Spring

The aim of this project is to build a desktop tool to be used to analyse and visualize Turkish maqam music pieces. This is an engineering project, it does not involve any research. The skills required are python and docker.

Project Phases

This project aims to deliver a web-based modeling editor similar to the piStar tool (https://www.cin.ufpe.br/~jhcp/pistar/) with added analysis capabilities via integration with OptiMathSat tool (https://optimathsat.disi.unitn.it/).

The idea is to convert the models to logic formulas (we already have algorithms for this), feed to formulas to the OptiMathSat tool, retrieve the solution and visualize it back on the model. 

Required skills: web development, javascript

In this project you are expected to implement a serverless computing framework for running applications on the edge. 
Serverless computing typically allows its users to define the application in terms of functions, events and triggers. In this context, developers are not explicitly aware of the computational infrastructure details such as VMs or containers. Although, at first sight this means a more frictionless development effort, serverless computing is not without its technical challenges. One example challenge is the cold-start problem and there are others as well.    

Automated Machine Learning (AutoML) consists of stages to automate the entire pipeline of machine learning. AutoML is especially useful for teams/organizations that does not necessarily have sufficient expertise on the  AI/ML domain but expected to implement practical ML applications based on given data sources. There are already a variety frameworks for AutoML such as H2O, TPOT, Auto-SKLearn and AutoGluon.