This year I focused my community activity on AI / Machine Learning by doing a series of talks. Thank you to everyone that attended and made them so successful! Please join me for my final public talk of the year, a full day workshop on Neural networks. RSVP HERE
1 – An Introduction to Artificial Neural Networks
This talk will cover the technologies used to create Neural Networks and give an introduction to the basics of why they work, the different types, and how they are being applied to today’s business problems. The topics covered include:
• Artificial Neural Networks
• Convolutional Neural Networks
• Self Organizing Maps
• Recurrent Neural Networks
You’ll leave with an understanding of Neural Network terminology and basic concepts, and understand how these neural networks can be applied to real-world problems.
2 – Azure Batch AI for Neural Networks
This talk will cover how to use the GPU power of Azure to train a Neural Network and how to turn that Neural Network into a REST service hosted in Azure. The topics covered include:
• A brief overview of Neural Networks
• Azure Batch AI
• Azure Data Science Virtual Machines
• Python in Azure Web Apps
You’ll leave with an understanding of how to use Azure to train and host your neural networks.
3 – Fundamentals of Neural Network Workshop
This workshop will use Python, CNTK, and Keras to build your first Neural Network, train it, and use it to make predictions. This workshop requires a computer running Windows and is focused on hands-on laboratory work. The topics covered in this course include:
- Introduction to Neural Networks
- The science of Neural Networks
- Stochastic Gradient Descent
- Neural Network Design
- Activation Functions
- Testing and Avoiding Overfitting
- Setting up your system for Neural Network Development
- How to predict with your neural network as a REST service
- Neural Networks in the cloud
You’ll leave with an understanding of Neural Network terminology and techniques, by creating and training a Neural Network during this workshop.
(by end of 2018)
Total Times Delivered Part 1 – 10
Total Times Delivered Part 2 – 5
Total Times Delivered Part 3 – 4
Total Conferences – 5
Total User Groups – 4
Each time I have a public speaking engagement, I make mistakes and learn something new to improve things, and this year was no exception:
- Real Tangible demos are an attention grabber, but Interactive demos with the audience are a show stopper.
- Doing a lab that involves installation with lots of dependencies is never going to go well, no matter how much I prepare!
- Scrub your source for passwords/keys before placing it somewhere publically.
- Doing a speaking series with different target audiences makes cross promotion hard.
- With a topic as complex as machine learning there will ALWAYS be someone in the audience that knows more about parts of your talk than you do, and that’s ok.
- Doing a workshop where over 90% succeed is incredibly rewarding.
- That 10 % that fail (usually due to equipment or install problems) is painful, especially when they invested 5-8 hours with you.
- The more interactive the audience is; the more fun I have as a speaker.
- Doing the same talk over and over eventually gets old.
This has been a great series of talks that has allowed me to meet many great people in our community. I’m super excited about Machine Learning and the Azure Offerings associated with them, which has truly democratized AI. Look for more talks next year on Machine Learning, Azure, and Software Architecture. Thank you again to everyone that has participated in these sessions. Have a great holiday season!