Arni S.R. Srinivasa Rao works in pure mathematics, applied mathematics, probability, artificial intelligence and applications in medicine. He developed the concept of “Exact Deep Learning Machines”, which can provide designs for accurate predictions without any uncertainty. He had edited these handbooks jointly with renowned statistician Dr. C. R. Rao. He is a Professor at the Medical College of Georgia, Augusta University, U.S.A., and the Director of the Laboratory for Theory and Mathematical Modeling housed within the Division of Infectious Diseases, Medical College of Georgia, Augusta, U.S.A. Previously, Dr. Rao conducted research and/or taught at the Mathematical Institute, University of Oxford (2003, 2005-07), Indian Statistical Institute (1998-2002, 2006-2012), Indian Institute of Science (2002-04), University of Guelph (2004-06). Until 2012, Dr. Rao held a permanent faculty position at the Indian Statistical Institute. He has won the Heiwa-Nakajima Award (Japan) and Fast Track Young Scientists Fellowship in Mathematical Sciences (DST, New Delhi). Dr. Rao also proved a major theorem in stationary population models, such as, Rao’s Partition Theorem inPopulations, Rao-Carey Theorem in stationary populations, and developed mathematical modeling-based policies for the spread of diseases like HIV, H5N1, COVID-19, etc. He developed a new set of network models for understanding avian pathogen biology on grid graphs (these were called chicken walk models), AI Models for COVID-19, and received wide coverage in the science media. Dr. Rao is an elected Fellow of ISMMACS (Indian Society for Mathematical Modeling and Computer Simulation), and ISPS (Indian Society for Probability and Statistics). He developed concepts such as “Multilevel Contours within a bundle of Complex Number Planes”.

Select Guide Rating

• Preface1. Neural networks with random weightsCira Perna and Michele La Rocca2. Bayesian Neural Networks for Official Statistics: Modeling High-Dimensional Structure in Complex Surveys and Administrative RecordsScott H. Holan3. weakly supervised learning for neural networksWei Wang, Gang Niu and Masashi Sugiyama4. How to test a neural network as a null hypothesisDavid Bickel5. TBDSoumendu Sundar Mukherjee6. Test-Time Adaptation with Neural Networks: Approaches and Advances in Image ClassificationSravan Danda7. Semantics and Verification of Neural Network Components in Robotic Control Software8. Artificial Neural Network Procedures for the Nonlinear Dynamical Plankton SystemAdnène Arbi Sr. and Walid Ben Ameur9. Neural Networks from Statistical PerspectiveQi on Patent - Qi Meng10. Neural Network applications in Assistive and Collaborative RoboticsBingguang Chen11. Neural Network applications in Assistive and Collaborative RoboticsAntonella Ferrara, NIKOLAS SACCHI, Gian Paolo Incremona, Edoardo Vacchini and Chiara Alessi12. Neural Networks using SPDEsHua Li