We introduce Recursive Routing Networks (RRNs), which are modular, adaptable models that learn effectively in diverse environments. RRNs consist of a set of functions, typically organized into a grid, and a meta-learner decision-making component called the router. The model jointly optimizes the parameters of the functions and the meta-learner's policy for routing inputs through those functions. RRNs can be incorporated into existing architectures in a number of ways; we explore adding them to word representation layers, recurrent network hidden layers, and classifier layers. Our evaluation task is natural language inference (NLI). Using the MULTINLI corpus, we show that an RRN's routing decisions reflect the high-level genre structure of that corpus. To show that RRNs can learn to specialize to more fine-grained semantic distinctions, we introduce a new corpus of NLI examples involving implicative predicates, and show that the model components become fine-tuned to the inferential signatures that are characteristic of these predicates. x Routing across examples Weight sharing Possible distribution Orthogonalized Knowledge
Background: Home enteral nutrition (HEN) is frequently prescribed to individuals who cannot consume adequate food orally. Commercial blenderized enteral formulas (CBEF) containing real-food ingredients are becoming more popular and more widely available; however, the demographics of patients receiving these formulas have rarely been evaluated, and little data are available on patient tolerance in the community. Methods: US claims data were obtained for children and adolescents/adults who used the CBEF of interest as the sole source of nutrition via enteral feeding tube in the community setting following discharge from acute care. Demographics, concomitant medications, clinical diagnoses, and Charlson Comorbidity Index scores were tabulated using descriptive statistics. Gastrointestinal (GI) symptoms before and after hospital discharge were compared using significance tests.
Results:The study included 231 participants (180 children, 51 adolescents/ adults). CBEFs were prescribed to patients with a variety of diagnoses, of which the most common were digestive and respiratory disorders. Children experienced significantly lower rates of diarrhea, nausea, vomiting, constipation, and abdominal distension in the weeks following hospital discharge compared with the baseline (all P < 0.001). Adolescents/adults experienced significantly lower rates of constipation, nausea, and vomiting (all P < 0.05).Neither group increased their usage of GI medications following hospital discharge.
Conclusion:These CBEFs, based on real-food ingredients, were prescribed to diverse patients in the community and were well tolerated. These formulas offer an alternative to standard polymeric formulas and an alternative or adjunct to homemade blenderized formulas.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.