Cracking open the black box of automated machine learning

MIT News  May 31, 2019 Automated machine-learning (AutoML) systems iteratively test and modify algorithms and hyperparameters and select the best-suited models. An international team of researchers (USA – MIT, Hong Kong, China) describes a tool called ATMSeer, that takes as input an AutoML system, a dataset, and some information about a user’s task. Then, it visualizes the search process in a user-friendly interface, which presents in-depth information on the models’ performance. They have demonstrated the utility and usability of ATMSeer through two case studies, expert interviews, and a user study with 13 end users. Video…read more. Open Access TECHNICAL ARTICLE

Can we trust scientific discoveries made using machine learning?

Eurekalert  February 15, 2019 According to the researchers at Rice University machine learning field has focused on developing predictive models that allow machine learning to make predictions about future data based on its understanding of data it has studied. A lot of these techniques are designed to always make a prediction. They never come back with ‘I don’t know,’ or ‘I didn’t discover anything,’ because they aren’t made to. People have applied machine learning to genomic data from clinical cohorts to find groups, or clusters, of patients with similar genomic profiles. But there are cases where discoveries aren’t reproducible; the […]