On Hybrid and Systems AI

                                Kristian Kersting

  Computer Science Department, TU Darmstadt, 64289 Darmstadt, Germany
                      kersting@cs.tu-darmstadt.de



    Abstract. Our minds make inferences that appear to go far beyond
    standard machine learning. Whereas people can learn richer representa-
    tions and use them for a wider range of learning tasks, machine learning
    algorithms have been mainly employed in a stand-alone context, con-
    structing a single function from a table of training examples. In this talk,
    I shall touch upon a view on AI and machine learning, called Systems
    AI, that can help capturing these human learning aspects by combining
    different AI and ML models using high-level programming. Since infer-
    ence remains intractable, existing approaches leverage deep learning for
    inference. Instead of “just going down the neural road,” I shall argue to
    also use probabilistic circuits, a deep but tractable architecture for prob-
    ability distributions. This hybrid approach can speed up inference as I
    shall illustrate for unsupervised science understanding, database queries
    and automating density estimation.




Copyright ©   2020 by the paper’s authors. Use permitted under Creative Commons
License Attribution 4.0 International (CC BY 4.0).