The NEC machine learning department studies theory and applications of statistical learning theory. We aim to understand learning through the analysis of new induction principles, efficient implementations of those principles, and the development of innovative applications that showcase their performance.
We aim to advance the theoretical understanding of learning through the analysis of new induction principles and through a paradigm shift from traditional inductive inference to non-inductive inference such as transductive and selective inference.
Accelerating computation by orders of magnitude through the development of more efficient learning algorithms, and through more efficient implementations.
Applications of our theoretical and algorithmic advances to innovative applications, showcasing their performance.