This paper presents an analysis of Correlation Matrix Memory (CMM), a binary associative neural network. CMM has been proposed as an inference engine, which could be utilized in an expert system (Austin, 1994). In this role, CMM encodes Tensor Products (Smolensky, 1990) to support Dynamic Variable Binding. The ability to perform partial match efficiently, with a large body of stored information...

This survey paper shows different mechanisms for controlling congestion in ATM network and some suggested solution for the existing mechanism to be modified using fuzzy logic. Different mechanisms are Jump Window (JW), Exponentially Weighted Moving Average (EWMA), and traditional Leaky Bucket (LB) and Fuzzy Leaky Bucket Algorithm. The Fuzzy Leaky Bucket (FLB) modifies the token rate according t...

An inference engine for classification of Electrocardiogram (ECG) signals is developed with the help of a rule based rough set decision system. For this purpose an automated data extraction system from ECG strips is being developed by using a few image processing techniques. A knowledge base is developed after consulting different medical books as well as feedback of reputed cardiologists on in...

Declarative systems aim at solving tasks by running inference engines on a specification, to free its users from having to specify how a task should be tackled. In order to provide such functionality, declarative systems themselves apply complex reasoning techniques, and, as a consequence, the development of such systems can be laborious work. In this paper, we demonstrate that the declarative ...

Compared to physiologically based biometric systems such as fingerprint, face, palm-vein and retina, behavioral based biometric systems such as signature, voice, gait, etc. are less popular and many of the research in these areas are still in their infancy. One of the reasons is due to the inconsistencies in human behavior which requires more robust algorithms in their developments. In this pap...

An inference engine using fuzzy logic is proposed for the analysis of Likert-type questionnaire. This method was used to understand and incorporate the imprecision of items in a questionnaire so that a single score that encompassed the different scales of the questionnaire could be created. A parent-rated questionnaire called the Parent Checklist of Peer Relationships (PCPR) was used as an exam...

Training of the neural autoregressive density estimator (NADE) can be viewed as doing one step of probabilistic inference on missing values in data. We propose a new model that extends this inference scheme to multiple steps, arguing that it is easier to learn to improve a reconstruction in k steps rather than to learn to reconstruct in a single inference step. The proposed model is an unsuperv...

Training a structured prediction model involves performing several loss-augmented inference steps. Over the lifetime of the training, many of these inference problems, although different, share the same solution. We propose AI-DCD, an Amortized Inference framework for Dual Coordinate Descent method, an approximate learning algorithm, that accelerates the training process by exploiting this redu...

A fuzzy logic controller with interval-valued inference mechanism is presented for the control of distributed parameter system (DPS). Interval-valued fuzzy set, a special case of type-2 fuzzy set, is innovatively designed to cope with the spatial information of distributed parameter systems. The proposed fuzzy logic controller is composed of six modules: fuzzifier, fuzzy composition, rules, inf...