Event Calendar:

July 2014

Mo Tu We Th Fr Sa Su
27 30 01 02 03 04 05 06
28 07 08 09 10 11 12 13
29 14 15 16 17 18 19 20
30 21 22 23 24 25 26 27
31 28 29 30 31 01 02 03

» All Events

Contact

Fabian Sinz

Address: Spemannstr. 41
72076 Tübingen
Room number: 1.B.05
Phone: +49 7071 601 1778
E-Mail: fabian.sinz

 

Picture of Sinz, Fabian

Fabian Sinz

Position: PhD Student  Unit: Alumni Bethge

I moved to the Lab of Prof. Jan Benda. Lastest information, code, notes, and publication can be found on my webpage.

Current Projects:

Picture

Natural Image Statistics We us the family of Lp-spherically and Lp-nested symmetric distributions to obtain more accurate morels of natural images and quantitatively assess normative hypotheses about the role of orientation selectivity and divisive normalization in the primate early visual system.

Further Reading

Past Projects:

Picture

UNIVERSVM: A SVM Implementation for Large Scale Transduction and Inference with a Universum The UNIVERSVM is a SVM implementation written in C++. Its functionality comprises large scale transduction (as described in Large Scale Transductive SVMs), sparse solutions (as described in Trading Convexity for Scalability) and inference with a universum (as described in Inference with the Universum).

  • Read online help
  • You can download Source code (C++ implementation) at mloss.org (just search for UniverSVM).

Picture

NEC-Labs ABCDetc letter/digit/symbol dataset (in collaboration Ronan Collobert and Jason Weston at NEC Labs America and Seyda Ertekin at PennState University)

We started to collect a dataset consisting of digits, symbols, uppercase and lowercase letters. At the moment it comprises around 50.000 examples.

If you want to contribute, please download the template , fill out the columns as indicated, scan it at 300 dpi and email it to me. (download page)


Transduction Loss as Linear Combination of Ramp Losses

Large Scale Optimization (in collaboration with Ronan Collobert, Jason Weston and Leon Bottou at NEC Labs America)

We show how the Concave-Convex Procedure can be applied to Transductive SVMs, which traditionally requires solving a combinatorial search problem. This provides for the first time a highly scalable algorithm in the nonlinear case.

(project details).


Grafik

Learning Depth from Stereo (Student Research Project) The depth of a point in space can be estimated by observing its image position from two different viewpoints. The classical approach to stereo vision calculates depth from the two projection equations which together form a stereocamera model. An unavoidable preparatory work for this approach is to estimate the parameters of the camera. This can become quite tedious.

In this study, we approached the depth estimation problem from a different point of view by applying generic machine learning algorithms to learn the mapping from image coordinates to spatial position. (project details).

Curriculum Vitae

  • October 2010 -December 2010: intership in the group of Gilles Laurent at the Max Planck Insitute for Brain Research in Frankfurt a.M.
  • March 2007 - January 2012: PhD student in the group of Matthias Bethge
  • August 2005 - October 2005: internship at the NEC laboratories in Princeton
  • 2002-2007: additional studies in philosophy
  • 2000-2007: studies in bioinformatics at the University of Tübingen

Employment

Scholarships and Awards

  • Best Paper Award at the Iternational Conference for Machine Learning 2006 (ICML 2006) for the paper Trading Convexity for Scalability
  • German National Academic Foundation (Studienstiftung des dt. Volkes, January 2008 - February 2010)

Teaching

  • Essential Mathematics for Neuroscience Lecture (Winterterm 2009, with J.-P. Lies), Graduate School of Neural and Behavioural Sciences, University of Tübingen
  • Essential Mathematics for Neuroscience Lecture (Winterterm 2008, with J. Macke), Graduate School of Neural and Behavioural Sciences, University of Tübingen
  • Essential Mathematics for Neuroscience Lecture (Winterterm 2007, with J. Macke), Graduate School of Neural and Behavioural Sciences, University of Tübingen
  • Ethics for Computer Scientists Seminar (Winterterm 2006, with P. Berens and D. Gümbel), University of Tübingen
  • Machine Learning and Neuroscience Practical Course (Winterterm 2004, with A. Gretton, Jeremy Hill and Dilan Görür), University of Tübingen

