About me:

• Education

  • DSc (Doctor of Science; in Intelligent Robotics, 2008) from the Swiss Federal Institute of Technology Zurich,

  • MS in Computer Science (with emphasis on Intelligent Robotics, 2004) from the University of Southern Calfornia, USA

  • BE in Computer Science and Engineering (2002) from the University of Madras, India.

• Key work themes

  • Intelligent Robotics @ Swiss Federal Institute of Technology Zurich

    • developing spatial awareness in robots; addressed problems relating to hierarchical representations of spatial data obtained from robot sensors (vision, image processing, range sensing) and the generation of increasingly abstract spatial constructs (e.g. a storage area or an office) from sensor data through machine learning; see YouTube demo-movie and poster-summary

  • Mining automation @ Rio Tinto Centre for Minining Automation, Australian Centre for Field Robotics

    • modeling and data-fusion for large-scale terrain, sub-surface ore-body and equipment health monitoring (predictive maintenance / prognostics); see YouTube demo-movie-1 , demo-movie-2 and poster-summary

  • Modeling natural resources @ IBM (Australia and India)

    • modeling and data-fusion for oil and gas (well log modeling), crop hail-damage prediction for insurance analytics and other modeling problems in agriculture (e.g., NDVI for crop-health); familiar with key modeling issues in the geothermal energy sector.

  • Workforce analytics @ IBM India

    • estimating propensity to reskill and estimating fungibility between skills for skill-demand forecasting

  • Deep Learning platforms @ IBM India

    • Mutual Information based learning rate decay for SGD training of deep neural networks

  • Enterprise financial-process transformation @ IBM India

    • Billing process transformation using multi-agent collaborative cognition approach to system design

  • AI/ML use-cases in the Telecommunications domain @ Ericsson India Global Services

    • Incorporating domain knowledge in ML-driven Telco Dimensioning models; Forecasting models for planning Telco network rollouts

• My work has been evidenced by several applied/granted patents and several publications (see below; email me in case of access issues)

• Involved in teaching through university teaching, lectures at conferences, summer/winter schools and up-skilling efforts (courses, labs, lectures) in organizations I have worked in.

• Best paper finalist at IEEE MFI (multi-sensor fusion and information integration) 2012

• Senior Member of the IEEE

Representative papers (peer-reviewed)

1. Shrihari Vasudevan, Mutual Information Based Learning Rate Decay for Stochastic Gradient Descent Training of Deep Neural Networks, in Entropy 2020, 22(5), 560.

2. Shrihari Vasudevan, Moninder Singh, Joydeep Mondal, Michael Peran, Ben Zweig, Brian Johnston and Rachel Rosenfeld, Estimating fungibility between skills by combining skill-similarities obtained from multiple data sources, in Journal of Data Science and Engineering, 2018.

3. Shrihari Vasudevan, Data Fusion with Gaussian Processes, Elsevier Journal of Robotics and Autonomous Systems, Volume 60, Issue 12, December 2012, Pages 1528-1544.

4. Shrihari Vasudevan, Arman Melkumyan and Steve Scheding, Efficacy of data fusion using convolved multi-output Gaussian processes, Journal of Data Science, 2014. Based on this arXiv report.

5. Shrihari Vasudevan, Fabio Ramos, Eric Nettleton and Hugh Durrant-Whyte, Gaussian Process Modeling of Large Scale Terrain, Journal of Field Robotics, Volume 26, Issue 10, October 2009, Pages 812-840.

6. Shrihari Vasudevan and Roland Siegwart, Bayesian Space Conceptualization and Place Classification for Mobile Robots. Elsevier Journal of Robotics and Autonomous Systems, Volume 56, Issue 6, "From Sensors to Human Spatial Concepts", Pages 522-537, 30 June 2008.

7. Shrihari Vasudevan, Stefan Gaechter, Ahad Harati and Roland Siegwart, A hierarchical Concept-Oriented Representation for Spatial Cognition in Mobile Robots, In M. Lungarella, F. IIda, J. Bongard and R. Pfeifer (eds.), 50 Years of Artificial Intelligence, Springer Lecture Notes in Artificial Intelligence, Vol. 4850, 2007.

8. Shrihari Vasudevan, Stefan Gaechter, Viet T. Nguyen and Roland Siegwart, Cognitive Maps for Mobile Robots - An object based approach. Elsevier Journal of Robotics and Autonomous Systems, Volume 55, Issue 5, "From Sensors to Human Spatial Concepts", 31 May 2007, Pages 359-371. (3rd most cited publication of the journal during 2007-2012)

Competitions

• Shrihari Vasudevan, Ritwik Chaudhuri, Madhavan Pallan and Sudhanshu Singh, “Gaussian process modelng for understanding labour markets”, Ranked #1 of 30 submissions in the data challenge of the ACM IKDD Conferernce on Data Science 2016, Pune, India.

