Publication
] Why Are Face and Object Processing Segregated in the Human Brain? Testing Computational Hypotheses with Deep Convolutional Neural Networks . Conference on Cognitive Computational Neuroscience (2020).
Why does deep and cheap learning work so well?. Journal of Statistical Physics 168, 1223–1247 (2017).
1608.08225.pdf (2.14 MB)
1608.08225.pdf (2.14 MB) Word-level Invariant Representations From Acoustic Waveforms. INTERSPEECH 2014 - 15th Annual Conf. of the International Speech Communication Association (International Speech Communication Association (ISCA), 2014). at <http://www.isca-speech.org/archive/interspeech_2014/i14_2385.html>
Mechanisms of Sensory Working Memory: Attention and Performance XXV. (Elsevier Inc. , 2015). at <https://www.sciencedirect.com/book/9780128013717/mechanisms-of-sensory-working-memory>
Write, Execute, Assess: Program Synthesis with a REPL. Neural Information Processing Systems (NeurIPS 2019) (2019). 9116-write-execute-assess-program-synthesis-with-a-repl.pdf (3.9 MB)
9116-write-execute-assess-program-synthesis-with-a-repl.pdf (3.9 MB) XDream: Finding preferred stimuli for visual neurons using generative networks and gradient-free optimization. PLOS Computational Biology 16, e1007973 (2020). gk7791.pdf (2.39 MB)
gk7791.pdf (2.39 MB) Young children’s automatic and alternating use of scene and object information in spatial symbols. Budapest CEU Conference on Cognitive Development (2015).
Young Children’s Use of Surface and Object Information in Drawings of Everyday Scenes. Child Development (2016). doi:10.1111/cdev.12658
Zero-shot linear combinations of grounded social interactions with Linear Social MDPs. Proceedings of the 37th AAAI Conference on Artificial Intelligence (AAAI) (2023).