Preferences: 
References per page: Year: Medium:

  
Show abstracts

Articles (9):

Froudarakis E , Berens P Person, Ecker AS Person, Cotton RJ , Sinz FH Person, Yatsenko D , Saggau P , Bethge M Person and Tolias AS Person (June-2014) Population code in mouse V1 facilitates readout of natural scenes through increased sparseness Nature Neuroscience 17(6) 851–857.
Sinz F Person and Bethge M Person (November-2013) What Is the Limit of Redundancy Reduction with Divisive Normalization? Neural Computation 25(11) 2809-2814.
Sinz F Person and Bethge M Person (January-2013) Temporal Adaptation Enhances Efficient Contrast Gain Control on Natural Images PLoS Computational Biology 9(1) 1-13.
Theis L Person, Gerwinn S Person, Sinz F Person and Bethge M Person (November-2011) In All Likelihood, Deep Belief Is Not Enough Journal of Machine Learning Research 12 3071-3096.
Sinz F Person and Bethge M Person (December-2010) Lp-Nested Symmetric Distributions Journal of Machine Learning Research 11 3409-3451.
pdf
Hosseini R Person, Sinz FH Person and Bethge M Person (October-2010) Lower bounds on the redundancy of natural images Vision Research 50(22) 2213-2222.
pdf
Sinz FH Person, Gerwinn S Person and Bethge M Person (May-2009) Characterization of the p-Generalized Normal Distribution Journal of Multivariate Analysis 100(5) 817-820.
Eichhorn J Person, Sinz FH Person and Bethge M Person (April-2009) Natural Image Coding in V1: How Much Use is Orientation Selectivity? PLoS Computational Biology 5(4:e1000336) 1-16.
Collobert R , Sinz F Person, Weston J Person and Bottou L (August-2006) Large Scale Transductive SVMs Journal of Machine Learning Research 7 1687-1712.
pspdf

Conference papers (8):

Sinz F Person, Simoncelli EP and Bethge M Person (April-2010) Hierarchical Modeling of Local Image Features through Lp-Nested Symmetric Distributions In: Advances in Neural Information Processing Systems 22, 23rd Annual Conference on Neural Information Processing Systems (NIPS 2009), Curran, Red Hook, NY, USA, 1696-1704.
pdfpdf
Sinz F Person and Bethge M Person (June-2009) The Conjoint Effect of Divisive Normalization and Orientation Selectivity on Redundancy Reduction In: Advances in neural information processing systems 21, Twenty-Second Annual Conference on Neural Information Processing Systems (NIPS 2008), Curran, Red Hook, NY, USA, 1521-1528.
pdf
Sinz FH Person, Chapelle O Person, Agarwal A Person and Schölkopf B Person (September-2008) An Analysis of Inference with the Universum In: Advances in neural information processing systems 20, Twenty-First Annual Conference on Neural Information Processing Systems (NIPS 2007), Curran, Red Hook, NY, USA, 1369-1376.
pdf
Weston J Person, Collobert R , Sinz F Person, Bottou L and Vapnik V Person (June-2006) Inference with the Universum In: ICML 2006, 23rd International Conference on Machine Learning, ACM Press, New York, NY, USA, 1009-1016.
pdf
Collobert R , Sinz F Person, Weston J Person and Bottou L (June-2006) Trading Convexity for Scalability In: ICML 2006, 23rd International Conference on Machine Learning, ACM Press, New York, NY, USA, 201-208.
pdf
Quinonero Candela J Person, Rasmussen CE Person, Sinz F Person, Bousquet O Person and Schölkopf B Person (April-2006) Evaluating Predictive Uncertainty Challenge In: Machine Learning Challenges: Evaluating Predictive Uncertainty, Visual Object Classification, and Recognising Tectual Entailment, First PASCAL Machine Learning Challenges Workshop (MLCW 2005), Springer, Berlin, Germany, 1-27.
pdf
Sinz F Person, Candela JQ Person, BakIr G Person, Rasmussen CE Person and Franz M Person (September-2004) Learning Depth From Stereo In: 26th DAGM Symposium, 26th DAGM Symposium, Springer, Berlin, Germany, 245-252.
pdfps
Görür D Person, Rasmussen CE Person, Tolias AS Person, Sinz F Person and Logothetis NK Person (September-2004) Modelling Spikes with Mixtures of Factor Analysers In: Pattern Recognition, 26th DAGM Symposium, Springer, Berlin, Germany, 391-398.
pdf

