The South African Centre for Artificial Intelligence Research (CAIR) kindly invites you to a public lecture by Adnan Darwiche from the University of California on Reasoning about the behavior of AI systems.
The lecture will take place on Monday, 9 December 2019 at 18:00 in Snape TS3B, Snape Building, University of Cape Town, Upper Campus.
I will discuss the compilation of some common machine learning systems into symbolic and tractable representations that precisely capture their input-output behavior. This includes classifiers based on neural networks, Bayesian networks and random forests. I will show how the compiled symbolic representations can be used to explain and verify system behavior, including bias, in addition to quantifying system robustness. I will also discuss a new class of tractable, machine learning models: Testing Arithmetic Circuits (TACs), which are as expressive as neural networks. The structure of TACs can be synthesized from domain knowledge and their parameters can be learned from labeled data using gradient descent. However, one can reason about the behavior of TACs and provide some guarantees that are invariant to how TACs are trained from labeled data.