I am a computer science PhD student at the University of California, Berkeley.
I am interested in machine learning and artificial intelligence, with a focus on deep reinforcement learning and deep imitation learning for robotics.
My advisor is John Canny. I also frequently collaborate with the folks in the AUTOLAB.
I am grateful to be supported by a National Physical Science Consortium fellowship (from 2015 to 2021), funded through the National Security Agency.
You can reach me at email@example.com.
I also frequently blog about technical and non-technical topics, and write code and notes on GitHub.
News and Updates
- 01/11/2018: Our paper on surgical debridement and calibration has been accepted to ICRA 2018!
- 09/21/2017: A preprint on surgical debridement is now available.
- 08/16/2017: I had a great time at UAI 2017 in Sydney, Australia! I especially enjoyed giving a talk on the fourth day.
- 08/02/2017: I wrote a blog post on the BAIR Blog about our work on minibatch Metropolis-Hastings.
- 05/30/2017: I created my academic website. Sorry for the delay.
Preprints and Publications
For all these papers, you can find the latest versions on arXiv.
Fast and Reliable Autonomous Surgical Debridement with Cable-Driven Robots Using a Two-Phase Calibration Procedure.
Daniel Seita, Sanjay Krishnan, Roy Fox, Stephen McKinley, John Canny, Ken Goldberg.
IEEE International Conference on Robotics and Automation (ICRA), May 2018.
An Efficient Minibatch Acceptance Test for Metropolis-Hastings.
Daniel Seita, Xinlei Pan, Haoyu Chen, John Canny.
Conference on Uncertainty in Artificial Intelligence (UAI), August 2017.
(Oral Presentation, Honorable Mention for Best Student Paper)
The following represents some of my older work and is not necessarily representative of my current research interests.
Large-Scale Supervised Learning of the Grasp Robustness of Surface Patch Pairs.
Daniel Seita, Florian T. Pokorny, Jeffrey Mahler, Danica Kragic, Michael Franklin, John Canny, Ken Goldberg.
IEEE International Conference on Simulation, Modeling, and Programming for Autonomous Robots (SIMPAR), December 2016.
Computing Abelian Complexity of Binary Uniform Morphic Words.
Francine Blanchet-Sadri, Daniel Seita, David Wise.
Theoretical Computer Science, Volume 640, June 2016.
Coursework and Teaching Assistantships
I've taken a number of graduate courses as part of the PhD program at UC Berkeley.
I also write reviews, which might be helpful for those thinking about taking future iterations of these classes.
I was also the GSI (i.e., Teaching Assistant) for the Deep Learning class in Fall 2016.
UC Berkeley also has an oral preliminary exam requirement for PhD students. Here's the transcript of my prelims.
- (Review) CS 267, Applications of Parallel Computing
- (Review) CS 280, Computer Vision
- (Review) CS 281A, Statistical Learning Theory
- (Review) CS 287, Advanced Robotics
- (Review) CS 288, Natural Language Processing
- (Review) CS 294-112, Deep Reinforcement Learning
- (Review) CS 294-112, Deep Reinforcement Learning (self-study)
- (Review) CS 294-115, Algorithmic Human-Robot Interaction
- (Review) CS 294-129, Deep Neural Networks (GSI/TA)
- (Review) CS 294-131, Special Topics in Deep Learning
- (Review) EE 227BT, Convex Optimization
- (Review) EE 227C, Convex Optimization and Approximation
- (Review) STAT 210A, Theoretical Statistics (Classical)
- (Review) STAT 210B, Theoretical Statistics (Modern)
© Daniel Seita. Last updated: January 2018.