PhD candidate @ IDSIA
University of Lugano & SUPSI
Email: rupesh _at_ idsia _dot_ ch
18/09/14: The winning entry of the Higgs Boson Machine Learning Challenge on Kaggle by Gábor Melis utilized the LWTA activation function proposed by us lastyear.
23/08/14: I just finished a summer internship at Microsoft Research in Redmond, USA. I got the opportunity to work on a very exciting project and collaborated with many researchers at MSR including Xiaodong He, Jianfeng Gao, Li Deng, Geoffrey Zweig and John Platt. More details will be available soon!
03/02/14: Check out sheldon.vim, my new collaboration with Engin. It's a fantastic shell-like interpreter for Vim!
05/09/13: Our paper Compete to Compute has been accepted to NIPS 2013. Here is the project page.
02/06/13: Compete to Compute: New IDSIA Tech Report on supervised learning using local competition in neural networks.
I am a researcher in artificial intelligence and machine learning. My supervisor is Prof. Jürgen Schmidhuber. I am currently spending my time understanding artificial neural networks, and their use in the field of Deep Learning.
You may want to have a look at my publications below or my profile on Google Scholar.
R. K. Srivastava, B. R. Steunebrink and J. Schmidhuber: First Experiments with PowerPlay. In: Neural Networks (2013) preprint
R. K. Srivastava, and K. Deb: An Evolutionary Algorithm based Approach to Design Optimization using Evidence Theory. To appear: ASME Journal of Mechanical Design (2013) preprint
R. K. Srivastava, and K. Deb: An Evolutionary based Bayesian Design Optimization Approach under Incomplete Information. Engineering Optimization, Vol. 45, No. 2, pp. 141-165 (2013) preprint
R. K. Srivastava, J. Masci, S. Kazerounian, F. Gomez, J. Schmidhuber: Compete to Compute. In: Advances in Neural Information Processing Systems (2013) pdf
R. K. Srivastava, B. R. Steunebrink, M. Stollenga and J. Schmidhuber: Continually Adding Self-Invented Problems to the Repertoire: First Experiments with PowerPlay. In: IEEE International Conference on Development and Learning and Epigenetic Robotics (ICDL) (2012) pdf
R. K. Srivastava, J. Schmidhuber and F. Gomez: Generalized Compressed Network Search. In: Parallel Problem Solving from Nature, PPSN XII, pp. 337–346 (2012) pdf
R. K. Srivastava, J. Schmidhuber and F. Gomez: Generalized Compressed Network Search. In: Proceedings of the 14th international conference on Genetic and Evolutionary Computation (Late Breaking Abstract), pp. 647–648 (2012) pdf
R. K. Srivastava and K. Deb: An EA-based Approach to Design Optimization using Evidence Theory. In: Proceedings of the 13th annual conference on Genetic and Evolutionary Computation, pp. 1139–1146 (2011) pdf
R. K. Srivastava and K. Deb: Bayesian Reliability Analysis under Incomplete Information using Evolutionary Algorithms. In: 8th International Conference on Simulated Evolution And Learning (SEAL - 2010), Lecture Notes in Computer Science, vol. 6457, pp. 435–444, Springer (2010) pdf
K. Nishijima, Y. Sun, R. K. Srivastava, H. Ogai and B. Bhattacharya: Advanced pipe inspection robot using rotating probe. In: 15th International Symposium on Artificial Life and Robotics, Beppu, Japan, pp. 573–576 (2010) pdf
R. K. Srivastava, J. Masci, S. Kazerounian, F. Gomez and J. Schmidhuber: Compete to Compute. IDSIA Tech Report 2013. pdf