MIT researchers are developing a tool to bring raw science data to non-statisticians in the form of generated models for analysis. In this way, the tool visualises data for everybody for further analysis. This is especially convenient for experts with statistic background to analyze, interpret, and predict underlying patterns in data. The tool currently is available on Jupyter Notebook. It is an open-source web framework that allows users to run programs interactively in their browsers.
Vikash Mansinghka, a researcher in the Department of Brain and Cognitive Sciences (BCS) who runs the Probabilistic Computing Project, explains: “When the system makes a model, it spits out a piece of code written in one of these domain-specific probabilistic programming languages … that people can understand and interpret. For example, users can check if a time series dataset like airline traffic volume has seasonal variation just by reading the code — unlike with black-box machine learning and statistical methods, where users have to trust a model’s predictions but can’t read it to understand its structure.” Source: MIT News Office
NEWS FROM ELEARNINGWORLD MEDIA