Distributed Learning of CNNs on Heterogeneous CPU/GPU Architectures
نویسندگان
چکیده
منابع مشابه
Distributed learning of CNNs on heterogeneous CPU/GPU architectures
Convolutional Neural Networks (CNNs) have shown to be powerful classification tools in tasks that range from check reading to medical diagnosis, reaching close to human perception, and in some cases surpassing it. However, the problems to solve are becoming larger and more complex, which translates to larger CNNs, leading to longer training times—the computational complex part—that not even the...
متن کاملOn Accepting Heterogeneous Ontologies in Distributed Architectures
Enforcing ontologies as conceptualisation standards in distributed architectures has some important drawbacks. It is, for instance, no solution for the legacy problem. In this article we address the possibility of accepting multiple heterogeneous ontologies in a distributed architecture. After discussing alternative ways to relate several ontologies we look into one particular (hierarchical) co...
متن کاملHeterogeneous Ontology Structures for Distributed Architectures
Enforcing ontologies as conceptualisation standards in distributed architectures has some well-known drawbacks. It is, for instance, no solution for the legacy problem. In this article we describe an experiment in accepting structures of (multiple) heterogeneous ontologies for use in distributed architectures. After discussing alternative ways to relate several ontologies we look into one parti...
متن کاملHeterogeneous Face Recognition with CNNs
Heterogeneous face recognition aims to recognize faces across different sensor modalities. Typically, gallery images are normal visible spectrum images, and probe images are infrared images or sketches. Recently significant improvements in visible spectrum face recognition have been obtained by CNNs learned from very large training datasets. In this paper, we are interested in the question to w...
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: Applied Artificial Intelligence
سال: 2018
ISSN: 0883-9514,1087-6545
DOI: 10.1080/08839514.2018.1508814