Schedule

SVRHM 2019 will be held on December 13, 2019 at the Vancouver Convention Center @ West Level 2 Room 220-222 in Vancouver, Canada. 
The Video Recordings of all talks are available here: https://slideslive.com/neurips/west-220-222-shared-visual-representations-in-human-and-machine-intelligence

08.50 - 09.00: Opening Remarks

Session 1

  • 09:00 - 09:25: Olivier Henaff (DeepMind) | Predictable representations in humans and machines
  • 09:25 - 09:50: Irina Higgins (DeepMind) | What is disentangling and does intelligence need it?

09.50 - 10.10: Coffee Break.

Session 2

  • 10.10 - 10.35: Will Xiao (Harvard) | A "distribution mismatch" dataset for comparing representational similarity in ANNs and the brain
  • 10.35 - 11.00: Bill Freeman (MIT) | Feathers, wings, and the future of computer vision research
  • 11.00 - 11.25: Erin Grant (UC Berkeley) | Taxonomic structure in learning from few positive examples
  • 11.25 - 11.50: Ruairidh Battleday (Princeton) | CIFAR-10H: using human-derived soft-label distributions to support more robust and generalizable classification
  • 11.50 - 12.15: Andrei Barbu (MIT) | Making the next generation of machine learning datasets: ObjectNet a new object recognition benchmark
  • 12.15 - 12.40: Mike Tarr (CMU) | The building blocks of vision

12.40 - 02.00: Lunch on your own

02.00 - 03.00: Poster Session

Session 3

03.00 - 03.30: Q&A from the Audience. Ask the Grad Students: Cross-disciplinary research experiences and tips for Graduate School Admissions Panelists:

  • Erin Grant (UC Berkeley)
  • Nadine Chang (CMU)
  • Ruairidh Battleday (Princeton)
  • Sophia Sanborn (UC Berkeley)
  • Nikhil Parthasarathy (NYU)
  • 3.30 - 3.55: Talia Konkle (Harvard) | Object representation in the human visual system
  • 3.55 - 4.20: Nikolaus Kriegeskorte (Columbia) | Cognitive computational neuroscience of vision
  • 4.20 - 4.45: Matthias Bethge (Universität Tübingen) | Perturbation-based remodeling of visual neural network representations
  • 4.45 - 5.10: Eero Simoncelli (NYU) | Local gain control and perceptual invariances

5.10 - 6.00: Panel Discussion: What sorts of cognitive or biological (architectural) inductive biases will be crucial for developing effective artificial intelligence? Panelists: Irina Higgins, Talia Konkle, Nikolaus Kriegeskorte, Matthias Bethge.

6.00 - 6.10: Concluding Remarks, Best Paper Award Prize (NVIDIA Titan RTX) Ceremony and Best Poster Award Prize Ceremony (Oculus Quest).

6.10 - 7.00: Evening Reception sponsored by MIT Quest for Intelligence.