Deep Learning in Practice: A Hands-On Introduction
Important note: Each workshop participant is required to bring their own laptop.
Intended Audience: Anyone who wishes to learn how to create deep learning systems using PyTorch, TensorFlow, Keras, and other popular software libraries.
Knowledge Level: Basic knowledge of machine learning terminology. Minimal programming experience with a C-family language such as Python, C/C++, C# or Java is recommended but not required.
Workshop Description
This one-day introductory workshop dives deep. You will explore deep neural classification, LSTM time series analysis, convolutional image classification, advanced data clustering, bandit algorithms, and reinforcement learning. It’s a hands-on class; you’ll learn to implement and understand both deep neural networks as well as unsupervised techniques using PyTorch, TensorFlow, Keras, and Python. Just as importantly, you’ll learn exactly what types of problems are appropriate for deep learning techniques, and what types of problems are not well suited to deep learning.
The instructors, Prerna and Bardia, take part in applying cutting-edge Large Language Models and other custom models to address various industries’ needs. They will be sharing case studies and examples from their experience during the workshop. Workshop participants will access much of the same state-of-the-art training material used for this work at Microsoft. Along the way, James will cover case studies detailing large-scale deployments for their internal clients that have generated astounding ROIs.
During the day, workshop attendees will gain the following practical hands-on experience:
- How to prepare, normalize, and encode data for deep learning systems.
- How to install deep learning libraries including TensorFlow, Keras, and PyTorch, and the pros and cons of each library.
- How to create deep learning predictive systems for various kinds of data: classical business data, time series data (such as sales data), image data (such as the famous MNIST dataset for handwriting recognition), and text/document data (such as legal contracts). These datasets are a great place to start – however, for the more experienced attendee, even more challenging, “next level” datasets, such as for object recognition, will be optionally available.
This workshop assumes you have a basic knowledge of machine learning terminology but does not assume you are a machine learning expert. Some theory will be presented but only enough to help you understand how to make a practical, working deep learning system. This is a code-based workshop, so some programming experience will be helpful. However, beginners will be able to follow along but may have to work a bit harder to keep up.
Hardware: Bring Your Own Laptop
Important note: Each workshop participant is required to bring their own laptop.
You are encouraged to bring a Windows 10 or 11 laptop if you have one available, but a Mac laptop will work as well.
Details regarding laptop options as well as pre-install instructions for both platforms will be updated closer to the event, since the new, forthcoming PyTorch 2.0, coming out spring 2023, will be utilized — but for now, you can access last year’s details here.
Assistants will also be on hand to help attendees with hardware/software issues.
Attendees receive an electronic copy of the course materials and related code at the conclusion of the workshop.
Schedule
- Workshop starts at 8:30am
- Morning Coffee Break at 10:30am – 11:00am
- Lunch at 12:30pm – 1:15pm
- Afternoon Coffee Break at 3:00pm – 3:30pm
- End of the Workshop: 4:30pm
Instructors:
Bardia Beigi, Applied Scientist II, Microsoft
Bardia Beigi works at Microsoft as an Applied Scientist II in the Industry AI group delivering AI/ML based solutions to various industries within Azure. Bardia has a master’s degree in Computer Science from Stanford University, as well as Bachelor of Applied Science in Engineering Physics from the University of British Columbia. In his spare time, Bardia enjoys traveling, trying out new dessert spots, and learning new life hacks.
Prerna Singh, Applied Scientist II, Microsoft
Prerna Singh is currently working as an Applied Scientist II in the Industry AI group @Microsoft where she develops machine learning-based solutions for different industrial verticals including finance and sustainability. Before joining Microsoft, she obtained her master’s degree in Electrical and Computer Engineering with a concentration on Machine Learning from Carnegie Mellon University (CMU). Prerna is passionate about machine learning, NLP and deep Reinforcement Learning. Besides work, Prerna enjoys traveling, Zumba and hiking in her free time.