• Title, Summary, Keyword: associative learning

Search Result 61, Processing Time 0.036 seconds

Design of a robot learning controller using associative mapping memory (연관사상 메모리를 이용한 로봇 머니퓰레이터의 학습제어기 설계)

  • 정재욱;국태용;이택종
    • 제어로봇시스템학회:학술대회논문집
    • /
    • /
    • pp.936-939
    • /
    • 1996
  • In this paper, two specially designed associative mapping memories, called Associative Mapping Elements(AME) and Multiple-Digit Overlapping AME(MDO-AME), are presented for learning of nonlinear functions including kinematics and dynamics of robot manipulators. The proposed associative mapping memories consist of associative mapping rules(AMR) and weight update rules(WUR) which guarantee generalization and specialization of input-output relationship of learned nonlinear functions. Two simulation results, one for supervised learning and the other for unsupervised learning, are given to demonstrate the effectiveness of the proposed associative mapping memories.

  • PDF

Unsupervised Incremental Learning of Associative Cubes with Orthogonal Kernels

  • Kang, Hoon;Ha, Joonsoo;Shin, Jangbeom;Lee, Hong Gi;Wang, Yang
    • Journal of Korean Institute of Intelligent Systems
    • /
    • v.25 no.1
    • /
    • pp.97-104
    • /
    • 2015
  • An 'associative cube', a class of auto-associative memories, is revisited here, in which training data and hidden orthogonal basis functions such as wavelet packets or Fourier kernels, are combined in the weight cube. This weight cube has hidden units in its depth, represented by a three dimensional cubic structure. We develop an unsupervised incremental learning mechanism based upon the adaptive least squares method. Training data are mapped into orthogonal basis vectors in a least-squares sense by updating the weights which minimize an energy function. Therefore, a prescribed orthogonal kernel is incrementally assigned to an incoming data. Next, we show how a decoding procedure finds the closest one with a competitive network in the hidden layer. As noisy test data are applied to an associative cube, the nearest one among the original training data are restored in an optimal sense. The simulation results confirm robustness of associative cubes even if test data are heavily distorted by various types of noise.

Optical Pattern Recognition Based on Holographic Associative Memory (홀로그램 연상기억을 이용한 광학적 영상인식에 관한 연구)

  • 서호형;김병윤;이상수
    • Proceedings of the Optical Society of Korea Conference
    • /
    • /
    • pp.33-39
    • /
    • 1991
  • We have developed a new holographic associative memory(HAN) based on an adaptive learning which uses learning pattern method (LPM). The LPM utilizes the simple optical implementation of outer-product learning, performance of adapitive learning. simulation are represented.

  • PDF

Hierarchical Associative Frame with Learning and Episode memory for the intelligent Knowledge Retrieval

  • Shim, Jeon-Yon
    • 제어로봇시스템학회:학술대회논문집
    • /
    • /
    • pp.694-698
    • /
    • 2004
  • In this paper, as one of these efforts for making the intelligent data mining system we propose the Associative frame of the memory according to the following three steps. First,the structured frame for performing the main brain function should be made. In this frame, the concepts of learning memory and episode memory are considered. Second,the learning mechanism for data acquisition and storing mechanism in the memory frame are provided. The obtained data are arranged and stored in the memory following the rules of the structured memory frame. Third, it is the last step of processing the inference and knowledge retrieval function using the stored knowledge in the associative memory frame. This system is applied to the area for estimating the purchasing degree from the type of customer's tastes, the pattern of commodities and the evaluation of a company.

  • PDF

Formation of Attention and Associative Memory based on Reinforcement Learning

  • Kenichi, Abe;Park, Jin-Bae
    • 제어로봇시스템학회:학술대회논문집
    • /
    • /
    • pp.22.3-22
    • /
    • 2001
  • An attention task, in which context information should be extracted from the first presented pattern, and the recognition answer of the second presented pattern should be generated using the context information, is employed in this paper. An Elman-type recurrent neural network is utilized to extract and keep the context information. A reinforcement signal that indicates whether the answer is correct or not, is only a signal that the system can obtain for the learning. Only by this learning, necessary context information became to be extracted and kept, and the system became to generate the correct answers. Furthermore, the function of an associative memory is observed in the feedback loop in the Elman-type neural network.

