The Advanced Uncertain Reasoning Architecture, AURA
نویسندگان
چکیده
The ADAM binary neural network which has been used for image analysis applications, is con-tructed around a central component termed a Correlation Matrix Memory (CMM). A recent re-examination of the CMM has led to development of the Advanced Uncertain Reasoning Architecture (AURA). AURA inherits many useful characteristics from ADAM, but is intended for applications requiring the manipulation of symbolic knowledge. This paper shows how the AURA architecture has been developed from ADAM and explains its method of operation. The paper also outlines the use of AURA in symbolic processing applications, and highlights some of the ways in which the AURA approach is superior to other methods.
منابع مشابه
A Hardware-Accelerated Novel IR System
AURA (Advanced Uncertain Reasoning Architecture) is a generic family of techniques and implementations intended for high-speed approximate search and match operations on large unstructured datasets. This paper continues the AURA II (Advanced Uncertain Reasoning Architecture) project’s research into distributed binary Correlation Matrix Memory (CMM) based upon the PRESENCE (PaRallEl Structured N...
متن کاملIP / SOC 2004 Session 3 B : Best IP Prize AICP : AURA Intelligent Co - processor for Binary Neural Networks
AURA (Advanced Uncertain Reasoning Architecture) is a generic family of techniques and implementations intended for high-speed approximate search and match operations on large unstructured datasets. AURA technology is based upon binary Correlation Matrix Memories (CMM). This paper describes a high performance IP-core for executing the core AURA operations. The IP-core processes the AURA data in...
متن کاملNeural Networks for Real-time Knowledge Based Applications
The architectures under investigation offer a true integration of symbolic and neural network styles of reasoning in a unified framework. In AURA, the basic functional blocks are neural networks which can perform symbolic reasoning, as well as the pattern processing functions normally associated with neural networks. A further feature of the approach is that a powerful partial-match mechanism s...
متن کاملShort - Term Traffic Prediction Using a Binary Neural Network
This paper presents a binary neural network algorithm for short-term traffic flow prediction. The algorithm can process both univariate and multivariate data from a single traffic sensor using time series prediction (temporal lags) and can combine information from multiple traffic sensors with time series prediction ( spatial-temporal lags). The algorithm provides Intelligent Decision Support (...
متن کاملCellular Associative Neural Networks (CANN)
We propose to present a novel syntactic pattern matching technique [1] that combines the correlative learning and generalisation properties of associative memories, with the parallel and distributed operation of cellular automata [2]. The tool is used for recognizing two dimensional objects in images. Each section of the object to be studied is represented by a cell, initially containing a low ...
متن کامل