[Defense] Teaching AI鈥檚 to reason and code, confidentially
Friday, April 26, 2024
3:00 pm - 4:00 pm
In
Partial
Fulfillment
of
the
Requirements
for
the
Degree
of
Doctor
of
Philosophy
Rabimba
Karanjai
will
defend
his
proposal
Teaching
AI鈥檚
to
reason
and
code,
confidentially
Abstract
The proliferation of AI models capable of generating code and making complex decisions necessitates a research focus on imbuing these models with robust reasoning capabilities while upholding stringent privacy standards. This research proposal explores novel methods for training AI agents to reason effectively, generate code accurately, and operate within confidential environments. By investigating system problems like decentralized computation, secure computation, smart contracts as well as their generation with security guarantees, this research aims to develop AI systems that can learn and make informed decisions without compromising sensitive data. The outcomes of this research have the potential to significantly impact various domains, including healthcare, finance, and autonomous systems, where AI-driven decision-making and code generation play critical roles.
Friday,
April
26,
2024
11:00
AM
-
12:00
PM
CT
PGH 550
Dr. Weidong (Larry) Shi, proposal advisor
Faculty, students, and the general public are invited.
