• Title/Summary/Keyword: Feed-forward learning

Search Result 67, Processing Time 0.023 seconds

The Use of Feed-forward and Feedback Learning in Firm-University Knowledge Development: The Case of Japan

  • Oh, In-Gyu
    • Asian Journal of Innovation and Policy
    • /
    • v.1 no.1
    • /
    • pp.92-115
    • /
    • 2012
  • The problem Japanese universities face is exactly the same as that of German universities: no international recognition in world rankings of universities despite their high levels of postwar economic and technological developments. This was indeed one reason why world-class Japanese firms, such as Toyota and Sony, have avoided working closely with Japanese universities for R&D partnership and new technology commercialization. To resolve this problem, the Japanese government has continuously implemented aggressive policies of the internationalization, privatization, liberalization, and privatization of universities since the onset of the economic recession in 1989 in order to revitalize the Japanese economy through radical innovation projects between universities and firms. National projects of developing medical robots for Japan's ageing society are some of the ambitious examples that emphasize feed-forward learning in innovation. However, this paper argues that none of these programs of fostering university-firm alliances toward feed-forward learning has been successful in promoting the world ranking of Japanese universities, although they showed potentials of reinforcing their conventional strength of introducing $kaizen$ through feedback learning of tacit knowledge. It is therefore argued in this paper that Japanese universities and firms should focus on feedback learning as a way to motivate firm-university R&D alliances.

Motion predictive control for DPS using predicted drifted ship position based on deep learning and replay buffer

  • Lee, Daesoo;Lee, Seung Jae
    • International Journal of Naval Architecture and Ocean Engineering
    • /
    • v.12 no.1
    • /
    • pp.768-783
    • /
    • 2020
  • Typically, a Dynamic Positioning System (DPS) uses a PID feed-back system, and it often adopts a wind feed-forward system because of its easier implementation than a feed-forward system based on current or wave. But, because a ship's drifting motion is caused by wind, current, and wave drift loads, all three environmental loads should be considered. In this study, a motion predictive control for the PID feedback system of the DPS is proposed, which considers the three environmental loads by utilizing predicted drifted ship positions in the future since it contains information about the three environmental loads from the moment to the future. The prediction accuracy for the future drifted ship position is ensured by adopting deep learning algorithms and a replay buffer. Finally, it is shown that the proposed motion predictive system results in better station-keeping performance than the wind feed-forward system.

Feed-forward Learning Algorithm by Generalized Clustering Network (Generalized Clustering Network를 이용한 전방향 학습 알고리즘)

  • Min, Jun-Yeong;Jo, Hyeong-Gi
    • The Transactions of the Korea Information Processing Society
    • /
    • v.2 no.5
    • /
    • pp.619-625
    • /
    • 1995
  • This paper constructs a feed-forward learning complex algorithm which replaced by the backpropagation learning. This algorithm first attempts to organize the pattern vectors into clusters by Generalized Learning Vector Quantization(GLVQ) clustering algorithm(Nikhil R. Pal et al, 1993), second, regroup the pattern vectors belonging to different clusters, and the last, recognize into regrouping pattern vectors by single layer perceptron. Because this algorithm is feed-forward learning algorithm, time is less than backpropagation algorithm and the recognition rate is increased. We use 250 ASCII code bit patterns that is normalized to 16$\times$8. As experimental results, when 250 patterns devide by 10 clusters, average iteration of each cluster is 94.7, and recognition rate is 100%.

