Sentence examples for transfer categories from inspiring English sources

The form of information transfer is categorized into four general Transfer Categories [84].

This section presents surveyed papers covering homogeneous transfer learning solutions and is divided into subsections that correspond to the transfer categories of instance-based, feature-based (both asymmetric and symmetric), parameter-based, and relational-based.

Facility identification and timing, demographics and reason and urgency of transfer categories all had variables with high rates of accuracy.

The microenvironment categories included in the TMAD were walk, bike, motorcycle, car/taxi, bus, tram, metro, and train ("in transfer" categories) and indoors at home, outdoors at home, indoors at work, outdoors at work, indoors at another location, and outdoors at another location ("not in transfer" categories) (Hänninen et al. 2004).

The significant representation within the Kinase and phosphate transfer categories also suggests an active metabolic control "program" occurs when the desiccated cells receive water and attempt to recover from the damage.

This distribution suggests that while mouse lemurs may fall along a continuous range of values, there is evidence of two louse transfer categories: 'donors' that are less likely to receive and more likely to donate lice, and 'recipients' that are more likely to receive and less likely to donate lice.

The second Transfer Category is transfer learning through features.

The first Transfer Category is transfer learning through instances.

Note, the 2SW-MDA approach is an example of an instance-based Transfer Category, but the CP-MDA approach is more appropriately classified as a parameter-based Transfer Category (see "Parameter-based transfer learning" section).

The last transfer category (and the least used approach) is to transfer knowledge based on some defined relationship between the source and target domains (examples in Mihalkova [74] and Li [62]).

The third transfer category is to transfer knowledge through shared parameters of source and target domain learner models or by creating multiple source learner models and optimally combining the reweighted learners (ensemble learners) to form an improved target learner (examples in Gao [37], Bonilla [8], and Evgeniou [33]).