學術出版;;Publications

Permanent URI for this communityhdl:11536/1

收集所有交通大學研究人員與學生個人或團體所發表之各項學術著作，涵蓋期刊論文、教師專書、學位論文等項。;;Collections of Publications of NCTU Researchers and Students Like Journal Papers and Thesis.

Browse

🏛️國立陽明交通大學機構典藏

Search Results

Now showing 1 - 10 of 11

RELAXATION BY THE HOPFIELD NEURAL NETWORK
(1992-02-01)
YU, SS
;
TSAI, WH
;
資訊工程學系
;
Department of Computer Science
The relaxation process is a useful technique for using contextual information to reduce local ambiguity and achieve global consistency in various applications. It is basically a parallel execution model, adjusting the confidence measures of involved entities based on interrelated hypotheses and confidence measures. On the other hand, the neural network is a computational model with massively parallel execution capability. The output of each neuron depends mainly on the information provided by other neurons. Therefore, there exist certain common properties in the relaxation process and the neural network technique. A mapping method that makes the Hopfield neural network perform the relaxation process is proposed. By this method, the neural network technology can be easily adapted to solve the many problems which have already been solved by the relaxation process. An advantage of this is that the relaxation process can be performed in real time since the Hopfield network can be implemented by conventional analog circuits. Experimental results are given to demonstrate the feasibility of the proposed method by performing the image thresholding operation on the proposed neural network.
NEURAL NETWORK SYNTHESIZER OF PAUSE DURATION FOR MANDARINE TEXT-TO-SPEECH
(1992-04-09)
HWANG, SH
;
CHEN, SH
;
電信工程研究所
;
電信研究中心
;
Institute of Communications Engineering
A neural network based approach of pause-duration synthesis for Mandarin text-to-speech is proposed. It uses an MLP to replace explicit synthesis rules for generating pause duration from input text. By properly training the MLP using a large set of utterances, phonological rules of producing pause duration are automatically learned. Experimental results confirmed that this is a promising approach.
DESIGN OF HOPFIELD-TYPE ASSOCIATIVE MEMORY WITH MAXIMAL BASIN OF ATTRACTION
(1993-11-25)
CHANG, JY
;
WU, CC
;
交大名義發表
;
電控工程研究所
;
National Chiao Tung University
A method is described for enlarging as much as possible the basin of attraction of a Hopfield-type associative memory. The proposed learning rule, a minimum-overlap learning algorithm that includes a threshold parameter, enables a Hopfield-type associative memory to be designed so that the memory will have a maximal basin of attraction. A technique that diminishes the effect of the threshold on the minimum-overlap learning algorithm is devised. Simulation results show that the basin of attraction constructed by the proposed method is indeed larger than that constructed by several well known methods.
SOLVING SYSTEM PARTITIONING PROBLEM USING A MASSIVELY-PARALLEL BIO-COMPUTING NETWORK
(1994)
CHANG, RI
;
HSIAO, PY
;
交大名義發表
;
資訊工程學系
;
National Chiao Tung University
In this paper a massively parallel bio-computing network model is presented for the system partitioning problem in VLSI CAD under timing and capacity constraints. Experiments show that the proposed method was able to find optimal solutions with fast feedback. The future research is to develop a neural network based CAD system for resolving time-consuming VLSI design problems.
COMPLEX-VALUED NEURAL-NETWORK FOR DIRECTION-OF-ARRIVAL ESTIMATION
(1994-03-31)
YANG, WH
;
CHAN, KK
;
CHANG, PR
;
交大名義發表
;
電信工程研究所
A complex-valued neural network for the implementation of a direction of arrival (DoA) estimator is presented. The network is based on the linear prediction method, with data processed fully in the complex domain. Simulation results are given to demonstrate the effectiveness of the network performances.
NEURAL-NETWORK-BASED F0 TEXT-TO-SPEECH SYNTHESIZER FOR MANDARINE
(1994-12-01)
HWANG, SH
;
CHEN, SH
;
電信工程研究所
;
電信研究中心
;
Institute of Communications Engineering
A neural-network-based approach to synthesising F0 information for Mandarin text-to-speech is discussed. The basic idea is to use neural networks to model the relationship between linguistic features, extracted from input text and parameters representing the pitch contour of syllables. Two MLPs are used to separately synthesise the mean and shape of pitch contour, using different linguistic features. A large set of utterances is employed to train these MLPs using the well known back-propagation algorithm. Pronunciation rules for generating F0 information are automatically learned and implicitly memorised by the MLPs. In the synthesis, parameters representing the mean and shape of the pitch contour of each syllable are generated using linguistic features extracted from the given input text. Simulation results confirmed that this is a promising approach for F0 synthesis. The resulting synthesised pitch contours of syllables match well with their original counterparts. Average root mean square errors of 0.94 ms/frame and 1.00ms/frame were achieved.
