Rupesh Kumar Srivastava

Research Scientist @ NNAISENSE
PhD candidate @ IDSIA
Lugano, Switzerland
Email: rupesh _at_ idsia _dot_ ch

I am the first Research Scientist at NNAISENSE.

I am also a PhD student studying artificial intelligence and machine learning, supervised by Prof. Jürgen Schmidhuber at IDSIA.

During my PhD, I spent time working on open-ended lifelong learning, general approaches for evolving large neural networks, and developed the first ever neural networks capable of learning with tens to hundreds of layers.

During an internship at Microsoft Research, I worked on one of the first neural network based Image Captioning systems, which won first place at the COCO Image Captioning Challenge 2015 (tied with Google).

During my masters, I also worked on robust evolutionary design optimization with Prof. Kalyanmoy Deb.

You may want to have a look at my publications below or my profile on Google Scholar.


Recent Updates


Publications

Under Review:

Recurrent Highway Networks
J. G. Zilly, R. K. Srivastava, J. Koutnik and J. Schmidhuber
arXiv Preprint arXiv:1607.03474

Conferences & Workshops:

Highway and Residual Networks learn Unrolled Iterative Estimation
K. Greff, R. K. Srivastava and J. Schmidhuber
International Conference on Learning Representations (ICLR 2017) arXiv:1612.07771

Training Very Deep Networks
R. K. Srivastava, K. Greff and J. Schmidhuber
Neural Information Processing Systems (NIPS 2015 Spotlight) arXiv:1507.06228

Highway Networks
R. K. Srivastava, K. Greff and J. Schmidhuber
Deep Learning Workshop (ICML 2015). arXiv:1505.00387 poster

Understanding Locally Competitve Networks
R. K. Srivastava, J. Masci, F. Gomez and J. Schmidhuber
International Conference on Learning Representations (ICLR 2015 Conference Track) arXiv:1410.1165
Previously presented at the NIPS 2014 Deep Learning Workshop.

From Captions to Visual Concepts and Back
H. Fang^, S. Gupta^, F. Iandola^, R. K. Srivastava^, L. Deng, P. Dollár, J. Gao, X. He, M. Mitchell, J. Platt, C. L. Zitnick, G. Zweig
IEEE International Conference on Computer Vision and Patter Recognition (CVPR 2015). arXiv:1411.4952

Compete to Compute
R. K. Srivastava, J. Masci, S. Kazerounian, F. Gomez and J. Schmidhuber
Neural Information Processing Systems (NIPS 2013) pdf

Continually Adding Self-Invented Problems to the Repertoire: First Experiments with PowerPlay
R. K. Srivastava, B. R. Steunebrink, M. Stollenga and J. Schmidhuber
IEEE International Conference on Development and Learning and Epigenetic Robotics (ICDL 2012) pdf

Generalized Compressed Network Search
R. K. Srivastava, J. Schmidhuber and F. Gomez
Parallel Problem Solving from Nature (PPSN 2012) pdf
Previously presented as a GECCO 2012 Late Breaking Abstract.

An EA-based Approach to Design Optimization using Evidence Theory
R. K. Srivastava and K. Deb
Conference on Genetic and Evolutionary Computation (GECCO 2011) pdf

Bayesian Reliability Analysis under Incomplete Information using Evolutionary Algorithms
R. K. Srivastava and K. Deb
Simulated Evolution And Learning (SEAL 2010) pdf

Advanced pipe inspection robot using rotating probe
K. Nishijima, Y. Sun, R. K. Srivastava, H. Ogai and B. Bhattacharya
International Symposium on Artificial Life and Robotics (AROB 2010) pdf

Journals:

First Experiments with PowerPlay
R. K. Srivastava, B. R. Steunebrink and J. Schmidhuber
Neural Networks (2013) preprint

An Evolutionary Algorithm based Approach to Design Optimization using Evidence Theory
R. K. Srivastava, K. Deb and R. Tulshyan
ASME Journal of Mechanical Design (2013) preprint

An Evolutionary based Bayesian Design Optimization Approach under Incomplete Information
R. K. Srivastava and K. Deb
Engineering Optimization (2013) preprint

LSTM: A Search Space Odyssey
K. Greff, R. K. Srivastava, J. Koutník, B. R. Steunebrink and J. Schmidhuber
IEEE Transactions on Neural Networks and Learning Systems
arXiv:1503.04069

Reports:

Compete to Compute
R. K. Srivastava, J. Masci, S. Kazerounian, F. Gomez and J. Schmidhuber
IDSIA Tech Report 2013 pdf


Last Modified: 22/03/2017