Patents

• See JUSTIA or Google Patents or my CV for comprehensive information

Book chapters (peer-reviewed)

1. Arnau Ramisa, Shrihari Vasudevan, Davide Scaramuzza, Ramon Lopez de Mantaras and Roland Siegwart, A tale of two object recognition methods for mobile robots, in the proceedings of the 6th International Conference on Computer Vision Systems, Santorini, Greece, May 12-15. Springer Lecture Notes in Computer Science 5008 (2008) 353-362.

2. Shrihari Vasudevan, Stefan Gaechter, Ahad Harati and Roland Siegwart, A hierarchical Concept-Oriented Representation for Spatial Cognition in Mobile Robots, In M. Lungarella, F. IIda, J. Bongard and R. Pfeifer (eds.), 50 Years of Artificial Intelligence, Springer Lecture Notes in Artificial Intelligence, Vol. 4850, 2007.

Journal papers (peer-reviewed)

1. Shrihari Vasudevan, Mutual Information Based Learning Rate Decay for Stochastic Gradient Descent Training of Deep Neural Networks, in Entropy 2020, 22(5), 560.

2. Shrihari Vasudevan, Moninder Singh, Joydeep Mondal, Michael Peran, Ben Zweig, Brian Johnston and Rachel Rosenfeld, Estimating fungibility between skills by combining skill-similarities obtained from multiple data sources, in Journal of Data Science and Engineering, 2018.

3. Shrihari Vasudevan, Ritwik Chaudhuri, Madhavan Pallan and Sudhanshu S. Singh, An empirical study of starting salaries and employment trends of Engineering students in India, Journal of Data Science, 2017.

4. Shrihari Vasudevan, Arman Melkumyan and Steve Scheding, Efficacy of data fusion using convolved multi-output Gaussian processes, Journal of Data Science, 2014.

5. Shrihari Vasudevan, Data Fusion with Gaussian Processes, Elsevier Journal of Robotics and Autonomous Systems, Volume 60, Issue 12, December 2012, Pages 1528-1544.

6. Aranu Ramisa, David Aldavert, Shrihari Vasudevan, Ricardo Toldedo and Ramon Lopez de Mantaras, Evaluation of three vision based object perception methods for a mobile robot, in Springer Journal of Intelligent and Robotic Systems, November 2012 (online 28 April 2012), Volume 68, Issue 2, pp 185-208.

7. Shrihari Vasudevan, Fabio Ramos, Eric Nettleton and Hugh Durrant-Whyte, A Mine on its own: Fully Autonomous, Remotely Operated Mine, in IEEE Robotics and Automation Magazine, June 2010.

8. Shrihari Vasudevan, Fabio Ramos, Eric Nettleton and Hugh Durrant-Whyte, Gaussian Process Modeling of Large Scale Terrain, Journal of Field Robotics, Volume 26, Issue 10, October 2009, Pages 812-840.

9. Shrihari Vasudevan and Roland Siegwart, Bayesian Space Conceptualization and Place Classification for Mobile Robots. Elsevier Journal of Robotics and Autonomous Systems, Volume 56, Issue 6, "From Sensors to Human Spatial Concepts", Pages 522-537, 30 June 2008.

10. Shrihari Vasudevan, Stefan Gaechter, Viet T. Nguyen and Roland Siegwart, Cognitive Maps for Mobile Robots - An object based approach. Elsevier Journal of Robotics and Autonomous Systems, Volume 55, Issue 5, "From Sensors to Human Spatial Concepts", 31 May 2007, Pages 359-371. (3rd most cited publication of the journal during 2007-2012)

Conference and workshop papers (peer-reviewed)

1. Venkatachalam Natchiappan, Shrihari Vasudevan, Thalanayar Muthukumar, Estimating Task Completion Times for Network Rollouts using Statistical Models within Partitioning-based Regression Methods, to appear in COMSNETS 2023 - MINDS workshop.

2. Shrihari Vasudevan, Sleeba Puthenpurakel, Marcial Gutierrez and M.J. Prasath, Bayesian Regression for Interpretable Network Dimensioning, to appear in COMSNETS 2023.

3. Gautham Krishna Gudur, R. Raaghul, K. Adithya and Shrihari Vasudevan, Data-Efficient Automatic Model Selection in Unsupervised Anomaly Detection, to appear in IEEE ICMLA 2022.

4. Shrihari Vasudevan, Moninder Singh, Joydeep Mondal, Michael Peran, Ben Zweig, Brian Johnston and Rachel Rosenfeld, Estimating fungibility between skills by combining skill-similarities obtained from multiple data sources, in proc. of International Workshop on Data Science for Human Capital Management (DSHCM), colocated with the IEEE International Conference on Data Mining (ICDM) 2017, New Orleans, USA.

