• 전자공학회논문지B
• /
• 제31B권4호
• /
• pp.138-144
• /
• 1994

An inference network is proposed as a tool for bidirectional approximate reasoning. The inference network can be designed directly from the given fuzzy data(knowledge). If a fuzzy input is given for the inference netwok, then the network renders a reasonable fuzzy output after performing approximate reasoning based on an equality measure. Conversely, due to the bidirectional structure, the network can yield its corresponding reasonable fuzzy input for a given fuzzy output. This property makes it possible to perform forward and backward reasoning in the knowledge base system.

• ETRI Journal
• /
• 제43권4호
• /
• pp.684-693
• /
• 2021

This paper presents a low-cost two-stage approximate multiplier for bfloat16 (brain floating-point) data processing. For cost-efficient approximate multiplication, the first stage implements Mitchell's algorithm that performs the approximate multiplication using only two adders. The second stage adopts the exact multiplication to compensate for the error from the first stage by multiplying error terms and adding its truncated result to the final output. In our design, the low-cost multiplications in both stages can reduce hardware costs significantly and provide low relative errors by compensating for the error from the first stage. We apply our approximate multiplier to the convolutional neural network (CNN) inferences, which shows small accuracy drops with well-known pre-trained models for the ImageNet database. Therefore, our design allows low-cost CNN inference systems with high test accuracy.

• 한국지능시스템학회:학술대회논문집
• /
• 한국퍼지및지능시스템학회 1993년도 Fifth International Fuzzy Systems Association World Congress 93
• /
• pp.1274-1276
• /
• 1993

We have designed a multiple-valued fuzzy Approximate Analogical-Reseaning system (AARS). The system uses a similarity measure of fuzzy sets and a threshold of similarity ST to determine whether a rule should be fired, with a Modification Function inferred from the Similarity Measure to deduce a consequent. Multiple-valued basic fuzzy blocks are used to construct the system. A description of the system is presented to illustrate the operation of the schema. The results of simulations show that the system can perform about 3.5 x 106 inferences per second. Finally, we compare the system with Yamakawa's chip which is based on the Compositional Rule of Inference (CRI) with Mamdani's implication.

• 한국전산구조공학회:학술대회논문집
• /
• 한국전산구조공학회 2000년도 봄 학술발표회논문집
• /
• pp.449-457
• /
• 2000

The paper describes the study of global approximate optimization utilizing soft computing techniques such as genetic algorithms (GA's), neural networks (NN's), and fuzzy inference systems(FIS). GA's provide the increasing probability of locating a global optimum over the entire design space associated with multimodality and nonlinearity. NN's can be used as a tool for function approximations, a rapid reanalysis model for subsequent use in design optimization. FIS facilitates to handle the quantitative design information under the case where the training data samples are not sufficiently provided or uncertain information is included in design modeling. Properties of soft computing techniques affect the quality of global approximate model. Evolutionary fuzzy modeling (EFM) and adaptive neuro-fuzzy inference system (ANFIS) are briefly introduced for structural optimization problem in this context. The paper presents the success of EFM depends on how optimally the fuzzy membership parameters are selected and how fuzzy rules are generated.

• 전자공학회논문지C
• /
• 제34C권10호
• /
• pp.98-105
• /
• 1997

In this work, we proesent a bidirectional approximate reasoning method and fuzzy inference network for interval valued decision making systems. For this, we propose a new type of similarity measure between two fuzzy vectors based on the Ordered Weighted Averaging (OWA) operator. Since the proposed similarity measure has a structure to give the extreme values by choosing a suitable weighting vector of the OWA operator, it can render an interval valued similarity value. From this property, we derive a bidirectional approximate reasoning method based on the similarity measure and show its fuzzy inference network implementation for the decision making systems requiring the interval valued decisions.

