Cascade ARTMAP: integrating neural computation and symbolic knowledge processing

نویسنده

  • Ah-Hwee Tan
چکیده

This paper introduces a hybrid system termed cascade adaptive resonance theory mapping (ARTMAP) that incorporates symbolic knowledge into neural-network learning and recognition. Cascade ARTMAP, a generalization of fuzzy ARTMAP, represents intermediate attributes and rule cascades of rule-based knowledge explicitly and performs multistep inferencing. A rule insertion algorithm translates if-then symbolic rules into cascade ARTMAP architecture. Besides that initializing networks with prior knowledge can improve predictive accuracy and learning efficiency, the inserted symbolic knowledge can be refined and enhanced by the cascade ARTMAP learning algorithm. By preserving symbolic rule form during learning, the rules extracted from cascade ARTMAP can be compared directly with the originally inserted rules. Simulations on an animal identification problem indicate that a priori symbolic knowledge always improves system performance, especially with a small training set. Benchmark study on a DNA promoter recognition problem shows that with the added advantage of fast learning, cascade ARTMAP rule insertion and refinement algorithms produce performance superior to those of other machine learning systems and an alternative hybrid system known as knowledge-based artificial neural network (KBANN). Also, the rules extracted from cascade ARTMAP are more accurate and much cleaner than the NofM rules extracted from KBANN.

برای دانلود رایگان متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

ثبت نام

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

منابع مشابه

First-order Cascade ARTMAP

First-order theory refinement using neural networks is still an open problem. Towards a solution to this problem, we define a First-Order extension of the Cascade ARTMAP (FOCA) system, using Inductive Logic Programming techniques. To present such a first-order extension of Cascade ARTMAP, we: a) modify the network structure to handle first-order objects; b) define firstorder versions of the mai...

متن کامل

Conjoint Computing: Integrating Numeric, Symbolic and Neural Computing

This paper describes an ongoing research effort to develop a single, unified computational paradigm for conjoint computing, which integrates concepts from symbolic processing, numeric processing and neural network technologies. The result of this research effort will be a new methodology for synthesizing intelligent systems. Neither the symbolic nor neural computational paradigms is sufficientl...

متن کامل

A Tool for Building Connectionist-like Networks Based on Term Unification

The paper presents a network modeling tool called Net-Clause Language (NCL), integrating some connectionist-like and some symbolic processing features in a uniied computational environment. Unlike the other connectionist symbol processing approaches, NCL represents and processes symbols not by implementing them as patterns of activity in a traditional neural network, rather it uses some connect...

متن کامل

The Grand Challenges and Myths of Neural-Symbolic Computation

The construction of computational cognitive models integrating the connectionist and symbolic paradigms of artificial intelligence is a standing research issue in the field. The combination of logic-based inference and connectionist learning systems may lead to the construction of semantically sound computational cognitive models in artificial intelligence, computer and cognitive sciences. Over...

متن کامل

ذخیره در منابع من


  با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید

عنوان ژورنال:
  • IEEE transactions on neural networks

دوره 8 2  شماره 

صفحات  -

تاریخ انتشار 1997