Goto

Collaborating Authors

Li

AAAI Conferences

Standard feature selection algorithms deal with given candidate feature sets at the individual feature level. When features exhibit certain group structures, it is beneficial to conduct feature selection in a grouped manner. For high-dimensional features, it could be far more preferable to online generate and process features one at a time rather than wait for generating all features before learning begins. In this paper, we discuss a new and interesting problem of online group feature selection from feature streams at both the group and individual feature levels simultaneously from a feature stream. Extensive experiments on both real-world and synthetic datasets demonstrate the superiority of the proposed algorithm.


Online Group Feature Selection from Feature Streams

AAAI Conferences

Standard feature selection algorithms deal with given candidate feature sets at the individual feature level. When features exhibit certain group structures, it is beneficial to conduct feature selection in a grouped manner. For high-dimensional features, it could be far more preferable to online generate and process features one at a time rather than wait for generating all features before learning begins. In this paper, we discuss a new and interesting problem of online group feature selection from feature streams at both the group and individual feature levels simultaneously from a feature stream. Extensive experiments on both real-world and synthetic datasets demonstrate the superiority of the proposed algorithm.  


Ensemble Feature Weighting Based on Local Learning and Diversity

AAAI Conferences

Recently, besides the performance, the stability (robustness, i.e., the variation in feature selection results due to small changes in the data set) of feature selection is received more attention. Ensemble feature selection where multiple feature selection outputs are combined to yield more robust results without sacrificing the performance is an effective method for stable feature selection. In order to make further improvements of the performance (classification accuracy), the diversity regularized ensemble feature weighting framework is presented, in which the base feature selector is based on local learning with logistic loss for its robustness to huge irrelevant features and small samples. At the same time, the sample complexity of the proposed ensemble feature weighting algorithm is analyzed based on the VC-theory. The experiments on different kinds of data sets show that the proposed ensemble method can achieve higher accuracy than other ensemble ones and other stable feature selection strategy (such as sample weighting) without sacrificing stability


Google's latest Android features are too vital to be Pixel-only

PCWorld

Google just introduced a number of great updates to Android, but only for its own Pixel product line. While that's awesome for Pixel users, it shuts out the rest of the Android community from important upgrades. There was a time when new Android updates brought more than just bug fixes and security patches. Like iOS, Google once handed out new features and enhancements throughout the lifespan of each version of Android to keep devices fresh and clean. For example, this latest drop includes adaptive battery improvements to make your phone last longer, a new bedtime feature in the Clock app that can play ambient noise and automatically limit notifications, and safety features that can alert your emergency contacts if you're alone and in a potentially dangerous situation. They're useful, important features that the rest of Android is missing out on.


Meijer Gardens Exhibition Features Sculptor Masayuki Koorida

U.S. News

Koorida is celebrated for partially carved and polished boulders like "Existence," which is permanently located in The Richard & Helen DeVos Japanese Garden in Grand Rapids. Meijer Gardens says his other important works include highly geometric pieces and large-scale drawings.