Smart PAC-learners
نویسندگان
چکیده
منابع مشابه
Smart PAC-Learners
The PAC-learning model is distribution-independent in the sense that the learner must reach a learning goal with a limited number of labeled random examples without any prior knowledge of the underlying domain distribution. In order to achieve this, one needs generalization error bounds that are valid uniformly for every domain distribution. These bounds are (almost) tight in the sense that the...
متن کاملPac-Man or Pac-Bot? Exploring subjective perception of players' humanity in Ms. Pac-Man
Simulating human behaviour when playing video games has been recently proposed as an interesting challenge for the research community on Artificial Intelligence. In the exploration on Machine Learning techniques for training virtual players (i.e. computer bots) to imitate the conduct of real (human) players, we are using the classic arcade game Ms. Pac-Man as testbed. Our research goal is to fi...
متن کاملThe Open University ’ s repository of research publications and other research outputs Do smart devices make smart learners ?
This paper follows up a paper presented at the mLearn 2007 conference (Kukulska-Hulme and Pettit, 2007). It reports on interview data gathered to complement the questionnaire findings reported in that earlier paper. Both papers relate to a study of participants who were each lent a smartphone, which they were encouraged to adopt and embed in their working practices as members of staff at The Op...
متن کاملPAC in FACTT: Time to PAC it in?
The groups had similar baseline characteristics. The rates of death during the first 60 days before discharge home were similar in the PAC and CVC groups (27.4 percent and 26.3 percent, respectively; P=0.69; absolute difference, 1.1 percent; 95 percent confidence interval, -4.4 to 6.6 percent), as were the mean (+/-SE) numbers of both ventilator-free days (13.2+/-0.5 and 13.5+/-0.5; P=0.58) and...
متن کاملPAC Classification based on PAC Estimates of Label Class Distributions
A standard approach in pattern classification is to estimate the distributions of the label classes, and then to apply the Bayes classifier to the estimates of the distributions in order to classify unlabeled examples. As one might expect, the better our estimates of the label class distributions, the better the resulting classifier will be. In this paper we make this observation precise by ide...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
ژورنال
عنوان ژورنال: Theoretical Computer Science
سال: 2011
ISSN: 0304-3975
DOI: 10.1016/j.tcs.2010.12.053