Solomonoff Induction is a theoretical framework for inductive inference that combines algorithmic probability with Bayesian reasoning to predict future data. It assigns higher probability to sequences generated by shorter computer programs, reflecting a preference for simpler explanations. Formulated using universal Turing machines, it defines an optimal predictor over all computable hypotheses, though it is not computable in practice. It underpins concepts in machine learning, compression, and formal approaches to intelligence.
We introduce a framework to analyse interpretability in deep learning, by drawing on a formal notion of model semantics from the philosophy of science. We argue that interpretability is only one aspect of a models semantics and illustrate our framework with examples from biomedicine.
Princeton Office
4 Independence Way, Suite 200
Princeton, NJ 08540
+1 609-520-1555
San Jose Office
2033 Gateway Place, Suite 200
San Jose, CA 95110
+1 408-863-6007
NEC Laboratories America, Inc. (NEC Labs) is the US-based center for NEC Corporation’s global network of corporate research laboratories. Our diverse research groups collaborate with industry, academia and governments to provide disruptive solutions to complex problems. A leader in the integration of IT and network technologies with more than 100 years of expertise, NEC provides a combination of products and solutions that cross-utilize the company’s experience and global resources to meet the complex and ever-changing needs of its customers.