Paul Horsfall

  • Citations Per Year
Learn More
Probabilistic programming languages (PPLs) are a powerful modeling tool, able<lb>to represent any computable probability distribution. Unfortunately, probabilistic<lb>program inference is often intractable, and existing PPLs mostly rely on expensive,<lb>approximate sampling-based methods. To alleviate this problem, one could try<lb>to learn from past(More)
This paper reports the nature, incidence, and severity of adverse reactions to regimens of rifampicin and ethambutol given once weekly, twice weekly, or daily and to a standard reserve regimen in a total of 330 Chinese failure patients who completed at least six months' chemotherapy in a therapeutic comparison in Hong Kong.The adverse reactions which(More)