5. Moninder Singh, Karthikeyan Natesan Ramamurthy and Shrihari Vasudevan, Propensity modeling for employee reskilling, in proc. of IEEE GlobalSIP 2017 Symposium on Signal and Information Processing for Finance and Business, Montreal, Canada.

6. Melanie Roberts and Shrihari Vasudevan, Fine-grained multi-factor hail damage modelling, in proc. of the 2015 Conference on Technologies and Applications of Artificial Intelligence, Taiwan.

7. Andrew Rawlinson and Shrihari Vasudevan, Gaussian process modeling of well logs, in proc. of the UKSim-AMSS 9th IEEE European Modelling Symposium on Mathematical Modelling and Computer Simulation, 2015, Madrid, Spain.

8. Jose F. Zubizarreta-Rodriguez and Shrihari Vasudevan, Condition Monitoring of Brushless DC Motors with Non-Stationary Dynamic Conditions, in proc. of the IEEE International Instrumentation and Measurement Technology Conference (I2MTC) 2014, Montevideo, Uruguay.

9. Jose F. Zubizarreta-Rodriguez and Shrihari Vasudevan, Bearing and Gear Failure Detection for Brushless DC Motors with Adaptive Feature Extraction and Classification, in proc. of the IEEE conference on Advanced Intelligent Mechatronics (AIM) 2014, France.

10. Aditya Mahajan, Shrihari Vasudevan, Mark Calleija and Steven Scheding, Experimental platform for predictive maintenance of permanent magnet synchronous motors, in proc. of the IEEE International Conference on Computer Science and Automation Engineering (CSAE) 2013, China. (Technical report)

11. Shrihari Vasudevan, Arman Melkumyan and Steven Scheding, Information fusion in multi-task Gaussian process models, in the proceedings of the IEEE International Conference on Multi-sensor Fusion and Information Integration (MFI) 2012, Hamburg, Germany. Best conference paper finalist.

12. Arnau Ramisa, David Aldavert, Shrihari Vasudevan, Ricardo Toldedo and Ramon Lopez de Mantaras, The IIIA30 Mobile Robot Object Recognition Dataset, in the proceedings of the International Conference on Mobile Robots and Competitions (Robotica) 2011, Lisbon, Portugal.

13. Shrihari Vasudevan, Fabio Ramos, Eric Nettleton and Hugh Durrant-Whyte, Non-stationary dependent Gaussian processes for data fusion in large scale terrain modeling, in the proceedings of the IEEE International Conference on Robotics and Automation (ICRA) 2011, Shanghai, China.

14. Shrihari Vasudevan, Fabio Ramos, Eric Nettleton and Hugh Durrant-Whyte, Large-scale terrain modeling from multiple sensors with dependent Gaussian processes, in the proceedings of the IEEE/RSJ International Conference on Robotics and Intelligent Systems (IROS) 2010, Taiwan.

15. Bertrand Douillard, James P. Underwood, Narek Melkumyan, Surya P. N. Singh, Shrihari Vasudevan, Cristopher J. Brunner and Alistair Quadros, Hybrid elevation maps: 3D surface models for segmentation, in IEEE/RSJ International Conference on Robotics and Intelligent Systems (IROS) 2010, Taiwan.

16. Shrihari Vasudevan, Fabio Ramos, Eric Nettleton and Hugh Durrant-Whyte, Heteroscedastic Gaussian Processes for Data Fusion in Large Scale Terrain Modeling, in the proceedings of the IEEE International Conference on Robotics and Automation (ICRA) 2010, Anchorage, Alaska, USA.

17. Shrihari Vasudevan, Fabio Ramos, Eric Nettleton and Hugh Durrant-Whyte, Evaluation of Gaussian Processes for Large Scale Terrain Modeling, in the proc. of the Australasian Conference on Robotics and Automation (ACRA) 2009, Sydney, Australia.

18. Arnau Ramisa, Shrihari Vasudevan, David Aldavert, Ricardo Toldedo and Ramon Lopez de Mantaras, Evaluation of the SIFT Object Recognition Method in Mobile Robots, in the proc. of the Catalan Conference on Artificial Intelligence (CCAI) 2009.

19. Shrihari Vasudevan, Fabio Ramos, Eric Nettleton, Hugh Durrant-Whyte and Allan Blair, Gaussian Process Modeling of Large Scale Terrain, in the proceedings of the IEEE International Conference on Robotics and Automation (ICRA) 2009, Kobe, Japan.

20. Shrihari Vasudevan and Roland Siegwart, A Bayesian approach to Conceptualization and Place Classification: Incorporating Spatial Relationships (distances) to infer concepts, in the proc. of the IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) 2007 Workshop: From Sensors to Human Spatial Concepts (FS2HSC), San Diego, USA.

