This class is part three in our AI series. We've designed it as a follow up to Introduction to Deep learning Part 2 Vision Algorithms, but might also be appropriate for someone who took the Coursera course in machine learning but wanted something more hands-on or who took Technical Introduction to AI, Machine Learning & Deep Learning Part I and wanted to really focus on time series and text.

This is a hands-on course that takes students with little knowledge of deep learning and gives them what they need to build real-world models. Our course requires very little math, but reasonably proficient programming skills.

At the end of class students will be able to build LSTMs on their own, and, more importantly, be able to quickly find resources to help them with new problems they encounter in their domain.

Technologies Introduced:

• Deep Learning Frameworks

• Keras

• Tensorflow

• Deep Learning Model Architectures

• RNN

• CNN

• LSTM

• GRU

• word2vec

• Applications

• Text generation

• Text classification

Prerequisites:

1. Completion of our introductory course “Technical Introduction to AI, Machine Learning & Deep Learning” and “Deep learning Part 2: Vision Algorithms," or,

2. Engineers with some deep learning experience but not LSTMs. Students should have trained a CNN in keras/tensorflow and understood how the individual layers worked

What you need to bring:

Students need to bring a laptop. We have detailed setup instructions at https://github.com/lukas/ml-class/blob/master/README.md

If you want to run on a GPU either on your laptop or in the cloud for this course, you can. We have setup instructions for an AWS machine at https://github.com/lukas/ml-class/blob/master/aws.md

Take aways:

- Practical high-level knowledge of how RNNs, LSTMs GRUs actually work.

- How to build multi layer LSTMs

- How to use popular vector embeddings like word2vec

Instructors:

Lukas Biewald is the founder of CrowdFlower, an Artificial Intelligence company that works with data science teams at Google, Bloomberg, Facebook and hundreds of other organizations to make machine learning work in the real world.

Prior to that, Lukas was the first data scientist at Powerset (Acquired by Microsoft and rebranded as Bing) and a scientist at Yahoo!, Lukas was shipping machine learning algorithms to hundreds of millions of users.

Lukas frequently teaches invited Machine Learning workshops with Galvanize, O’Reilly and ODSC. He is a contributor to Computerworld, Forbes and O’Reilly and has presented at the machine learning academic conferences such as AAAI, SIGIR, ACL and EMNLP. He was in Inc’s annual 30 under 30 and was also a finalist at TechCrunch Disrupt.

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.

Curriculum:

Morning: Introduction to RNNs, LSTMs

9:00 – 10:00

Breakfast, Laptop Setup and deep learning overview

10:00 - 11:00

High-level overview of RNNs, LSTMs, word vector encodings and how they work

11:00 - 12:00

Train a time series predicton model in keras/tensorflow and run on sample data.

12:00-1:00

Lunch

Afternoon: Applications

1:00 - 2:00

Build a text generation model

2:00 - 3:00

Word vector embeddings and working with text data

3:00 - 5:00

Build, debug and deploy a text classification model and apply to other domains (sentiment analysis, search relevance).

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.”