A Self-configuring Network

Connectionist research today is inhibited by two kinds of rigidity. First, a rigidity in architecture: the connectivity of most networks is fixed at the start by the programmer. This limits the universality of learning procedures. Secondly, a mental rigidity: the widespread assumption that a node's activation must be a real number and that activations should be combined using weighted sums. This paper explores the consequences of relaxing these rigidities. I describe a neural network for unsupervised pattern learning. Given an arbitrary environment of input patterns it grows into a configuration which allows it to represent the high-level regularities in the input. Like the Boltzmann machine, it runs in two phases: observing the environment and simulating the environment. It continually monitors its own performance and grows new nodes as the need for them is identified. Simulating the environment involves repeatedly choosing states to satisfy many constraints. The usual method is to maximize a ‘harmony’ function, which leads to a merging or blending of constraints: this lacks a clear semantics. My network uses logical inference to settle into a state consistent with as many as possible of the strongest constraints.     

Combining Prior Symbolic Knowledge and Constructive Neural Network Learning

The concepts of knowledge-based systems and machine learning are combined by integrating an expert system and a constructive neural networks learning algorithm. Two approaches are explored: embedding the expert system directly and converting the expert system rule base into a neural network. This initial system is then extended by constructively learning additional hidden units in a problem-specific manner. Experiments performed indicate that generalization of a combined system surpasses that of each system individually.     

混凝土强度无损检测数据处理的混沌优化神经网络模型

依据混凝土标准试块强度检测数据，建立了混沌优化的神经网络计算模型，从而克服传统BP网络收敛速度慢、易出现麻痹现象等不足。与混凝土无损检测现行规程规定的方法相比较，谊计算模型简单可行，搜索速度快，预测结果可靠、精度高。     

A Hybrid Symbolic/Connectionist Model for Noun Phrase Understanding

This paper describes a hybrid model which integrates symbolic and connectionist techniques for the analysis of noun phrases. Our model consists of three levels: (1) a distributed connectionist level, (2) a localist connectionist level, and (3) a symbolic level. While most current systems in natural language processing use techniques from only one of these three levels, our model takes advantage of the virtues of all three processing paradigms. The distributed connectionist level provides a learned semantic memory model. The localist connectionist level integrates semantic and syntactic constraints. The symbolic level is responsible for restricted syntactic analysis and concept extraction. We conclude that a hybrid model is potentially stronger than models that rely on only one processing paradigm.     

Perceptually Grounded Language Learning: Part 1—A Neural Network Architecture for Robust Sequence Association

In this two-part series, we explore how a perceptually based foundation for natural language semantics might be acquired, via association of sensory/motor experiences with verbal utterances describing those experiences. In Part 1, we introduce a novel neural network architecture, termed Katamic memory, that is inspired by the neurocircuitry of the cerebellum and that exhibits (a) rapid/robust sequence learning/recogmtion and (b) allows integrated learning and performance. These capabilities are due to novel neural elements, which model dendritic structure and function in greater detail than in standard connectionist models. In Part 2, we describe the DETE system, a massively parallel proceduraljneural hybrid model that utilizes over 50 Katamic memory modules to perform two associative learning tasks: (a) verbal-to-visual / motor association—given a verbal sequence, DETE learns to regenerate a neural representation of the visual sequence being described and/or to carry out motor commands; and (b) visual/motor-to-verbal association—given a visual/motor sequence, DETE learns to produce a verbal sequence describing the visual input. DETE can learn verbal sequences describing spatial relations and motions of 2D 'blob-like objects; in addition, the system can also generalize to novel inputs. DETE has been tested successfully on small, restricted subsets of English and Spanish—languages that differ in inflectional properties, word order and how they categorize perceptual reality.     

A Unified Error Model for Tolerance Design, Assembly and Error Compensation of 3-DOF Parallel Kinematic Machines with Parallelogram Struts

This paper presents a unified geometric error model that enables the tolerance design, assembly and calibration of a class of 3-DOF parallel kinematic machines with parallelogram struts to be integrated into a comprehensive framework. The error mapping function is formulated with a goal that enables the source errors affecting the uncompensatable pose error to be found. This is followed by the investigation into the influences of source errors on the pose accuracy with the aid of sensitivity analysis. The assembly process that enables to effectively reduce the uncompensatable pose error is also proposed.