  • PDF

Fight Detection in Hockey Videos using Deep Network

  • Mukherjee, Subham;Saini, Rajkumar;Kumar, Pradeep;Roy, Partha Pratim;Dogra, Debi Prosad;Kim, Byung-Gyu
    • Journal of Multimedia Information System
    • /
    • v.4 no.4
    • /
    • pp.225-232
    • /
    • 2017
  • Understanding actions in videos is an important task. It helps in finding the anomalies present in videos such as fights. Detection of fights becomes more crucial when it comes to sports. This paper focuses on finding fight scenes in Hockey sport videos using blur & radon transform and convolutional neural networks (CNNs). First, the local motion within the video frames has been extracted using blur information. Next, fast fourier and radon transform have been applied on the local motion. The video frames with fight scene have been identified using transfer learning with the help of pre-trained deep learning model VGG-Net. Finally, a comparison of the methodology has been performed using feed forward neural networks. Accuracies of 56.00% and 75.00% have been achieved using feed forward neural network and VGG16-Net, respectively.

A Study on the Neuro-Fuzzy Control and Its Application

  • So, Myung-Ok;Yoo, Heui-Han;Jin, Sun-Ho
    • Journal of Advanced Marine Engineering and Technology
    • /
    • v.28 no.2
    • /
    • pp.228-236
    • /
    • 2004
  • In this paper. we present a neuro-fuzzy controller which unifies both fuzzy logic and multi-layered feed forward neural networks. Fuzzy logic provides a means for converting linguistic control knowledge into control actions. On the other hand. feed forward neural networks provide salient features. such as learning and parallelism. In the proposed neuro-fuzzy controller. the parameters of membership functions in the antecedent part of fuzzy inference rules are identified by using the error back propagation algorithm as a learning rule. while the coefficients of the linear combination of input variables in the consequent part are determined by using the least square estimation method. Finally. the effectiveness of the proposed controller is verified through computer simulation for an inverted pole system.

Side scan sonar image super-resolution using an improved initialization structure (향상된 초기화 구조를 이용한 측면주사소나 영상 초해상도 영상복원)

  • Lee, Junyeop;Ku, Bon-hwa;Kim, Wan-Jin;Ko, Hanseok
    • The Journal of the Acoustical Society of Korea
    • /
    • v.40 no.2
    • /
    • pp.121-129
    • /
    • 2021
  • This paper deals with a super-resolution that improves the resolution of side scan sonar images using learning-based compressive sensing. Learning-based compressive sensing combined with deep learning and compressive sensing takes a structure of a feed-forward network and parameters are set automatically through learning. In particular, we propose a method that can effectively extract additional information required in the super-resolution process through various initialization methods. Representative experimental results show that the proposed method provides improved performance in terms of Peak Signal-to-Noise Ratio (PSNR) and Structure Similarity Index Measure (SSIM) than conventional methods.

Context-sensitive Spelling Error Correction using Feed-Forward Neural Network (Feed-Forward Neural Network를 이용한 문맥의존 철자오류 교정)

  • Hwang, Hyunsun;Lee, Changki
    • Annual Conference on Human and Language Technology
    • /
    • 2015.10a
    • /
    • pp.124-128
    • /
    • 2015
  • 문맥의존 철자오류는 해당 단어만 봤을 때에는 오류가 아니지만 문맥상으로는 오류인 문제를 말한다. 이러한 문제를 해결하기 위해서는 문맥정보를 보아야 하지만, 형태소 분석 단계에서는 자세한 문맥 정보를 보기 어렵다. 본 논문에서는 형태소 분석 정보만을 이용한 철자오류 수정을 위한 문맥으로 사전훈련(pre-training)된 단어 표현(Word Embedding)를 사용하고, 기존의 기계학습 알고리즘보다 좋다고 알려진 딥 러닝(Deep Learning) 기술을 적용한 시스템을 제안한다. 실험결과, 기존의 기계학습 알고리즘인 Structural SVM보다 높은 F1-measure 91.61 ~ 98.05%의 성능을 보였다.

