Instructor
Introduction to Convolutional Neural Networks.
Amazon Machine Learning University
Dr. Ragav Venkatesan is currently a senior software engineer at Nvidia AI and was previously employed as an applied scientist at Amazon Alexa AI and AWS Sagemaker. He received his PhD in Computer Science from Arizona State University in 2017. He had been a research associate with the Visual Representation and Processing Group at ASU, and had served as an instructor or teaching assistant for several graduate-level courses in machine learning, computer vision and signal processing. Prior to this, he was a research assistant with the Image Processing and Applications Lab at ASU, and obtained a Master of Science in Electrical Engineering in 2012. Venkatesan was also employed by the Intel Corporation as a computer vision research intern working on technologies for autonomous vehicles. Dr. Venkatesan regularly serves as a reviewer/program committee member for several peer-reviewed journals and conferences in machine learning and computer vision. Dr. Venkatesan was also the author of the book Convolutional Neural Networks in Visual Computing, which is currently available in both English and Mandarin.
Amazon Web Services AI Labs
Applied Scientist
Research Scientist
Intel
Computer Vision
Researcher Intern
Introduction to Convolutional Neural Networks.
Amazon Machine Learning University
School of Computing Informatics and Decision Systems Engineering
Arizona State University
Visual Representation and Processing Group
Arizona State University
School of Computing Informatics and Decision Systems Engineering
Arizona State University
Doctor of Philosophy
Advisor: Dr. Baoxin Li
Computer Science
Arizona State University
Master of Science
Advisor: Dr. David
Frakes
Electrical Engineering
Arizona State University
Bachelor of Engineering
Electronics and Communication Engineering
Anna University
Domain Adaptation using Stochastic Neighborhood Embedding.
Workshop on Amazon SageMaker.
Amazon SageMaker Semantic Segmentation.
Professional Networking for Graduate Students.
Neural Dataset Generality.
Perception-Inspired Spatio-Temporal Video Deinterlacing.
Retrieving clinically relevant diabetic retinopathy images using a multi-class multiple instance framework..