Presenting dynamically expandable hypermedia
نویسندگان
چکیده
منابع مشابه
Presenting dynamically expandable hypermedia
The Multimedia Information Presentation System (MIPS) will allow end-users to browse multimedia information presented in a user-friendly and consistent manner. In its most powerful configuration, it will allow the end-user to formulate queries which are interpreted, analysed , and despatched by the system to heterogeneous distributed external data sources, and to view a coherent and customized ...
متن کاملLifelong Learning with Dynamically Expandable Networks
We propose a novel deep network architecture for lifelong learning which we refer to as Dynamically Expandable Network (DEN), that can dynamically decide its network capacity as it trains on a sequence of tasks, to learn a compact overlapping knowledge sharing structure among tasks. DEN is efficiently trained in an online manner by performing selective retraining, dynamically expands network ca...
متن کاملContext-aware Hypermedia in a Dynamically Changing
Context-Aware Hypermedia in a Dynamically Changing Environment, Supported by a High-Level Petri Net. (December 2001) Jin-Cheon Na, B.S., Hanyang University; M.S., Oklahoma State University Chair of Advisory Committee: Dr. Richard Furuta In modern hypertext systems, with the increased availability of personal computers with environmental sensors (e.g., GPS sensors), adaptation support to meet th...
متن کاملA Model Adapting Dynamically an Online Hypermedia Learning
For a few years, the concept of hypermedia has become closely related to the eLearning thanks to its important contribution covering informational, navigational and interactional dimensions. However, the various studies and experiments carried out recently made it possible to identify certain possibilities for improvements being able to be beneficial with the process of learning. One of these i...
متن کاملDataflow matrix machines as programmable, dynamically expandable, self-referential generalized recurrent neural networks
Dataflow matrix machines are a powerful generalization of recurrent neural networks. They work with multiple types of linear streams and multiple types of neurons, including higher-order neurons which dynamically update the matrix describing weights and topology of the network in question while the network is running. It seems that the power of dataflow matrix machines is sufficient for them to...
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: Information and Software Technology
سال: 1995
ISSN: 0950-5849
DOI: 10.1016/0950-5849(95)91490-q