About the Lab
The Patel Lab’s main purpose is to serve as a bridge between the fields of computational neuroscience and deep machine learning. Advances in understanding in one domain often lead to advances in the other. Using the brain as a guide, we build theories of intelligent computation and translate them into working high-performing architectures for a wide variety of difficult tasks in computer vision, medical imaging, and high-energy physics.
Talks
The following are talks given by Ankit B. Patel:
Invited Talk: “A Tutorial on Deep Learning: Why Does it Work?” International Conference of Computational Photography. Held at Rice University. April 25, 2015.
“How and Why Deep Learning Works” ISS Seminar Series, SEAS Dept., Harvard University. October 2015.
“How and Why Deep Learning Works: Applications to Computational Neuroscience.” Jim DiCarlo Lab, Brain and Cognitive Science Dept., MIT. October 2015.
“A Probabilistic Theory of Deep Learning: Applications to Computational Neuroscience.” CBCL Seminar, Tomaso Poggio Lab, Brain and Cognitive Science Dept., MIT. October 2015.
“A Probabilistic Theory of Deep Learning: Or How I Learned to Love Neural Nets.” NIPS Workshop on Multi-scale Learning. Montreal Canada, December 2015. (Due to sickness, talk was given by Richard G. Baraniuk instead).
“A Probabilistic Theory of Deep Learning: It’s Message Passing, Stupid.” Seminar Series, Brain and Cognitive Sciences Dept., University of Rochester. January 2016.
Lab Publications
“A Probabilistic Theory of Deep Learning.” Ankit Patel, Tan Nguyen, Richard Baraniuk. No. 2015-1: Rice University, Department of Electrical and Computer Engineering, Mar. 15, 2015. In preparation.
"Order in Proliferating Metazoan Epithelia.” Ankit Patel, Matthew Gibson, Radhika Nagpal, Norbert Perrimon. Nature 42, pp. 1038-1041. Aug 31, 2006.
“Modeling and inferring cleavage patterns in proliferating epithelia." AB Patel, WT Gibson, MC Gibson, R Nagpal. PLoS computational biology 5 (6), e1000412.
“Epithelial topology." R Nagpal, A Patel, MC Gibson. BioEssays 30 (3), 260-266.
“Desynchronization: A self-organizing algorithm for desynchronization and periodic resource scheduling.” Ankit Patel, Julius Degesys, Radhika Nagpal. IEEE International Conference on Self-Adaptive and Self-Organizing Systems, July 2007.
“DESYNC: Self-organizing Desynchronization and TDMA on Wireless Sensor Networks.” Julius Degesys, Ian Rose, Ankit Patel, Radhika Nagpal. To be submitted to the International Conference on Information Processing in Sensor Networks, April 2007.
“Firefly-Inspired Sensor Network Synchronicity with Realistic Radio Effects.” Geoff Werner-Allen, Geetika Tewari, Ankit Patel, Matt Welsh, Radhika Nagpal. In the ACM Conference on Embedded Networked Sensor Systems (SenSys'05), November 2005.
View citations for the above papers: Google Scholar site
