ICAART 2022 Highlights HMC CS Research
January 14, 2022Share story
Two papers authored by computer scientists from 无忧视频 Professor George Monta帽ez鈥檚 AMISTAD Lab have been accepted to the 14th International Conference on Agents and Artificial Intelligence (ICAART 2022), Feb. 3鈥�5. Both papers were accepted as聽full papers聽for聽oral presentation聽in the main聽conference track.
鈥淔or previous iterations of ICAART, the full paper acceptance rate has been less than 20%,鈥� says Monta帽ez, 鈥渟o getting a full paper in that track is an accomplishment. The selection for oral presentation is an additional honor.鈥�
鈥淰ectorization of Bias in Machine Learning Algorithms鈥� by Sophie Bekerman 鈥�24, Eric Chen 鈥�24 and Lily Lin (Biola University) concerns estimation of inductive orientation vectors, which have, until now, been a strictly theoretical quantity used for proving various bounds on algorithm performance. 鈥淭his work presents methods for estimating these vectors from data, allowing us to cluster and compare black-box classification algorithms based on their output behavior alone,鈥� Monta帽ez says. 鈥淪ince the vectors reflect underlying assumptions and biases in the algorithms, it allows us to find similarities in the inductive biases of algorithms without knowing anything about their internal structure.鈥�
鈥淭he Gopher Grounds: Testing the Link Between Structure and Function in Simple Machines鈥� by Anshul Kamath 鈥�23, Nick Grisanti 鈥�23, Sadie Zhao 鈥�23 (Pomona College) and Monta帽ez builds off a 2021 paper (鈥淭he Gopher鈥檚 Gambit: Survival Advantages of Artifact-Based Intention Perception鈥� by Monta帽ez, Cynthia Hom 鈥�23, Amani Maina-Kilaas 鈥�23, Kevin Ginta 鈥�21 [Biola University] and Cindy Lay 鈥�22 [Claremont McKenna College]) on intention-perception in traps for artificial gophers. 鈥淚n this new paper, we test and challenge some of the assumptions in the original paper (such as whether coherence is strongly or only weakly correlated with functionality) and see if producing traps using genetic algorithms changes the properties of the produced traps in terms of their coherence and functionality,鈥� says Monta帽ez. This paper is part of a larger body of work that includes a third paper still in development, looking specifically at applying the hypothesis tests from the Hom et al. paper to the genetic-algorithm produced traps.