Knowledge transfer: what, how, and why
نویسنده
چکیده
People learn and induce from prior experiences. We first learn how to use a spoon and then know how to use forks of various sizes. We first learn how to sew and then learn how to embroider. Transferring knowledge from one situation to another related situation often increases the speed and quality of learning. This observation is relevant to human learning, as well as machine learning. This thesis focuses on the problem of knowledge transfer in the context of machine learning and information science. The goal of knowledge transfer is to train a system to recognize and apply knowledge acquired from previous tasks to new tasks or new domains. An effective knowledge transfer system facilitates the learning processes for novel tasks, where little information is available. For example, the ability to transfer knowledge from a model that identifies writers born in the U.S. to identify writers born in Kiribati, a much lesser known country, would increase the speed of learning to identify writers born in Kiribati from scratch. In this thesis, we investigate three dimensions of knowledge transfer: what, how, and why. We present and elaborate on these questions: What type of knowledge should we transfer? How should we transfer knowledge across entities? Why do we observe certain pattern of knowledge transfer? We first propose Segmented Transfer – a novel knowledge transfer model – to identify and learn from the most informative partitions from prior tasks. We apply the proposed model to the problem of Wikipedia vandalism detection and entity search and classification.
منابع مشابه
The Why, Who, What, How, and When of Patient Engagement in Healthcare Organizations: A Response to Recent Commentaries
متن کامل
A Brief Philosophical Encounter with Science and Medicine
We show a lot of respect for science today. To back up our claims, we tend to appeal to scientific methods. It seems that we all agree that these methods are effective for gaining the truth. We can ask why science has its special status as a supplier of knowledge about our external world and our bodies. Of course, one should not always trust what scientists say. Nonetheless, epistemological jus...
متن کاملAging, Pensions and Long-term Care: What, Why, Who, How?; Comment on “Financing Long-term Care: Lessons From Japan”
Japan has been aging faster than other industrialized nations, and its experience offers useful lessons to others. Japan has been willing to expand its welfare state with a long-term care (LTC) insurance to finance home care and nursing home care for frail elderly. As Ikegami shows, it created new facilities and expanded specialized staffing for home care, developed a c...
متن کاملUnderstanding Personal Practical Knowledge; From what teachers must know to what teachers already know
The purpose of this study is understanding the Personal Practical Knowledge (PPK) of teachers which has been done through qualitative method. Understanding PPK helps us to understand why teachers act in a specific way. In this regards, reflecting on their personal and professional narratives also help to improve their practice. This study was conducted along with 13 teachers in a non-profit pri...
متن کاملWhat helps where - and why? Semantic relatedness for knowledge transfer
Remarkable performance has been reported to recognize single object classes. Scalability to large numbers of classes however remains an important challenge for today’s recognition methods. Several authors have promoted knowledge transfer between classes as a key ingredient to address this challenge. However, in previous work the decision which knowledge to transfer has required either manual su...
متن کامل