI components.

This is a hands-on course that takes students from little knowledge of active learning to comfort building real world models. It requires very little math, but reasonably proficient programming skills. At the end of class students will be able to build Active Learning systems on their own, and more importantly be able to quickly find resources to help them with new problems they encounter in their domain.

Technologies Used

- Tensorflow

- ImageNet

Prerequisites

Basic python programming skills and,

1. Completion of our introductory courses,

or

2. Some Deep Learning experience as an engineer or data scientist

What you need to bring:

Students need to bring a laptop. We will provide setup instructions closer to the class.

Take aways:

- Practical high-level knowledge of how Active Learning works

- Understanding of how Deep Learning architectures have specific properties that are useful for Active Learning

- How to design user interfaces for annotation that take into account whether there is raw data or output from a Machine Learning model

Curriculum:

Morning: Introduction to RNNs, LSTMs

9:00 – 10:00 Breakfast, Laptop Setup and deep learning overview

10:00 - 11:00 Set up CrowdFlower accounts and run first job

11:00 - 12:00 Active Learning Overview

12:00-1:00 Lunch

Afternoon: Hands-on experiments

1:00 - 2:00 Create your first Active Learning model and evaluate on ImageNet data

2:00 - 3:00 Implement one advanced Active Learning technique; Overview of Advanced User Interfaces and Human Computer Interaction (HCI) for Data Annotation

3:00 - 5:00 Build and evaluate User Interfaces for Active Learning.

Testimonials and Feedback

"I found it to be really engaging and interesting. I was already familiar with some ML concepts, so it helped me understand them better and think about how to apply them. The code samples are really great and will definitely reference them in the future. I thought the class went at a generally good pace."

"Good experience - full of great resources and discussion. Good, practical intro for new folks, and also valuable for those familiar with the basics. I walked away excited to experiment!"

“Class was great, you ticked off my curiosity. I am excited to review the content and retry it by myself. Thank you for encouraging peer to peer collaboration and making the effort to build the slack channel. I think it was nice to see you debug live.”

Instructor:

Robert Munro is the VP of Machine Learning at CrowdFlower and an expert in combining Human and Machine Intelligence, working with Machine Learning approaches to text, speech, image and video processing. Robert has founded several AI companies, building some of the top teams in Artificial Intelligence. He has worked in many diverse environments, from Sierra Leone, Haiti and the Amazon, to London, Sydney and Silicon Valley, in organizations ranging from startups to the United Nations. He most recently ran Product for AWS’s first Natural Language Processing services in the Deep Learning team at Amazon AI.

Robert has published more than 50 papers and is a regular speaker about technology in an increasingly connected world. He has a PhD from Stanford University.