The Center for Brains, Minds and Machines is well-represented at the thirty-third Conference on Neural Information Processing Systems (NeurIPS 2019).
Below, you will find listings to papers/proceedings accepted and accompanying coverage:
J. Feather, Durango, A., Gonzalez, R., and McDermott, J. H., NeurIPS 2019. Vancouver, Canada, 2019.
- [video] Metamers of neural networks reveal divergence from human perceptual systems
- [article] Differences between deep neural networks and human perception [MIT News]
, 33rd Conference on Neural Information Processing Systems (NeurIPS 2019). Vancouver, Canada, 2019. (* indicates equal contribution)
- [article] Helping machines perceive some laws of physics [MIT News]
- [supplementary webpage] http://physadept.csail.mit.edu/
- [video] https://www.youtube.com/watch?v=95HlF9nCca4
- [video] Brain-Like Object Recognition with High-Performing Shallow Recurrent ANNs
- [supplemental materials] github.com/dicarlolab/neurips2019 | github.com/dicarlolab/cornet | brain-score.org
"Finding Friend and Foe in Multi-Agent Games"
Jack Serrino (MIT) · Max Kleiman-Weiner (Harvard/MIT) · David Parkes (Harvard University) · Josh Tenenbaum (MIT)
- [article] Bot can beat humans in multiplayer hidden-role games
- [article] Friend or Foe?
- [video] Finding Friend and Foe in Multi-Agent Games
"Write, Execute, Assess: Program Synthesis with a REPL"
Kevin Ellis (MIT) · Maxwell Nye (MIT) · Yewen Pu (MIT) · Felix Sosa (Harvard and Center for Brains, Minds, and Machines) · Josh Tenenbaum (MIT) · Armando Solar-Lezama (MIT)
"Visual Concept-Metaconcept Learning"
Chi Han (Tsinghua University) · Jiayuan Mao (MIT) · Chuang Gan (MIT-IBM Watson AI Lab) · Josh Tenenbaum (MIT) · Jiajun Wu (MIT)
"ObjectNet: A large-scale bias-controlled dataset for pushing the limits of object recognition models"
Andrei Barbu (MIT) · David Mayo (MIT) · Julian Alverio (MIT) · William Luo (MIT) · Christopher Wang (Massachusetts Institute of Technology) · Dan Gutfreund (IBM Research) · Josh Tenenbaum (MIT) · Boris Katz (MIT)
- [article] This object-recognition dataset stumped the world’s best computer vision models
- [article] MIT and IBM's ObjectNet shows that AI struggles at object detection in the real world
- [supplemental website] https://objectnet.dev/
"Untangling in Invariant Speech Recognition"
Cory Stephenson (Intel) · Jenelle Feather (MIT) · Suchismita Padhy (Intel AI Lab) · Oguz Elibol (Intel AI Lab) · Hanlin Tang (Intel AI Products Group) · Josh McDermott (Massachusetts Institute of Technology) · SueYeon Chung (Columbia/MIT)
"Implicit Regularization of Accelerated Methods in Hilbert Spaces"
Nicolò Pagliana (Università degli studi di Genova (DIMA)) · Lorenzo Rosasco (University of Genova- MIT - IIT)
"Beating SGD Saturation with Tail-Averaging and Minibatching"
Nicole Muecke (University of Stuttgart) · Gergely Neu (Universitat Pompeu Fabra) · Lorenzo Rosasco (University of Genova- MIT - IIT)
Shared Visual Representations in Human & Machine Intelligence
2019 NeurIPS Workshop @ Vancouver Convention Center. Vancouver, Canada
The SVRHM workshop at NeurIPS was an epic success! Thanks a lot to CBMM's team for the support!
- Session 1: https://slideslive.com/38921934/shared-visual-representations-in-human-and-machine-intelligence-1
- Session 2: https://slideslive.com/38921936/shared-visual-representations-in-human-and-machine-intelligence-2
- Session 3: https://slideslive.com/38921937/shared-visual-representations-in-human-and-machine-intelligence-3