  • PDF

Prediction of ship power based on variation in deep feed-forward neural network

  • Lee, June-Beom;Roh, Myung-Il;Kim, Ki-Su
    • International Journal of Naval Architecture and Ocean Engineering
    • /
    • v.13 no.1
    • /
    • pp.641-649
    • /
    • 2021
  • Fuel oil consumption (FOC) must be minimized to determine the economic route of a ship; hence, the ship power must be predicted prior to route planning. For this purpose, a numerical method using test results of a model has been widely used. However, predicting ship power using this method is challenging owing to the uncertainty of the model test. An onboard test should be conducted to solve this problem; however, it requires considerable resources and time. Therefore, in this study, a deep feed-forward neural network (DFN) is used to predict ship power using deep learning methods that involve data pattern recognition. To use data in the DFN, the input data and a label (output of prediction) should be configured. In this study, the input data are configured using ocean environmental data (wave height, wave period, wave direction, wind speed, wind direction, and sea surface temperature) and the ship's operational data (draft, speed, and heading). The ship power is selected as the label. In addition, various treatments have been used to improve the prediction accuracy. First, ocean environmental data related to wind and waves are preprocessed using values relative to the ship's velocity. Second, the structure of the DFN is changed based on the characteristics of the input data. Third, the prediction accuracy is analyzed using a combination comprising five hyperparameters (number of hidden layers, number of hidden nodes, learning rate, dropout, and gradient optimizer). Finally, k-means clustering is performed to analyze the effect of the sea state and ship operational status by categorizing it into several models. The performances of various prediction models are compared and analyzed using the DFN in this study.

Reinforcement Learning Control using Self-Organizing Map and Multi-layer Feed-Forward Neural Network

  • Lee, Jae-Kang;Kim, Il-Hwan
    • 제어로봇시스템학회:학술대회논문집
    • /
    • 2003.10a
    • /
    • pp.142-145
    • /
    • 2003
  • Many control applications using Neural Network need a priori information about the objective system. But it is impossible to get exact information about the objective system in real world. To solve this problem, several control methods were proposed. Reinforcement learning control using neural network is one of them. Basically reinforcement learning control doesn't need a priori information of objective system. This method uses reinforcement signal from interaction of objective system and environment and observable states of objective system as input data. But many methods take too much time to apply to real-world. So we focus on faster learning to apply reinforcement learning control to real-world. Two data types are used for reinforcement learning. One is reinforcement signal data. It has only two fixed scalar values that are assigned for each success and fail state. The other is observable state data. There are infinitive states in real-world system. So the number of observable state data is also infinitive. This requires too much learning time for applying to real-world. So we try to reduce the number of observable states by classification of states with Self-Organizing Map. We also use neural dynamic programming for controller design. An inverted pendulum on the cart system is simulated. Failure signal is used for reinforcement signal. The failure signal occurs when the pendulum angle or cart position deviate from the defined control range. The control objective is to maintain the balanced pole and centered cart. And four states that is, position and velocity of cart, angle and angular velocity of pole are used for state signal. Learning controller is composed of serial connection of Self-Organizing Map and two Multi-layer Feed-Forward Neural Networks.

  • PDF

Classification System of EEG Signals During Mental Tasks

  • Seo Hee Don;Kim Min Soo;Eoh Soo Hae;Huang Xiyue;Rajanna K.
    • Proceedings of the IEEK Conference
    • /
    • 2004.08c
    • /
    • pp.671-674
    • /
    • 2004
  • We propose accurate classification method of EEG signals during mental tasks. In the experimental task, the tasks of subjects show 3 major measurements; there are mathematical tasks, color decision tasks, and Chinese phrase tasks. The classifier implemented for this work is a feed-forward neural network that trained with the error back-propagation algorithm. The new BCI system is proposed by using neural network. In this system, tr e architecture of the neural network is composed of three layers with a feed-forward network, which implements the error back propagation-learning algorithm. By applying this algorithm to 4 subjects, we achieved $95{\%}$ classification rates. The results for BCI mathematical task experiments show performance better than those of the Chinese phrase tasks. The selection time of each task depends on the mental task of subjects. We expect that the proposed detection method can be a basic technology for brain-computer interface by combining with left/right hand movement or yes/no discrimination methods.

  • PDF