Dotan Di Castro
Dotan Di Castro
Research Manager at Bosch-AI, Haifa, Israel
Verified email at
Cited by
Cited by
Policy gradients with variance related risk criteria
A Tamar, D Di Castro, S Mannor
Proceedings of the twenty-ninth international conference on machine learning …, 2012
Memristor-based multilayer neural networks with online gradient descent training
D Soudry, D Di Castro, A Gal, A Kolodny, S Kvatinsky
IEEE transactions on neural networks and learning systems 26 (10), 2408-2421, 2015
Contextual markov decision processes
A Hallak, D Di Castro, S Mannor
arXiv preprint arXiv:1502.02259, 2015
Learning the variance of the reward-to-go
A Tamar, D Di Castro, S Mannor
The Journal of Machine Learning Research 17 (1), 361-396, 2016
Policy gradients with variance related risk criteria
D Di Castro, A Tamar, S Mannor
arXiv preprint arXiv:1206.6404, 2012
You've got mail, and here is what you could do with it! analyzing and predicting actions on email messages
D Di Castro, Z Karnin, L Lewin-Eytan, Y Maarek
Proceedings of the ninth acm international conference on web search and data …, 2016
Temporal difference methods for the variance of the reward to go
A Tamar, D Di Castro, S Mannor
International Conference on Machine Learning, 495-503, 2013
A convergent online single time scale actor critic algorithm
DD Castro, R Meir
The Journal of Machine Learning Research 11, 367-410, 2010
Insertionnet-a scalable solution for insertion
O Spector, D Di Castro
IEEE Robotics and Automation Letters 6 (3), 5509-5516, 2021
Enforcing k-anonymity in web mail auditing
D Di Castro, L Lewin-Eytan, Y Maarek, R Wolff, E Zohar
Proceedings of the Ninth ACM International Conference on Web Search and Data …, 2016
Model selection in markovian processes
A Hallak, D Di-Castro, S Mannor
Proceedings of the 19th ACM SIGKDD international conference on Knowledge …, 2013
Adaptive bases for reinforcement learning
D Di Castro, S Mannor
Joint European Conference on Machine Learning and Knowledge Discovery in …, 2010
Temporal difference based actor critic learning-convergence and neural implementation
D Castro, D Volkinshtein, R Meir
Advances in neural information processing systems 21, 2008
Hand gesture recognition in images and video
I Steinberg, TM London, D Di Castro
Irwin and Joan Jacobs Center for Communication and Information Technologies …, 2010
SOLO: search online, learn offline for combinatorial optimization problems
J Oren, C Ross, M Lefarov, F Richter, A Taitler, Z Feldman, D Di Castro, ...
Proceedings of the International Symposium on Combinatorial Search 12 (1 …, 2021
Structural clustering of machine-generated mail
N Avigdor-Elgrabli, M Cwalinski, D Di Castro, I Gamzu, I Grabovitch-Zuyev, ...
Proceedings of the 25th ACM International on Conference on Information and …, 2016
Integrating a Partial Model into Model Free Reinforcement Learning.
A Tamar, D Di Castro, R Meir, P Dayan
Journal of Machine Learning Research 13 (6), 2012
Insertionnet 2.0: Minimal contact multi-step insertion using multimodal multiview sensory input
O Spector, V Tchuiev, D Di Castro
2022 International Conference on Robotics and Automation (ICRA), 6330-6336, 2022
Analog multiplier using a memristive device and method for implemening Hebbian learning rules using memrisor arrays
D Di Castro, D Soudry, S Kvatinsky, A Gal, A Kolodny
US Patent 9,754,203, 2017
Hebbian learning rules with memristors
D Soudry, D Di Castro, A Gal, A Kolodny, S Kvatinsky
Israel Institute of Technology: Haifa, Israel, 2013
The system can't perform the operation now. Try again later.
Articles 1–20