Apurva NarayanAssistant ProfessorDepartment of Computer Science,The University of British Columbia, Okanagan Campus, Adjunct Assistant ProfessorDepartment of Systems Design EngineeringUniversity of Waterloo, Waterloo, ON Canada
Address: 1177 Research Rd,Kelowna, BC, Canada V1V 1V7
Office: SCI - 110Email: apurva dot narayan at ubc dot caEmail: apurva dot narayan at uwaterloo dot caPhone: +1 250.807.8272
Google Scholar, DBLP, LinkedIn
Looking for motivated students (undergrads and grads) interested in working in the domain of Data Science, Machine Learning, Artificial Intelligence, Safety and Security of Cyber Physical Systems. Mail Apurva Narayan for further information.
In your email please mention your area of interests and attach your detailed CV and transcripts with links to your sample work (if applicable).
- (6-Oct-2018) Invited talk at West Coast Optimization Meeting 2018 , UBC, Okanagan
- (1-July-2018) Joined the University of British Columbia, as Assistant Professor in Data Science and Computer Science
- (9-Feb-2018) Giving a talk at TU Wien, Vienna on "Data Science for Real-Time Systems"
- (8-Feb-2018) Attending MATHMOD 2018, TU Wien, Vienna, Austria, February 21-23, 2018
- (11-Jan-2018) Our work on "Learning Graph Dynamics using Deep Neural Networks" accepted for publication at 9th Vienna International Conference on Mathematical Modelling, Vienna, Austria, February 21-23, 2018
- (25-Nov-2017) Received the prestigious Systems Society of India's "Young Scientist Award"
- (21-Nov-2017) Delivering a plenary talk at QANSAS 2017, DEI, Dayalbagh, Agra
- (2-Nov-2017) Hands on demo of our tool TREM at 32nd IEEE/ACM Conference on Automated Software Engineering, 2017 at University of Illinois, Urbana-Champaign, USA
- (1-Nov-2017) Presented our tool paper "TREM: A tool for mining timed regular expressions" at 32nd IEEE/ACM Conference on Automated Software Engineering, 2017 at University of Illinois, Urbana-Champaign, USA
- (30-Oct-2017) Presented our latest work on mining "Nested Words in System Traces" at SoftwareMining @ 32nd IEEE/ACM Conference on Automated Software Engineering, 2017 at University of Illinois, Urbana-Champaign, USA
Dr. Apurva Narayan obtained his Ph.D. from the Department of Systems Design Engineering, University of Waterloo and his Bachelor’s degree in Electrical Engineering from Dayalbagh Educational Institute in 2015 and 2008 respectively. His PhD thesis was an archetype of a holistic systems approach for modeling and designing engineering systems under uncertainty. Dr. Narayan was a NSERC post-doctoral fellow with the Real-Time Embedded Systems Group in the Department of Electrical and Computer Engineering at the University of Waterloo, Ontario, Canada.
Dr. Narayan’s research interests lie at the interface of Artificial Intelligence/Machine Learning with emphasis on explainable AI/ML and Quantum Machine Learning, Data Mining, Data Analytics, Safety and Security of Cyber Physical Systems, Software Engineering, Graph Theoretic Analysis of Complex Systems, and Decision Making under Uncertainty. He has authored and co-authored more than 20 peer-reviewed publications in top-tier ACM/IEEE conferences and journals.
Dr. Narayan's current research focuses on data mining, data analytics, and machine learning in context of safety, security and understanding complex Cyber Physical Systems. He is currently interested in developing models for reverse engineering complex software systems. He is also interested in developing interpretable/explainable machine learning models. These models could be used for anomaly detection, specification mining, cyber-physical system security, and other applications.
Key Words: machine learning (data analytics and data modeling), stochastic optimization, Quantum Machine Learning, Quantum Computing
PhD, Department of System Design Engineering, University of Waterloo, ON Canada
Thesis: A Framework for Microgrid Planning Using Multidisciplinary Design Optimization
BSc Engg, Department of Electrical Engineering, Dayalbagh Educational Institute, Agra, India
Thesis: Quantum Evolutionary Algorithms for Difficult Knapsack Problems