  • PDF

Using Colours to alter Consumer Behaviour and Product Success

  • Page, Tom;Thorsteinsson, Gisli;Ha, Joong-Gyu
    • International Journal of Contents
    • /
    • v.8 no.1
    • /
    • pp.69-73
    • /
    • 2012
  • This paper aims to present colour theories and show how they can be used to explain consumer's preferences of some products over others. It will, furthermore, attempt to link these theories to the design industry and look at how colour associations determine product success. Due to associative learning and personal preference, the colours of objects can cause consumers to either favour or dislike products over those with identical functions and efficiency. Age and gender affect the preferred colour choices of the individual, making some products more popular to particular groups of potential consumers. Designers can utilise colour theories to ensure that they use the most appropriate colour schemes to maximise and appeal to their targeted market successfully. A survey was conducted with 100 participants. It demonstrates the associative links between colours, emotions and product categories. It can be shown that the colour of an object can contribute to its success or failure in the market based on a number of different criteria. The design must use colour confidently to evoke certain emotions or connotations and must be carried out appropriately. The designer also has to consider whom it is that be viewing it and making the decision of preference.

Monitoring of Chemical Processes Using Modified Scale Space Filtering and Functional-Link-Associative Neural Network (개선된 스케일 스페이스 필터링과 함수연결연상 신경망을 이용한 화학공정 감시)

  • Park, Jung-Hwan;Kim, Yoon-Sik;Chang, Tae-Suk;Yoon, En-Sup
    • Journal of Institute of Control, Robotics and Systems
    • /
    • v.6 no.12
    • /
    • pp.1113-1119
    • /
    • 2000
  • To operate a process plant safely and economically, process monitoring is very important. Process monitoring is the task to identify the state of the system from sensor data. Process monitoring includes data acquisition, regulatory control, data reconciliation, fault detection, etc. This research focuses on the data recon-ciliation using scale-space filtering and fault detection using functional-link associative neural networks. Scale-space filtering is a multi-resolution signal analysis method. Scale-space filtering can extract highest frequency factors(noise) effectively. But scale-space filtering has too large calculation costs and end effect problems. This research reduces the calculation cost of scale-space filtering by applying the minimum limit to the gaussian kernel. And the end-effect that occurs at the end of the signal of the scale-space filtering is overcome by using extrapolation related with the clustering change detection method. Nonlinear principal component analysis methods using neural network have been reviewed and the separately expanded functional-link associative neural network is proposed for chemical process monitoring. The separately expanded functional-link associative neural network has better learning capabilities, generalization abilities and short learning time than the exiting-neural networks. Separately expanded functional-link associative neural network can express a statistical model similar to real process by expanding the input data separately. Combining the proposed methods-modified scale-space filtering and fault detection method using the separately expanded functional-link associative neural network-a process monitoring system is proposed in this research. the usefulness of the proposed method is proven by its application a boiler water supply unit.

  • PDF

Learning and inference of fuzzy inference system with fuzzy neural network (퍼지 신경망을 이용한 퍼지 추론 시스템의 학습 및 추론)

  • 장대식;최형일
    • Journal of the Korean Institute of Telematics and Electronics B
    • /
    • v.33B no.2
    • /
    • pp.118-130
    • /
    • 1996
  • Fuzzy inference is very useful in expressing ambiguous problems quantitatively and solving them. But like the most of the knowledge based inference systems. It has many difficulties in constructing rules and no learning capability is available. In this paper, we proposed a fuzzy inference system based on fuzy associative memory to solve such problems. The inference system proposed in this paper is mainly composed of learning phase and inference phase. In the learning phase, the system initializes it's basic structure by determining fuzzy membership functions, and constructs fuzzy rules in the form of weights using learning function of fuzzy associative memory. In the inference phase, the system conducts actual inference using the constructed fuzzy rules. We applied the fuzzy inference system proposed in this paper to a pattern classification problem and show the results in the experiment.

  • PDF

A Novel Model, Recurrent Fuzzy Associative Memory, for Recognizing Time-Series Patterns Contained Ambiguity and Its Application (모호성을 포함하고 있는 시계열 패턴인식을 위한 새로운 모델 RFAM과 그 응용)

  • Kim, Won;Lee, Joong-Jae;Kim, Gye-Young;Choi, Hyung-Il
    • The KIPS Transactions:PartB
    • /
    • v.11B no.4
    • /
    • pp.449-456
    • /
    • 2004
  • This paper proposes a novel recognition model, a recurrent fuzzy associative memory(RFAM), for recognizing time-series patterns contained an ambiguity. RFAM is basically extended from FAM(Fuzzy Associative memory) by adding a recurrent layer which can be used to deal with sequential input patterns and to characterize their temporal relations. RFAM provides a Hebbian-style learning method which establishes the degree of association between input and output. The error back-propagation algorithm is also adopted to train the weights of the recurrent layer of RFAM. To evaluate the performance of the proposed model, we applied it to a word boundary detection problem of speech signal.