 |
Center for Nonlinear Studies |
The systematic application of Artificial Intelligence (AI) including machine learning to computational science is likely to result in vastly improved capabilities for doing science. Since AI is increasingly grounded in applied mathematics, including methods of statistical physics and machine learning as well as the classic AI paradigm of symbolic representation, search and logical inference, the path is open to such a mathematically grounded synthesis of AI and computational science. I will illustrate the possibilities with recent work in computational biology including signal transduction in synapses and gene regulation/signaling networks in developmental biology, by means of stochastic model reduction, hierarchical model architectures, enriched graphical models expressed using computer algebra, and declarative modeling languages for heterogeneous dynamics.
Host: Bill Hlavacek