This paper presents a pipelined match-line and a hierarchical search-line architecture to reduce power in contentaddressable memories (CAM). The overall power reduction is 60%, with 29% contributed by the pipelined match-lines and 31% contributed by the hierarchical search-lines. This proposed architecture is employed in the design of a 1024×144 bit ternary CAM, achieving 7 ns search cycle time...

We present a learning architecture for lexical semantic classification problems that supplements task-specific training data with background data encoding general “world knowledge”. The model compiles knowledge contained in a dictionaryontology into additional training data, and integrates task-specific and background data through a novel hierarchical learning architecture. Experiments on a wor...

As a result of not running appropriately the software development process, many problems occurs. One of important these problems is not forming software architecture. Analysis, development and testing will become harder, maybe impossible with a system without software architecture.For this reason, focused on software architecture recovery from source code and tested various methods. While lack ...

This paper presents a pipelined architecture for the hierarchical block-matching motion estimation algorithm (HBMA). The hierarchical style leads enormous computation and complex data flow between hierarchy levels. Each stage of the proposed architecture consists of a systolic array for block-matching and an interpolation unit for bilinear interpolation. The interpolation unit regulates also th...

Hierarchical block matching is an eecient motion estimation technique which provides an adaptation of the block size and the search area to the properties of the image. In this work, we propose two novel special-purpose architec-tures for implementing hierarchical block matching. The rst architecture is memory-eecient, but requires a large external memory bandwidth and a large number of process...

An architecture for supervision and programming by demonstration in robotized assembly is presented. This architecture provides, at different levels of abstraction, functions for dispatching actions, monitoring their execution, and diagnosing and recovering from failures. Through the use of machine learning techniques, the supervision architecture is given capabilities for improving its perform...

Many time series of practical relevance data have multi-scale characteristics. Prime examples are speech, texts, writing, or gestures. If one wishes to learn models of such systems, the models must be capable to represent dynamical features on different temporal and/or spatial scales. One natural approach to this end is hierarchical models, where higher processing layers are responsible for pro...

Unexpected events in hierarchical production planning, such as rush orders, labor problems, lack of availability of materials and faulty machines have to be managed efficiently because they represent a risk for business continuity, based on their impact and duration. The use of inter-enterprise architecture offers multiple benefits for collaborative networks, including: business strategy and in...

Hierarchical event correlation is very important for distributed monitoring network and distributed system operations. In many largescale distritbuted monitoring environments such as monitions senor networks for data aggregation, battlefield compact operations, and security events, an efficient hierarchical monitoring agent architecture must be constructed to facilitate event reporting and corr...