The Experts below are selected from a list of 256410 Experts worldwide ranked by ideXlab platform
Anastasios Tefas - One of the best experts on this subject based on the ideXlab platform.
-
learning deep representations with probabilistic Knowledge Transfer
European Conference on Computer Vision, 2018Co-Authors: Nikolaos Passalis, Anastasios TefasAbstract:Knowledge Transfer (KT) techniques tackle the problem of Transferring the Knowledge from a large and complex neural network into a smaller and faster one. However, existing KT methods are tailored towards classification tasks and they cannot be used efficiently for other representation learning tasks. In this paper we propose a novel probabilistic Knowledge Transfer method that works by matching the probability distribution of the data in the feature space instead of their actual representation. Apart from outperforming existing KT techniques, the proposed method allows for overcoming several of their limitations providing new insight into KT as well as novel KT applications, ranging from KT from handcrafted feature extractors to cross-modal KT from the textual modality into the representation extracted from the visual modality of the data.
-
probabilistic Knowledge Transfer for deep representation learning
2018Co-Authors: Nikolaos Passalis, Anastasios TefasAbstract:Knowledge Transfer (KT) techniques tackle the problem of Transferring the Knowledge from a large and complex neural network into a smaller and faster one. However, existing KT methods are tailored towards classification tasks and they cannot be used efficiently for other representation learning tasks. In this paper a novel Knowledge Transfer technique, that is capable of training a student model that maintains the same amount of mutual information between the learned representation and a set of (possible unknown) labels as the teacher model, is proposed. Apart from outperforming existing KT techniques, the proposed method allows for overcoming several limitations of existing methods providing new insight into KT as well as novel KT applications, ranging from Knowledge Transfer from handcrafted feature extractors to {cross-modal} KT from the textual modality into the representation extracted from the visual modality of the data.
-
learning deep representations with probabilistic Knowledge Transfer
arXiv: Learning, 2018Co-Authors: Nikolaos Passalis, Anastasios TefasAbstract:Knowledge Transfer (KT) techniques tackle the problem of Transferring the Knowledge from a large and complex neural network into a smaller and faster one. However, existing KT methods are tailored towards classification tasks and they cannot be used efficiently for other representation learning tasks. In this paper a novel Knowledge Transfer technique, that is capable of training a student model that maintains the same amount of mutual information between the learned representation and a set of (possible unknown) labels as the teacher model, is proposed. Apart from outperforming existing KT techniques, the proposed method allows for overcoming several limitations of existing methods providing new insight into KT as well as novel KT applications, ranging from Knowledge Transfer from handcrafted feature extractors to {cross-modal} KT from the textual modality into the representation extracted from the visual modality of the data.
Andrew C Inkpen - One of the best experts on this subject based on the ideXlab platform.
-
Knowledge Transfer and international joint ventures the case of nummi and general motors
Southern Medical Journal, 2008Co-Authors: Andrew C InkpenAbstract:Using a case study of NUMMI, a joint venture between General Motors (GM) and Toyota, this research note examines alliances and Knowledge Transfer with a focus on the organizational processes used to Transfer Knowledge. The results suggest two possible explanations for the Knowledge Transfer outcome. The primary explanation is that the systematic implementation of Knowledge Transfer mechanisms can overcome the stickiness and causal ambiguity of new Knowledge. A second explanation is that creating successful Knowledge Transfer should be viewed from a change management perspective in which trial and error learning experiences and experimentation support the Transfer outcome. Copyright © 2007 John Wiley & Sons, Ltd.
-
an examination of collaboration and Knowledge Transfer china singapore suzhou industrial park
Journal of Management Studies, 2006Co-Authors: Andrew C Inkpen, Wang PienAbstract:This paper examines alliance Knowledge Transfer using a case study of the China-Singapore Suzhou Industrial Park (SIP), an alliance involving the Chinese and Singaporean governments, their agencies, and various private sector organizations. The objective is to extend existing Knowledge in the alliance learning area and provide deeper understanding of some process-oriented aspects of alliance learning performance. We found that tacit Knowledge was particularly difficult to Transfer and that issues involving collaborative interactions between the partners both facilitated and impeded Knowledge Transfer. We also found that competitive learning occurred, which impacted the partner relationship and Knowledge Transfer. Copyright Blackwell Publishing Ltd 2006.
-
social capital networks and Knowledge Transfer
Academy of Management Review, 2005Co-Authors: Andrew C Inkpen, Eric W K TsangAbstract:We examine how social capital dimensions of networks affect the Transfer of Knowledge between network members. We distinguish among three common network types: intracorporate networks, strategic alliances, and industrial districts. Using a social capital framework, we identify structural, cognitive, and relational dimensions for the three network types. We then link these social capital dimensions to the conditions that facilitate Knowledge Transfer. In doing so, we propose a set of conditions that promote Knowledge Transfer for the different network types.
Eric W K Tsang - One of the best experts on this subject based on the ideXlab platform.
-
social capital networks and Knowledge Transfer
Academy of Management Review, 2005Co-Authors: Andrew C Inkpen, Eric W K TsangAbstract:We examine how social capital dimensions of networks affect the Transfer of Knowledge between network members. We distinguish among three common network types: intracorporate networks, strategic alliances, and industrial districts. Using a social capital framework, we identify structural, cognitive, and relational dimensions for the three network types. We then link these social capital dimensions to the conditions that facilitate Knowledge Transfer. In doing so, we propose a set of conditions that promote Knowledge Transfer for the different network types.
Brian S Silverman - One of the best experts on this subject based on the ideXlab platform.
-
strategic alliances and interfirm Knowledge Transfer
Strategic Management Journal, 1996Co-Authors: David C Mowery, Joanne E Oxley, Brian S SilvermanAbstract:This paper examines interfirm Knowledge Transfers within strategic alliances. Using a new measure of changes in alliance partners' technological capabilities, based on the citation patterns of their patent portfolios, we analyze changes in the extent to which partner firms' technological resources ‘overlap’ as a result of alliance participation. This measure allows us to test hypotheses from the literature on interfirm Knowledge Transfer in alliances, with interesting results: we find support for some elements of this ‘received wisdom’—equity arrangements promote greater Knowledge Transfer, and ‘absorptive capacity’ helps explain the extent of technological capability Transfer, at least in some alliances. But the results also suggest limits to the ‘capabilities acquisition’ view of strategic alliances. Consistent with the argument that alliance activity can promote increased specialization, we find that the capabilities of partner firms become more divergent in a substantial subset of alliances.
S. X. Zeng - One of the best experts on this subject based on the ideXlab platform.
-
collaborative innovation network and Knowledge Transfer performance a fsqca approach
Journal of Business Research, 2016Co-Authors: Liangxiu Fang, S. X. ZengAbstract:Under the context of “open innovation”, scholars increasingly consider collaborative innovation network as an effective framework to enable firms' Knowledge Transfer. This study examines four factors of collaborative innovation network that affect the level of Knowledge Transfer performance of firms, viz., network size, network heterogeneity, network tie-strength, and network centrality. Based on a survey to high-tech firms in China, this study uses fuzzy-set Qualitative Comparative Analysis (fsQCA) to explore the relationships between collaborative innovation network and Knowledge Transfer performance. This study supports the argument that different causal paths explain Knowledge Transfer performance of firms. The findings reveal that the presence of network size, network tie-strength, and network centrality determines the level of Knowledge Transfer performance. However, network heterogeneity does not show significant impact on the Knowledge Transfer performance. The findings also identify theoretical and practical implications of collaborative innovation network and Knowledge Transfer research.
