Jascha Sohl-Dickstein

I am a graduate student in the Redwood Center for Theoretical Neuroscience, at University of California, Berkeley. I am a member of Bruno Olshausen's lab, and the Biophysics Graduate Group. My email address is jascha@berkeley.edu.

I am interested in how we learn to perceive the world. There is evidence that much of our representation of the world is learned during development rather than being pre-programmed - everything from the way light intensity is correlated on adjacent patches of the retina, all the way up to the behavior (and existence!) of objects. We seem to infer most of human scale physics from examples of sensory input.

How this unsupervised learning problem is solved - how we learn the structure inherent in the world just by experiencing examples of it - is not well understood. This is the problem I am interested in tackling.

There are two large (known) parts to this problem. The first is the design of models which are flexible enough to describe *anything* without being unwieldy (greater flexibility frequently comes at the cost of an explosion in the number of parameters and/or computationally costly implementation). The second is training these models once they've been designed (almost any model you can write down is impractical to exactly evaluate - a factor called the "partition function", coming from the constraint that the probabilities of all states must sum to 1, is intractable to compute. This inability to exactly evaluate the model makes training exceedingly difficult.). I am attempting to work on both parts of this problem, though I've had more success so far with the second.

Current projects

I am working with Peter Battaglino and Michael DeWeese on a technique for parameter estimation in probabilistic models with intractable partition functions, involving minimization of probability flows. See the arXiv pre/e-print.

I am working with Jimmy Wang and Bruno Olshausen to build a Lie algebraic model of the transformations which occur in natural video. See a poster pdf, or Jimmy's web page.

I am working on my own to build probabilistic models out of unstructured recurrent neural networks, and train them on natural stimuli. Nothing to show here yet...

Relevant publications

J Sohl-Dickstein, P Battaglino, M DeWeese. Minimum probability flow learning. (2009) http://arxiv.org/abs/0906.4779

C Abbey, J Sohl-Dickstein, B Olshausen. Higher-order scene statistics of breast images. Proceedings of SPIE (2009) http://link.aip.org/link/?PSISDG/7263/726317/1

POSTER - J Sohl-Dickstein, B Olshausen. Learning in energy based models via score matching. Cosyne (2007) - this (dense!) poster introduces a spatial derivation of score matching, applies it to learning in a Field of Experts model, and then extends Field of Experts to work with heterogeneous experts (to form a "tapestry of experts"). download poster

POSTER - J Wang, J Sohl-Dickstein, B Olshausen. Unsupervised learning of Lie group operators from natural movies. Bay Area Vision Research Day (2009). download poster

Notes and work in progress

Entropy of Generic Distributions - Calculates the entropy that can be expected for a distribution drawn at random from the simplex of all possible distributions

The following are titles for informal notes I intend to write, but haven't gotten to/finished yet. If any of the following sound interesting to you, pester me and they will appear more quickly.

• Natural gradients made quick and dirty
• A log bound on the growth of intelligence with system size
• The field of experts model learns Gabor-like receptive fields when trained via score matching
• For small time bins, generalized linear models and causal Boltzmann machines become equivalent
• How to construct volume preserving recurrent networks
• Maximum likelihood learning as constraint satisfaction
• A spatial derivation of score matching

Interests

If you know anything about the following, I would love to pick your brain:

• non-equilibrium statistical mechanics (Jaynes, Crooks, Jarzynski...)
• criticality
• compressive sensing (specifically - connections to information theory / manifolds)
• echo state networks / liquid state machines (specifically - what can we say about the classes of transformations the input undergoes?)
• ways to close the sensori-motor loop. (what's the objective function for the brain?)
• brain-machine interfaces (especially - thoughts about algorithm design on the machine side. I feel like it should be able to adapt intelligently, and online, to brain output)

Papers from my previous life as a Martian

Kinch et al. Dust deposition on the Mars Exploration Rover Panoramic Camera (Pancam) calibration targets. Journal of Geophysical Research-Planets (2007)

Johnson et al. Radiative transfer modeling of dust-coated Pancam calibration target materials: Laboratory visible/near-infrared spectrogoniometry. J. Geophys. Res (2006)

Joseph et al. In-flight calibration and performance of the Mars Exploration Rover Panoramic Camera (Pancam) Instruments. J. Geophys. Res (2006)

Parker et al. Stratigraphy and sedimentology of a dry to wet eolian depositional system, Burns formation, Meridiani Planum, Mars. Earth and Planetary Science Letters (2005)

Soderblom et al. Pancam multispectral imaging results from the Opportunity rover at Meridiani Planum. Science (2004)

Soderblom et al. Pancam multispectral imaging results from the Spirit rover at Gusev crater. Science (2004)

Smith et al. Athena microscopic imager investigation. Journal of Geophysical Research-Planets (2003)

Bell et al. Hubble Space Telescope Imaging and Spectroscopy of Mars During 2001. American Geophysical Union (2001)