Speaker "Vandana Kannan" Details Back



AI powered Emotion recognition : From Inception to Production


In this session we will implement an AI-powered emotion recognition system and a sentiment analysis system, and take it all the way from inception, through training a deep learning model, and up to deploying a scalable service in production that identifies human emotions in images. During the session we will review the problem of emotion recognition and sentiment analysis and how we can use state of the art research to make use of pre-trained models for building these AI powered systems using Apache MXNet, and finally we will deploy our model to production using Model Server for Apache MXNet. Attendees will go through a hands-on overview of an end-to-end development lifecycle for deep learning models: data preparation, model building, training, and deploying to production.


Vandana Kannan is a Deep Learning Engineer with Amazon AI. She is currently working on Apache MXNet, one of the most scalable and developer-friendly Deep Learning frameworks. In the past, she was a device driver developer and has contributed actively to the open source Linux kernel. Recently, she has been working on providing support for ONNX on MXNet. She holds a Master of Science degree in Computer Science from San José State University, where her research focus was on Genetic Algorithms.