• 한국산학기술학회논문지
• /
• 제12권8호
• /
• pp.3689-3696
• /
• 2011

의사결정 지원시스템에서 작업자들은 대량의 데이터 집계 연산을 요구하며, 데이터에 대한 정확한 응답보다는 경향 분석에 더 많은 관심을 가진다. 그러므로 정확한 응답보다 빠른 근사 질의응답을 제공하는 것이 필요하며 그것을 실현하기 위한 근사질의 응답 기법의 연구가 필요하다. 따라서 본 논문에서는 기존 연구들의 단점을 보안하고 근사 응답의 정확성을 향상시킬 수 있는 Fuzzy C-Means (FCM) 클러스터링 기반 Adaptive Neuro-Fuzzy Inference System (ANFIS)을 이용한 근사 질의응답 기법을 제안한다. FCM-ANFIS을 이용한 근사 질의응답 기법은 다차원 데이터의 지식 표현 모델을 생성함으로써 거대한 다차원 데이터 큐브에 직접적인 접근 없이 집계 질의 수행이 가능하다. 비교실험을 통하여 제안된 기법이 기존의 NMF 기법보다 근사 질의응답의 정확성이 향상되었음을 확인한다.

• 한국지능시스템학회논문지
• /
• 제7권1호
• /
• pp.16-26
• /
• 1997

China is one of the few countries where natural disaster strike frequently and cause heavy damage. In this paper, we mathematically develop two models to assess fuzzy risk of natural disaster in China. One is to assess the risk based on database of historical disaster effects by using information diffusion method relevant in fuzzy information analysis. In another model, we give an overview over advanced method to calculate the risk of release, exposure and consequence assessent, where information distribution technique is used to calculate basic fuzzy relationships showing historical experience of natural disasters, and fuzzy approximate inference is employed to study loss risk based on these basic relationships. We also present an examples to show how to use the first model. Result show that the model is effective for natural disaster risk assessment.

• Journal of Mechanical Science and Technology
• /
• 제15권8호
• /
• pp.1132-1142
• /
• 2001

The paper describes the construction of global function approximation models for use in design optimization via global search techniques such as genetic algorithms. Two different approximation methods referred to as evolutionary fuzzy modeling (EFM) and neuro-fuzzy modeling (NFM) are implemented in the context of global approximate optimization. EFM and NFM are based on soft computing paradigms utilizing fuzzy systems, neural networks and evolutionary computing techniques. Such approximation methods may have their promising characteristics in a case where the training data is not sufficiently provided or uncertain information may be included in design process. Fuzzy inference system is the central system for of identifying the input/output relationship in both methods. The paper introduces the general procedures including fuzzy rule generation, membership function selection and inference process for EFM and NFM, and presents their generalization capabilities in terms of a number of fuzzy rules and training data with application to a three-bar truss optimization.

• Communications for Statistical Applications and Methods
• /
• 제18권5호
• /
• pp.645-655
• /
• 2011

Chandrasekar et al. (2004) introduced a generalized Type-II hybrid censoring. In this paper, we propose generalized doubly Type-II hybrid censoring. In addition, this paper presents the statistical inference on the scale parameter for the half logistic distribution when samples are generalized doubly Type-II hybrid censoring. The approximate maximum likelihood(AMLE) method is developed to estimate the unknown parameter. The scale parameter is estimated by the AMLE method using two di erent Taylor series expansion types. We compar the AMLEs in the sense of the mean square error(MSE). The simulation procedure is repeated 10,000 times for the sample size n = 20; 30; 40 and various censored samples. The $AMLE_I$ is better than $AMLE_{II}$ in the sense of the MSE.

• 한국지능시스템학회:학술대회논문집
• /
• 한국퍼지및지능시스템학회 1993년도 Fifth International Fuzzy Systems Association World Congress 93
• /
• pp.1118-1120
• /
• 1993

Fuzzy logic places a considerable burden on an inference engine for applications such as control or approximate reasoning. Various neural network architectures have been proposed to deal with the computational task, and yet, maintain flexibility in the desired traits of the final system. Recently, we introduced a trainable network architecture whose nodes implement weighted Yager additive hybrid operators for fuzzy logic inference in an approximate reasoning setting. In this paper we examine the utility of such networks for control situations. We show that they are capable of learning control functions which are piece-wise monotonic in each of the variables. The learning ability is demonstrated through an example.