Noga Zaslavsky
Cited by
Cited by
Deep learning and the information bottleneck principle
N Tishby, N Zaslavsky
2015 IEEE Information Theory Workshop (ITW), 1-5, 2015
Efficient compression in color naming and its evolution
N Zaslavsky, C Kemp, T Regier, N Tishby
Proceedings of the National Academy of Sciences 115 (31), 7937-7942, 2018
Color Naming Reflects Both Perceptual Structure and Communicative Need
N Zaslavsky, C Kemp, N Tishby, T Regier
Topics in Cognitive Science 11 (1), 207-219, 2019
Communicative need in colour naming
N Zaslavsky, C Kemp, N Tishby, T Regier
Cognitive Neuropsychology, 1-13, 2019
Semantic categories of artifacts and animals reflect efficient coding
N Zaslavsky, T Regier, N Tishby, C Kemp
41st Annual Meeting of the Cognitive Science Society, 2019
Let's talk (efficiently) about us: Person systems achieve near-optimal compression
N Zaslavsky, M Maldonado, J Culbertson
CogSci 2021, 2021
Cloze Distillation: Improving Neural Language Models with Human Next-Word Prediction
T Eisape, N Zaslavsky, R Levy
Proceedings of the 24th Conference on Computational Natural Language …, 2020
A Rate-Distortion view of human pragmatic reasoning
N Zaslavsky, J Hu, RP Levy
Proceedings of the Society for Computation in Linguistics, 2020
Efficient encoding of motion is mediated by gap junctions in the fly visual system
S Wang, A Borst, N Zaslavsky, N Tishby, I Segev
PLoS Computational Biology 13 (12), e1005846, 2017
Beyond linear regression: mapping models in cognitive neuroscience should align with research goals
AA Ivanova, M Schrimpf, S Anzellotti, N Zaslavsky, E Fedorenko, L Isik
Neurons, Behavior, Data analysis, and Theory (NBDT), 2022
The forms and meanings of grammatical markers support efficient communication
F Mollica, G Bacon, N Zaslavsky, Y Xu, T Regier, C Kemp
Proceedings of the National Academy of Sciences 118 (49), 2021
Efficient human-like semantic representations via the Information Bottleneck principle
N Zaslavsky, C Kemp, T Regier, N Tishby
NeuIPS 2017 Cognitively Informed AI workshop, 2017
Information-Theoretic Principles in the Evolution of Semantic Systems
N Zaslavsky
Ph.D. Thesis, The Hebrew University of Jerusalem, 2020
The evolution of color naming reflects pressure for efficiency: Evidence from the recent past
N Zaslavsky, K Garvin, C Kemp, N Tishby, T Regier
Journal of Language Evolution, 2022
Probing artificial neural networks: insights from neuroscience
AA Ivanova, J Hewitt, N Zaslavsky
ICLR 2021 Brain2AI Workshop, 2021
Scalable pragmatic communication via self-supervision
J Hu, R Levy, N Zaslavsky
ICML 2021 Workshop on Self-Supervised Learning for Reasoning and Perception, 2021
Toward human-like object naming in artificial neural systems
TN Eisape, R Levy, JB Tenenbaum, N Zaslavsky
ICLR 2020 Bridging AI and Cognitive Science workshop, 2020
Towards Human-Agent Communication via the Information Bottleneck Principle
M Tucker, J Shah, R Levy, N Zaslavsky
RSS Workshop on Social Intelligence in Humans and Robots, 2022
Deterministic annealing and the evolution of optimal information bottleneck representations
N Zaslavsky, N Tishby
Technical Report, 2019
Artificial neural network language models align neurally and behaviorally with humans even after a developmentally realistic amount of training
EA Hosseini, MA Schrimpf, Y Zhang, S Bowman, N Zaslavsky, ...
bioRxiv, 2022
The system can't perform the operation now. Try again later.
Articles 1–20