Interactive Structure Learning with Structural Query-by-Committee
Christopher Tosh, Sanjoy Dasgupta
Neural Information Processing Systems http://nips.cc/
MarginGAN: Adversarial Training in Semi-Supervised Learning
The newfeature isthattheclassifier attempts toincrease themarginofrealexamples and to decrease the margin of fake examples.
Flexible information routing in neural populations through stochastic comodulation
Caroline Haimerl, Cristina Savin, Eero Simoncelli
Humans and animals are capable of flexibly switching between a multitude of tasks,eachrequiringrapid,sensory-informed decisionmaking. Incomingstimuli are processed by ahierarchyof neural circuits consisting of millions of neurons withdiversefeatureselectivity.
Learning Plannable Representations with Causal InfoGAN
Thanard Kurutach, Aviv Tamar, Ge Yang, Stuart J. Russell, Pieter Abbeel
Asanexample,consider designing a logical representation for the state of a deformable object such as a rope.
Diff-eRank: ANovelRank-BasedMetricfor EvaluatingLargeLanguageModels
In this paper, we introduce a novel rank-based metric,Diff-eRank, grounded in information theory and geometry principles.
d6797a91df19b768409b5178642dcb26-Paper-Conference.pdf
First, each place cell has localized spatial coding which fires inrestricted regions ofa givenenvironment (placefields)[7,8].
Answerer in Questioner's Mind: Information Theoretic Approach to Goal-Oriented Visual Dialog
Sang-Woo Lee, Yu-Jung Heo, Byoung-Tak Zhang
Neural Information Processing Systems http://nips.cc/