Global ETD Search
Search theses and dissertations gathered from participating repositories worldwide. Every result links back to the library that holds it. No account is needed.
Results
Showing 1 to 10 of 10 for “"Neural logic"”.
-
Differentiable neural logic networks and their application onto inductive logic programming
Despite the impressive performance of Deep Neural Networks (DNNs), they usually lack the explanatory power of disciplines such as logic programming. Even though they can learn to solve very difficult problems, the learning is usually implicit and it is very difficult, if not impossible, to …
-
AN ON-LINE CHINESE CHARACTER RECOGNITION SYSTEM USING COMPLEX NEURAL LOGIC NETWORKS
… system. It is based on a new class of neural networks known as neural logic networks which is being researched at the Institute of Systems Science, National University of Singapore. Using the pattern recognition ability of complex neural logic networks, an implementation of a fast and …
-
Strain Variation as a Window Into the Neural Logic of Drosophila Mate Choice
… for over a century to understand the genetic and neural underpinnings of flexible, hard-wired behavior. Courtship–particularly on the crowded wild food patches where flies congregate to mate–is a dynamic interaction between a male and surrounding potential partners that requires he integrate …
-
FUZZY NEURAL NETWORK WITH APPLICATION TO DECISION SUPPORT SYSTEM
… is the design of FUZZY NELONET DSS or FUZZY NEural LOgic NETwork based Decision Support System [Nah F.H. (1991)] which incorporates a neural network approach, Fuzzy Neural Logic Network [Hsu L.S., et. al. (1989a, 1989b, 1990a, 1990b, 1990c, 1990d)], into the three components of a decision …
-
Autonomous star identification with neural networks
… feature patterns in the database increase. Fuzzy logic and neural networks can help deal with these problems. The parallelism of neural networks can help speed pattern search and fuzzy logic helps deal with measurement uncertainty. The fuzzy Neural Logic Network (NLN) is a neural network model …
-
Semantic scene understanding for intelligent robotics
… the segmented point clouds are identified by a neural-logic network that incorporates general knowledge of spatial constraints in terms of first-order logic. The proposed HRI interface superimposes robot-centered and human-centered reality on the working space to construct a mutual understanding …
-
A Secure Neuromemristive Primitive to Mitigate Correlation Power Analysis on SHA-3 Hash Function
… mitigations are created to exploit dual-rail logic. A secure neuromemristive primitive is designed using neural logic blocks that, to the best of our knowledge, have not been considered by others in mitigation of power analysis. Also, an in-depth analysis of power attacks on linear functions …
-
INTEGRATING RULE-BASED EXPERT SYSTEM AND NEURAL NETWORK FOR DECISION SUPPORT
… two broad categories, connectionist systems (neural networks) and artificial intelligence symbolic systems (rule-based systems). They have been regarded as two fundamentally different computational paradigms for knowledge representation and processing. This thesis integrates the complementary …
-
Connecting Female Mating Decisions and Male Courtship Strategies in Drosophila
… to attract females or repel rival males. The neural mechanisms mediating these male behavioral traits and how females use them to guide their mating decisions remain elusive. In this thesis,I present our efforts to uncover the neural logic underlying mate selection in Drosophila melanogaster. …