21. Shrihari Vasudevan, Ahad Harati and Roland Siegwart, A Bayesian approach to Conceptualization and Place Classification: using the number of occurrences of objects to infer concepts, in the proc. of 3rd European Conference on Mobile Robotics (ECMR) 2007, Freiburg, Germany.

22. Shrihari Vasudevan and R. Siegwart, A Bayesian Conceptualization of Space for mobile robots. in the proceedings of the IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) 2007, San Diego, USA.

23. Shrihari Vasudevan, Stefan Gachter and Roland Siegwart, Cognitive Spatial Representations for Mobile Robots - Perspectives from a user study. In the proceedings of the IEEE International Conference on Robotics and Automation - Workshop: Semantic Information in Robotics (ICRA - SIR) 2007, Rome, Italy.

24. Shrihari Vasudevan, Stefan Gachter, Marc Berger and Roland Siegwart, Cognitive Maps for Mobile Robots - An Object based Approach. In the proceedings of the IEEE/RSJ International Conference on Intelligent Robots and Systems - Workshop: From Sensors to Human Spatial Concepts (IROS - FS2HSC) 2006, Beijing, China.

25. Shrihari Vasudevan, Viet T. Nguyen and Roland Siegwart, Towards a Cognitive Probabilistic Representation of Space for Mobile Robots. In the Proceedings of the IEEE International Coference on Information Acquisition (ICIA) 2006, Shandong, China.

26. Adriana Tapus, Shrihari Vasudevan and Roland Siegwart, Toward a Multilevel Cognitive Probabilistic Representation of Space. In Proceedings of the International Conference on Human Vision and Electronic Imaging X, part of the IS&T/SPIE Symposium on Electronic Imaging 2005, 16-20 January 2005, CA, USA

27. Roland Siegwart, Shrihari Vasudevan and Adriana Tapus, From Geometric to Cognitive Maps - A Key Element for Personal Robots, 18th IFIP World Computer Congress, Toulouse, France, August 2004, pp. 755-760.

28. Nathan Mundhenk, Vidhya Navalpakkam, Hendrik Makaliwe, Shrihari Vasudevan and Laurent Itti, Biologically Inspired Feature based Categorization of Objects, in the proc. of the International Conference on Human Vision and Electronic Imaging IX, part of the IS&T/SPIE Symposium on Electronic Imaging, January 2004, San Jose, CA, USA.

29. Shrihari Vasudevan and S. Sudarsun, Motion Planning - Robot Navigation - Ranging method, in proc. of the National (Indian) level technical conference (INCON) 2002. Best paper award.

Other reports

1. Shrihari Vasudevan, Dynamic learning rate using Mutual Information, arXiv:1805.07249, 2018.

2. Shrihari Vasudevan, Arman Melkumyan and Steve Scheding, Information fusion in multi-task Gaussian process models, arXiv report 1210.1928.

3. Shrihari Vasudevan, Data Fusion with Gaussian Processes, technical report ACFR-TR-2012-001 (Completed, 03 Nov 2011 / Released, 20 June 2012), Australian Centre for Field Robotics, The University of Sydney.

4. Andrew Maclean and Shrihari Vasudevan, Paraview used in a Mining Research Environment, in Kitware Source, Issue 11, October 2009 (Invited paper)

5. Aranu Ramisa, David Aldavert, Shrihari Vasudevan, Ricardo Toldedo and Ramon Lopez de Mantaras, Evaluation of three vision based object perception methods for a mobile robot, arxiv report 1102.0454, Feb 2011.

6. Shrihari Vasudevan, Spatial Cognition for Mobile Robots: A Hierarchical Probabilistic Concept-Oriented Representation of Space, Thesis Number 17612, March 2008, Swiss Federal Institute of Technology Zurich. [ Abstract | outline of chapters | presentation | poster ]

Teaching

1. AI Microdegree program offered by Ericsson and KTH Sweden; Laboratory on Distributed Machine Learning, 2021.

2. Two lectures on "Uncertainty quantfication for machine learning applications" at the Indo-French Centre for Applied Mathematics (IFCAM) Winter School 2018, IISER Kolkata, India, 13 December 2018.

   • Modeling and Information fusion with Gaussian Processes

   • Uncertainty quantification for mobile robots

   • Model selection with uncertainty quantification in Neural Networks

3. Half day tutorial on "Modeling and information fusion using Gaussian processes" at the IEEE International Conference on Multisensor Fusion and Information Integration (MFI), 13-15 September 2012.

4. AMME 4710 - Computer Vision and Image Processing at the University of Sydney, July - Nov 2008, 2009 and 2010.

5. Cogniron Winter School on Human Robot Interaction (January 2008) : Session on Cognitive Maps