SPEAKER-INDEPENDENT MANDARINE PLOSIVE RECOGNITION WITH DYNAMIC FEATURES AND MULTILAYER PERCEPTRONS
(1995-02-16)
CHEN, WY
;
CHEN, SH
;
交大名義發表
;
電信工程研究所
;
National Chiao Tung University
A new method for recognising plosives in isolated Mandarin syllables is discussed in the Letter. After automatically detecting the plosive segment of the input utterance, some dynamic features are extracted from its spectral parameter contours using orthonormal polynomial transforms. Next, an MLP trained with an algorithm based on a minimum error criterion is employed to distinguish plosives using these features. A promising recognition rare of 73.6% is achieved in a speaker-independent test using a database containing utterances of 110 syllables uttered by 100 speakers.
NEURO-FUZZY MODELING AND CONTROL
(1995-03-01)
JANG, JSR
;
SUN, CT
;
資訊工程學系
;
Department of Computer Science
Fundamental and advanced developments in neuro-fuzzy synergisms for modeling and control are reviewed. The essential part of neuro-fuzzy synergisms comes from a common framework called adaptive networks, which unifies both neural networks and fuzzy models. The fuzzy models under the framework of adaptive networks is called Adaptive-Network-based Fuzzy Inference System (ANFIS), which possess certain advantages over neural networks. We introduce the design methods for ANFIS in both modeling and control applications. Current problems and future directions for neuro-fuzzy approaches are also addressed.
A NEURAL FUZZY CONTROL-SYSTEM WITH STRUCTURE AND PARAMETER LEARNING
(1995-03-20)
LIN, CT
;
交大名義發表
;
電控工程研究所
;
National Chiao Tung University
;
Institute of Electrical and Control Engineering
A general connectionist model, called neural fuzzy control network (NFCN), is proposed for the realization of a fuzzy logic control system. The proposed NFCN is a feedforward multilayered network which integrates the basic elements and functions of a traditional fuzzy logic controller into a connectionist structure which has distributed learning abilities. The NFCN can be constructed from supervised training examples by machine learning techniques, and the connectionist structure can be trained to develop fuzzy logic rules and find membership functions. Associated with the NFCN is a two-phase hybrid learning algorithm which utilizes unsupervised learning schemes for structure learning and the backpropagation learning scheme for parameter learning. By combining both unsupervised and supervised learning schemes, the learning speed converges much faster than the original backpropagation algorithm. The two-phase hybrid learning algorithm requires exact supervised training data for learning. In some real-time applications, exact training data may be expensive or even impossible to obtain. To solve this problem, a reinforcement neural fuzzy control network (RNFCN) is further proposed. The RNFCN is constructed by integrating two NFCNs, one functioning as a fuzzy predictor and the other as a fuzzy controller. By combining a proposed on-line supervised structure-parameter learning technique, the temporal difference prediction method, and the stochastic exploratory algorithm, a reinforcement learning algorithm is proposed, which can construct a RNFCN automatically and dynamically through a reward-penalty signal (i.e., ''good' or ''bad'' signal), Two examples are presented to illustrate the performance and applicability of the proposed models and learning algorithms.
A FUZZY NEURAL-NETWORK FOR RULE ACQUIRING ON FUZZY CONTROL-SYSTEMS
(1995-05-12)
SHANN, JJ
;
FU, HC
;
交大名義發表
;
資訊工程學系
;
National Chiao Tung University
This paper presents a layer-structured fuzzy neural network (FNN) for learning rules of fuzzy-logic control systems. Initially, FNN is constructed to contain all the possible fuzzy rules. We propose a two-phase learning procedure for this network. The first phase is a error-backprop (EBP) training, and the second phase is a rule pruning. Since some functions of the nodes in the FNN have the competitive characteristics, the EBP training will converge quickly. After the training, a pruning process is performed to delete redundant rules for obtaining a concise fuzzy rule base. Simulation results show that for the truck backer-upper control problem, the training phase learns the knowledge of fuzzy rules in several dozen epochs with an error rate of less than 1%. Moreover, the fuzzy rule base generated by the pruning process contains only 14% of the initial fuzzy rules and is identical to the target fuzzy rule base.

學術出版;;Publications

Browse

Filters

Settings

Sort By

Results per page

🏛️國立陽明交通大學機構典藏

Search Results