Online event: Getting Started with Interpretable and Fair AI

Hi everyone!!! We're baaaack! Hope everyone stayed safe and healthy during Covid. Much like the rest of the world, our meetup has moved to zoom. Hope you can join us on Wednesday, 8/19/2020 at 12:00 PM PST for an hour session with Dr. Adnan Masood. He's not only a distinguished speaker but also one of the organizers for Irvine Programming Meetup.

Zoom Link:
https://us02web.zoom.us/j/82933578176?pwd=UlJzcmRiMHBKcy9OdU8zaDBoaG91Zz09
Passcode: 477920

Getting Started with Interpretable and Fair AI

AI is ubiquitous in modern day systems while our ability to build fair, interpretable, and responsible ML models is still in its early stages. Most real datasets have hidden biases. Being able to detect the impact of the bias in the data on the model, and then to repair the model, is critical if we are going to deploy machine learning in applications that affect people’s health, welfare, and social opportunities.

In this talk, Dr. Adnan Masood will discuss what it means to develop AI in a transparent way. We will discuss different types of biases in the datasets, and what can do to mitigate these using algorithms, and tools like AIF 360, WhatIf, and Microsoft's InterpretableML and FairLearn. These toolkits are open source, and provides developers and data scientists with capabilities to assess the fairness of their machine learning models and mitigate unfairness. The aaudience will be introduced to interpretability toolkits which enable you to use different state-of-the-art interpretability methods to explain your models decisions. We will walk through the machine learning development lifecycle, and explain how during the training phase of the AI development cycle, you can use interpretability output of a model to verify hypotheses and build trust with stakeholders. The talk also uses jupyter notebooks and FairLearn to demonstrate how you can also use the insights for debugging, validating model behavior, and to check for bias.

About the Speaker: Dr. Adnan Masood is the UST-Global's Chief Architect for AI and Machine Learning. In his role, he is responsible for the firm’s overall strategy for cognitive computing, AI, machine learning, and academic relationships. Adnan is a seasoned researcher, engineer, author, and thought leader with over 20 years of global experience in financial technology, and developing large scale systems. He is recognized as Microsoft Regional Director, and MVP (Most Valuable Professional) for Artificial Intelligence by Microsoft for his outstanding contributions in the field. Dr. Masood collaborates with Stanford Artificial Intelligence Lab, MIT CSAIL, and lead a team of data scientists and engineers building artificial intelligence solutions to produce business value and insights that affect a range of businesses, products, and initiatives.

Zoom Link:
https://us02web.zoom.us/j/82933578176?pwd=UlJzcmRiMHBKcy9OdU8zaDBoaG91Zz09

Passcode: 477920