Contributions to books (1):

Collobert R , Sinz F Person, Weston J Person and Bottou L : Trading Convexity for Scalability, 275-300. In: Large Scale Kernel Machines, (Ed) L. Bottou, MIT Press, Cambridge, MA, USA, (September-2007).
pdf

Technical reports (3):

Sinz FH Person and Bethge M Person: How Much Can Orientation Selectivity and Contrast Gain Control Reduce the Redundancies in Natural Images, 169, Max Planck Institute for Biological Cybernetics, Tübingen, Germany, (March-2008).
pdf
Sinz FH Person and Schölkopf B Person: Minimal Logical Constraint Covering Sets, 155, Max Planck Institute for Biological Cybernetics, Tübingen, (December-2006).
pdf
Sinz FH Person: Kamerakalibrierung und Tiefenschätzung: Ein Vergleich von klassischer Bündelblockausgleichung und statistischen Lernalgorithmen, Wilhelm-Schickard-Institut für Informatik, Universität Tübingen, Tübingen, Germany, (March-2004).
pdf

Posters (7):

Froudarakis A , Berens P Person, Ecker AS Person, Cotton RJ , Sinz FH Person, Yatsenko D , Saggau P , Bethge M Person and Tolias AS Person (June-2014): Population Code in Mouse V1 Facilities Read-out of Natural Scenes through Increased Sparseness, AREADNE 2014: Research in Encoding and Decoding of Neural Ensembles, Santorini, Greece.
Theis L Person, Gerwinn S Person, Sinz F Person and Bethge M Person (October-2010): Likelihood Estimation in Deep Belief Networks, Bernstein Conference on Computational Neuroscience (BCCN 2010), Berlin, Germany, Frontiers in Computational Neuroscience, Conference Abstract: Bernstein Conference on Computational Neuroscience.
Hosseini R Person, Sinz F Person and Bethge M Person (October-2010): New Estimate for the Redundancy of Natural Images, Bernstein Conference on Computational Neuroscience (BCCN 2010), Berlin, Germany, Frontiers in Computational Neuroscience, Conference Abstract: Bernstein Conference on Computational Neuroscience.
Sinz F Person and Bethge M Person (October-2009): A new class of distributions for natural images generalizing independent subspace analysis, Bernstein Conference on Computational Neuroscience (BCCN 2009), Frankfurt a.M., Germany, Frontiers in Computational Neuroscience, 2009(Conference Abstract: Bernstein Conference on Computational Neuroscience).
Sinz FH Person and Bethge M Person (October-2008): The Conjoint Effect of Divisive Normalization and Orientation Selectivity on Redundancy Reduction in Natural Images, Bernstein Symposium 2008, München, Germany, Frontiers in Computational Neuroscience, 2008(Conference Abstract: Bernstein Symposium 2008).
Sinz F Person and Bethge M Person (August-2008): Redundancy Reduction in Natural Images: Quantifying the Effect of Orientation Selectivity and Contrast Gain Control, Gordon Research Conference: Sensory Coding and The Natural Environment 2008, 2008 1.
Sinz F Person and Franz MO Person (February-2004): Learning Depth, 7th Tübingen Perception Conference (TWK 2004), Tübingen, Germany.
pdf

Theses (1):

Sinz FH Person: A priori Knowledge from Non-Examples, Eberhard-Karls-Universität Tübingen, Tübingen, Germany, (March-2007). Diplom thesis
pdf

Export as:
BibTeX, XML, Pubman, Edoc, RTF
Last updated: Friday, 17.01.2014