Adversarial machine-learning attacks and defenses have political dimensions... (more…)

When training a machine learning model, it is standard procedure for the researcher to have full knowledge of both the data and model. However, this engenders a lack of trust between data owners and data scientists. Data owners are justifiably reluctant t... (more…)

Transparent machine learning is a research proposal that would enable machine learning to produce source code in typical programming languages that humans ca... (more…)

From a computer’s standpoint, the difficulty in pattern recognition is one of surplus: with an endless variety of patterns, all… (more…)

Engineers at Osaka University apply machine learning to develop and virtually experiment with molecules for organic solar cells. (more…)