Learning to weave; weaving to learn ... what?
نویسندگان
چکیده
منابع مشابه
Learning What Data to Learn
Machine learning is essentially the sciences of playing with data. An adaptive data selection strategy, enabling to dynamically choose different data at various training stages, can reach a more effective model in a more efficient way. In this paper, we propose a deep reinforcement learning framework, which we call Neural Data Filter (NDF), to explore automatic and adaptive data selection in th...
متن کاملHow to Learn/What to Learn
Abst rac t : This paper discusses the kind of in fo rmat ion that must be present in a computer program that models the l i n g u i s t i c development of a c h i l d . A three stage model is presented that character izes the development of a na tu ra l l a n guage parser in a c h i l d of ages one, one and a h a l f , and two. Some data from ch i ld ren of these ages is presented. General prob...
متن کاملInfants Learn What They Want to Learn: Responding to Infant Pointing Leads to Superior Learning
The majority of current developmental models prioritise a pedagogical approach to knowledge acquisition in infancy, in which infants play a relatively passive role as recipients of information. In view of recent evidence, demonstrating that infants use pointing to express interest and solicit information from adults, we set out to test whether giving the child the leading role in deciding what ...
متن کاملTask Structures: What To Learn?
Broadly characterized, learning can improve problem-solving performance by increasing its efficiency and effectiveness, and by improving the quality of produced solutions. Traditional AI systems have limited the role of learning to the first two performance-improvement goals. We have developed a reflection process that uses a model of the system’s functional architecture to monitor its performa...
متن کاملLearning to learn categories
Learning to categorize objects in the world is more than just learning the specific facts that characterize individual categories. We can also learn more abstract knowledge about how categories in a domain tend to be organized – extending even to categories that we’ve never seen examples of. These abstractions allow us to learn and generalize examples of new categories much more quickly than if...
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: Journal of the Royal Anthropological Institute
سال: 2010
ISSN: 1359-0987,1467-9655
DOI: 10.1111/j.1467-9655.2010.01615.x