A
Asela Gunawardana
Researcher at Microsoft
Publications - 75
Citations - 4488
Asela Gunawardana is an academic researcher from Microsoft. The author has contributed to research in topics: Acoustic model & Expectation–maximization algorithm. The author has an hindex of 27, co-authored 75 publications receiving 4237 citations. Previous affiliations of Asela Gunawardana include Johns Hopkins University & Lafayette College.
Papers
More filters
Book ChapterDOI
Evaluating Recommendation Systems
Guy Shani,Asela Gunawardana +1 more
TL;DR: This paper discusses how to compare recommenders based on a set of properties that are relevant for the application, and focuses on comparative studies, where a few algorithms are compared using some evaluation metric, rather than absolute benchmarking of algorithms.
Journal Article
A Survey of Accuracy Evaluation Metrics of Recommendation Tasks
Asela Gunawardana,Guy Shani +1 more
TL;DR: This paper reviews the proper construction of offline experiments for deciding on the most appropriate algorithm, and discusses three important tasks of recommender systems, and classify a set of appropriate well known evaluation metrics for each task.
Proceedings ArticleDOI
Hidden conditional random fields for phone classification.
TL;DR: This paper presents the results on the TIMIT phone classification task and shows that HCRFs outperforms comparable ML and CML/MMI trained HMMs and has the ability to handle complex features without any change in training procedure.
Book ChapterDOI
Evaluating Recommender Systems
Asela Gunawardana,Guy Shani +1 more
TL;DR: This paper discusses how to compare recommenders based on a set of properties that are relevant for the application, and focuses on comparative studies, where a few algorithms are compared using some evaluation metric, rather than absolute benchmarking of algorithms.
Proceedings ArticleDOI
A unified approach to building hybrid recommender systems
TL;DR: Unified Boltzmann machines are described, which are probabilistic models that combine collaborative and content information in a coherent manner that are competitive with collaborative techniques in recommending items that have been seen before, and also effective at recommending cold-start items.