D.r Aaron Nielsen will be speaking on a fast (aka auto) way to take a differentiation. In Machine Learning and AI, the gradient descent is a standard technique used during the training phase of a neural network. However gradient descent requires computing the derivative of a potentially complicated function at every step during the training process. Computing the form of the derivative of the function can be tricky and error prone, but a technique called auto-differentiation allows for the derivative to be computed automatically without know the functional form of the derivative. Auto-differentiation uses a class of number known as dual-numbers to compute these derivatives automatically. This talk will discuss dual-numbers and their special properties and then walk thru how these properties allow for auto-differentiation. A simple gradient descent example will be presented using auto-differentiation and some python packages which perform auto-differentiation will be presented.
The Gem City Machine Learning (ML) group is part of the GemCity TECH family of user communities in Dayton OH.
Each month we meet at the Innovation Hub located in the newly renovated Downtown Dayton Arcade.
We meet to explore the exciting and growing field of Machine Learning (ML) and Artificial Intelligence (AI).
We regularly meet on the third Thursday of the month. You can find our next event on the GemCity TECH Meetup events calendar.
Would you like to discover more about machine learning or artificial intelligence?
Are you interested in being part of a community who are also interested in exploring the field of machine learning?
Do you work in the field of machine learning and would like to share your knowledge and experience?
Our goal is to have a space where people can present and learn new ML/AI ideas, ask for help on problems they are working on, and meet new people.
We have short talks about machine learning (ML) and how to get into this field.
The format is:
Social: ~ 30 min
Lecture: ~ 1 hour
Social: ~ 30 min