Worcester Polytechnic Institute-Similarity Search Engine to Support Artificial Intelligence Applications of Robotic Data

Keywords:​ Artificial Intelligence, large-scale robotic dataset, similarity query engine

Recommendation: ​This is a project designed for students who have background in computer science or data science. It is recommended for any students who target to gain the research experience by means of a fundamental research topic which is related to Artificial Intelligence application for large-scale Robotic datasets.

Introduction:

What is Artificial Intelligence? What is deep learning? Or intelligent automation? Or any number of Artificial Intelligence related technologies and applications that seem to be used more and more every day? However, have you considered the atom-level operations to support such complex machine learning tasks at infrastructure-level? It is an approximate similarity search engine in the big data era today. The massive amounts of data continuously generated and collected by various IoT devices, particularly industrial robots, require new search engines at infrastructure-level to speed up data similarity processes on which various Artificial Intelligence techniques rely. Maybe you never heard Apache Hadoop and Apache Spark, but big data should be heard so many times. The project will tell you how big data supports AI applications, particularly the underpinning mechanism. Actually, such fundamental research projects are the backbone of whole AI research. Except the basic concepts of big data and AI, the state-of-the-art similarity search engine techniques will be introduced as the baseline for your research. Meanwhile, key areas that are critical to successfully scale Artificial Intelligence in big data platforms should be identified and customized to guarantee the scalability.

The goal is to help students understand the way of conducting research in computer science and data science, like how to search state-of-the-art material and read papers in the right way, how to generate and optimize a novel intuition to be an excellent research and how to design experiments to validate the research. Above methodology of research would be practiced under instruction using one fundamental topic. By learning search engines knowledge and reading state-of-the-art papers, students are encouraged to generate novel algorithms or architectures to improve the performance or optimize current work. Meanwhile, it is helpful to understand high-level Artificial Intelligence related applications. Students are recommended to write a report including the background of the search engine and relationship with machine learning tasks, the design of new algorithm and expected experiment performance.