by Katharina Dost | Jul 29, 2021 | AI Reading Group, News
Where and when: Thursday, Aug 5 at 2-3pm in 303S-561 Abstract A longstanding question in cognitive science concerns the learning mechanisms underlying compositionality in human cognition. Humans can infer the structured relationships (e.g., grammatical rules) implicit...
by Katharina Dost | Jul 15, 2021 | AI Reading Group, News
Where and when: Thursday, July 22 at 2-3pm in 303S-561 Abstract In this paper, we present a new approach to time series forecasting. Time series data are prevalent in many scientific and engineering disciplines. Time series forecasting is a crucial task in modeling...
by Katharina Dost | Jul 1, 2021 | AI Reading Group, News
Where and when: Thursday, July 8 at 2-3pm in 303S-561 Abstract In computational material design, ionic radius is one of the most important physical parameters used to predict material properties. Motivated by the progress in computational materials science and...
by Katharina Dost | Jun 17, 2021 | AI Reading Group, News
Where and when: Thursday, June 24 at 2-3pm in 303S-561 Abstract This paper introduces SuperGlue, a neural network that matches two sets of local features by jointly finding correspondences and rejecting non-matchable points. Assignments are estimated by solving a...
by Katharina Dost | May 28, 2021 | Adversarial Learning, AI Reading Group, News
Where and when: Thursday, June 10 at 2-3pm in 303S-561 Transferability captures the ability of an attack against a machine-learning model to be effective against a different, potentially unknown, model. Empirical evidence for transferability has been shown in previous...
by Katharina Dost | May 10, 2021 | AI Reading Group, News
Saliency methods are widely used to interpret neural network predictions, but different variants of saliency methods often disagree even on the interpretations of the same prediction made by the same model. In these cases, how do we identify when are these...
