Topic
Hybrid neural network
About: Hybrid neural network is a research topic. Over the lifetime, 1305 publications have been published within this topic receiving 18223 citations.
Papers published on a yearly basis
Papers
More filters
18 Jul 2021
25 Apr 2005
TL;DR: A new method for storing and programming digital weights in a hybrid neural network using pulse-coupled communication between neurons, compatible with typical CMOS processes, and analog multiplication and addition for modeling neural behavior is presented.
Abstract: This paper presents a new method for storing and programming digital weights in a hybrid neural network. The network uses pulse-coupled communication between neurons, compatible with typical CMOS processes, and analog multiplication and addition for modeling neural behavior. Programming of individual neurons is done using existing interconnect, eliminating the need for additional inputs or wiring. Furthermore, the weight storage network supports direct addressing of synaptic weights, allowing the implementation of adaptation and learning. Results from a 4-4-3 array, fabricated in a 1.5 micron process, are presented.
•
18 Apr 2019
TL;DR: In this article, a hybrid neural network prediction model was used to determine the spending power of a target user with respect to a target object, based on the combination of the one or more pieces of statistical feature data and the timing sequence feature data.
Abstract: An embodiment of the present invention relates to the technical field of computers, and provided thereby are a method and apparatus for predicting spending power, as well as an electronic device and a readable storage medium. According to an embodiment of the described method, by means of acquiring from among historical data of a target user one or more pieces of statistical feature data and one or more pieces of timing sequence feature data for a target object, a preset hybrid neural network prediction model may, on the basis of the one or more pieces of statistical feature data and the one or more pieces of timing sequence feature data, be used to determine the spending power of the target user with respect to the target object.
••
26 May 2009TL;DR: It has been indicated that the injection parameter optimization method based on the hybrid neural network and genetic algorithm approach is feasible and the BP network is stable and reliable.
Abstract: In this paper, an optimization system is established based on a hybrid neural network and genetic algorithm approach. The application program is compiled in Matlab engineering computing language, which is used in calculating the parameter value predicted by neural network and the result of genetic algorithm optimization .The comparison and error analysis has been carried out between the results predicted by network and CAE simulated results, which shows that the BP network is stable and reliable. The optimized outcome verified by CAE simulation and tested by experiment has been proved to be correct. It has been bean indicated that the injection parameter optimization method based on the hybrid neural network and genetic algorithm approach is feasible.
••
20 Jul 2003TL;DR: A hybrid feature evaluation method using a competitive learning neural network and fuzzy logic for the analysis of high dimensional data to discover the nature of data represented by multiple features by evaluating the importance of features representing data and the data best describing the information embedded by features.
Abstract: This paper presents a hybrid feature evaluation method using a competitive learning neural network and fuzzy logic for the analysis of high dimensional data. Not only can we give the quantitative information of the relative importance of features but the contributions of features to each data category can be observed during the analysis. The motivation of this study is to provide a method to discover the nature of data represented by multiple features by evaluating the importance of features representing data and the data best describing the information embedded by features.