Emin Orhan

CV | Research blog | GitHub | Google Scholar

Research

I am, in general, interested in understanding how intelligent behavior (broadly defined) emerges from brain-like computational architectures. I use ideas and tools from deep learning and computational neuroscience to address this question.

Papers

Orhan AE, Pitkow X (submitted) Improved memory in recurrent neural networks with non-normal dynamics.

Orhan AE, Ma WJ (2019) A diverse range of factors affect the nature of neural representations underlying short-term memory. Nature Neuroscience, 22, 275–283. [video] [bioRxiv:244707]

Orhan AE, Pitkow X (2018) Degeneracy, trainability, and generalization in deep neural networks. NIPS 2018 Workshop on Integration of Deep Learning Theories

Orhan AE (2018) A simple cache model for image recognition. NIPS 2018 [arxiv:1805.08709]

Orhan AE, Pitkow X (2018) Skip connections eliminate singularities. ICLR 2018 [arXiv:1701.09175]

Orhan AE, Ma WJ (2017) Efficient probabilistic inference in generic neural networks trained with non-probabilistic feedback. Nature Communications, 8, 138. [arXiv:1601.03060]

Orhan AE, Ma WJ (2015) Neural population coding of multiple stimuli. Journal of Neuroscience, 35(9), 3825-41. [arXiv:1410.1093]

Orhan AE, Jacobs RA (2014) Are performance limitations in visual short-term memory tasks due to capacity limitations or model mismatch? arXiv:1407.0644

Orhan AE, Jacobs RA (2014) Toward ecologically realistic theories in visual short-term memory research. Attention, Perception, & Psychophysics, 76, 2158-70.

Orhan* AE, Sims* CR, Jacobs RA, Knill DC (2014) The adaptive nature of visual working memory. Current Directions in Psychological Science, 23(3), 164-70. (*equal contribution)

Orhan AE, Jacobs RA (2013) A probabilistic clustering theory of the organization of visual short-term memory. Psychological Review, 120(2), 297-328.

Orhan AE, Jacobs RA (2011) Probabilistic modeling of dependencies among visual short-term memory representations. NIPS 2011.

Orhan AE, Michel MM, Jacobs RA (2010) Visual learning with reliable and unreliable features. Journal of Vision, 10(2):2, 1-15.

Notes

Here are some notes I have written over the years:

Cover's function counting theorem | Dirichlet processes | Helmholtz machine | Hopfield model | leaky integrate-and-fire neuron | linear dynamics in Schur modes | locally linear embedding | Isomap algorithm | particle filtering.

Please send me an e-mail if you find any typos, errors, inaccuracies or grave omissions in these notes.

Links

What I've been reading recently (non-fiction):

The Fabric of Reality, David Deutsch

The Emperor's New Mind, Roger Penrose

Quantum Mechanics and Experience, David Albert

The Interpretation of Quantum Mechanics, Roland Omnes


Some podcasts I like to follow:

In Our Time (BBC 4 Radio)

Ideas (CBC Radio)

BBC Inside Science (BBC 4 Radio)

Sean Carroll's Mindscape

Brain Inspired

Nature podcast

Quanta Magazine podcast