Mustafa KabulIlknur Kaynar-Kabul

Sponsored by

SAS

Implementing AI systems with interpretability, transparency, and trust

Thursday, January 25, 2018
10:00am PT | Show Timezones...


Add to Calendar 01/25/2018 10:00 01/25/2018 11:00 America/Los_Angeles Webcast: Implementing AI systems with interpretability, transparency, and trust Online Go to the webcast O'Reilly Media webcast@oreilly.com MM/DD/YYYY

Presented by: Mustafa Kabul, Ilknur Kaynar-Kabul

Duration: Approximately 60 minutes.

Cost: Free

Questions? Please send email to




Interact with experts online, for free.

Sign in to Register

Description:

This webcast will focus on different machine learning and visualization techniques that can be used to make complex artificial intelligence systems interpretable, transparent and trustable. We will show how these techniques can be used in the AI life cycle, specifically in pre-modelling, modeling and post-modelling stages.

Machine learning models have been used successfully in areas such as object recognition, speech perception, language modeling and automated decision optimization leveraging reinforcement learning. However, increasingly complicated nonlinear models and heavily engineered features limit transparency, slowing adoption of machine learning models in application areas where critical decisions are made. Data scientists who understand the workings of complex models, their limitations, and the reasons for individual predictions are able to use predictive models more effectively.

The goal of this webcast is to provide you with actionable takeaways regarding:

  • Techniques for understanding and interpreting your dataset with a critical eye
  • Insights about inner workings of deep neural networks
  • Methods to interpret predictions given by a black box model
  • Interpretability from the perspective of a model consumer

Speakers

Ilknur Kaynar-Kabul, Senior Manager of Advanced Analytics at SAS

Ilknur is a Senior Manager in the SAS Advanced Analytics division, where she leads the SAS R&D team that focuses on machine learning algorithms and applications. The team is responsible for researching and implementing new data mining and machine learning algorithms that can solve complex big data problems in the high-performance analytics environment. She likes working at the interface of computer science, statistics and optimization. Her research interests include model interpretability, transfer learning, clustering and feature engineering. Prior to joining SAS, Kaynar-Kabul worked on medical image analysis and visualization techniques at University of North Carolina at Chapel Hill and Kitware. She holds multiple patents in automated market segmentation using clustering and deep neural networks. She has a PhD in Computer Science from UNC Chapel Hill.

Mustafa Kabul, Senior Data Scientist at SAS

Mustafa is an Operations Research expert who is working at the interface of machine learning and optimization. He works as a Data Scientist in Analytic Server Division of SAS R&D and leads innovative projects for SAS’s next generation AI Enabled Analytics products including applications of Deep Learning. His current focus is on applying Deep Reinforcement Learning to operational problems in CRM and IoT space. During his PhD he worked on game theory models of supply chains selling to strategic customers. Earlier in his career at SAS he developed distributed large scale integer optimization algorithms for Marketing Optimization problems. As an optimization enthusiast he always looks into ways to improve the algorithms. Nowadays his favorites are the Distributed Stochastic Gradient and Online Learning methods.