• Title/Summary/Keyword: Learning Algorithms

Search Result 2,317, Processing Time 0.035 seconds

Self-adaptive Online Sequential Learning Radial Basis Function Classifier Using Multi-variable Normal Distribution Function

  • Dong, Keming;Kim, Hyoung-Joong;Suresh, Sundaram
    • 한국정보통신설비학회:학술대회논문집
    • /
    • 2009.08a
    • /
    • pp.382-386
    • /
    • 2009
  • Online or sequential learning is one of the most basic and powerful method to train neuron network, and it has been widely used in disease detection, weather prediction and other realistic classification problem. At present, there are many algorithms in this area, such as MRAN, GAP-RBFN, OS-ELM, SVM and SMC-RBF. Among them, SMC-RBF has the best performance; it has less number of hidden neurons, and best efficiency. However, all the existing algorithms use signal normal distribution as kernel function, which means the output of the kernel function is same at the different direction. In this paper, we use multi-variable normal distribution as kernel function, and derive EKF learning formulas for multi-variable normal distribution kernel function. From the result of the experience, we can deduct that the proposed method has better efficiency performance, and not sensitive to the data sequence.

  • PDF

Neural Learning Algorithms for Independent Component Analysis

  • Choi, Seung-Jin
    • Journal of IKEEE
    • /
    • v.2 no.1 s.2
    • /
    • pp.24-33
    • /
    • 1998
  • Independent Component analysis (ICA) is a new statistical method for extracting statistically independent components from their linear instantaneous mixtures which are generated by an unknown linear generative model. The recognition model is learned in unsupervised manner so that the recovered signals by the recognition model become the possibly scaled estimates of original source signals. This paper addresses the neural learning approach to ICA. As recognition models a linear feedforward network and a linear feedback network are considered. Associated learning algorithms for both networks are derived from maximum likelihood and information-theoretic approaches, using natural Riemannian gradient [1]. Theoretical results are confirmed by extensive computer simulations.

  • PDF

Design and Implementation of Online Algorithm Bank for Algorithm E-learning (컴퓨터 알고리즘 교육을 위한 온라인 알고리즘 뱅크 구현)

  • Park, Uchang
    • The Journal of Korean Association of Computer Education
    • /
    • v.7 no.4
    • /
    • pp.1-6
    • /
    • 2004
  • For an e-learning class, many voice and video technics for enhancing student teacher interaction. But for programming exercise courses, it's very difficult to add interactive components via web browser. In this paper, we make an online algorithm bank to manage and search algorithms, build an programming exercise interface on web. Students can edit, compile and execute programs included in online algorithm bank. Online program compile and execution enhance e-learning effectiveness for programming courses, and make students feel ease for computer algorithms.

  • PDF

Grasping Algorithm using Point Cloud-based Deep Learning (점군 기반의 심층학습을 이용한 파지 알고리즘)

  • Bae, Joon-Hyup;Jo, HyunJun;Song, Jae-Bok
    • The Journal of Korea Robotics Society
    • /
    • v.16 no.2
    • /
    • pp.130-136
    • /
    • 2021
  • In recent years, much study has been conducted in robotic grasping. The grasping algorithms based on deep learning have shown better grasping performance than the traditional ones. However, deep learning-based algorithms require a lot of data and time for training. In this study, a grasping algorithm using an artificial neural network-based graspability estimator is proposed. This graspability estimator can be trained with a small number of data by using a neural network based on the residual blocks and point clouds containing the shapes of objects, not RGB images containing various features. The trained graspability estimator can measures graspability of objects and choose the best one to grasp. It was experimentally shown that the proposed algorithm has a success rate of 90% and a cycle time of 12 sec for one grasp, which indicates that it is an efficient grasping algorithm.

Transfer Learning Using Convolutional Neural Network Architectures for Glioma Classification from MRI Images

  • Kulkarni, Sunita M.;Sundari, G.
    • International Journal of Computer Science & Network Security
    • /
    • v.21 no.2
    • /
    • pp.198-204
    • /
    • 2021
  • Glioma is one of the common types of brain tumors starting in the brain's glial cell. These tumors are classified into low-grade or high-grade tumors. Physicians analyze the stages of brain tumors and suggest treatment to the patient. The status of the tumor has an importance in the treatment. Nowadays, computerized systems are used to analyze and classify brain tumors. The accurate grading of the tumor makes sense in the treatment of brain tumors. This paper aims to develop a classification of low-grade glioma and high-grade glioma using a deep learning algorithm. This system utilizes four transfer learning algorithms, i.e., AlexNet, GoogLeNet, ResNet18, and ResNet50, for classification purposes. Among these algorithms, ResNet18 shows the highest classification accuracy of 97.19%.

Application of a deep learning algorithm to Compton imaging of radioactive point sources with a single planar CdTe pixelated detector

  • Daniel, G.;Gutierrez, Y.;Limousin, O.
    • Nuclear Engineering and Technology
    • /
    • v.54 no.5
    • /
    • pp.1747-1753
    • /
    • 2022
  • Compton imaging is the main method for locating radioactive hot spots emitting high-energy gamma-ray photons. In particular, this imaging method is crucial when the photon energy is too high for coded-mask aperture imaging methods to be effective or when a large field of view is required. Reconstruction of the photon source requires advanced Compton event processing algorithms to determine the exact position of the source. In this study, we introduce a novel method based on a Deep Learning algorithm with a Convolutional Neural Network (CNN) to perform Compton imaging. This algorithm is trained on simulated data and tested on real data acquired with Caliste, a single planar CdTe pixelated detector. We show that performance in terms of source location accuracy is equivalent to state-of-the-art algorithms, while computation time is significantly reduced and sensitivity is improved by a factor of ~5 in the Caliste configuration.

An Introduction of Machine Learning Theory to Business Decisions

  • Kim, Hyun-Soo
    • Journal of the Korean Operations Research and Management Science Society
    • /
    • v.19 no.2
    • /
    • pp.153-176
    • /
    • 1994
  • In this paper we introduce machine learning theory to business domains for business decisions. First, we review machine learning in general. We give a new look on a previous framework, version space approach, and we introduce PAC (probably approximately correct) learning paradigm which has been developed recently. We illustrate major results of PAC learning with business examples. And then, we give a theoretical analysis is decision tree induction algorithms by the frame work of PAC learning. Finally, we will discuss implications of learning theory toi business domains.

  • PDF

RECURRENT NEURAL NETWORKS -What Do They Learn and How\ulcorner-

  • Uchikawa, Yoshiki;Takase, Haruhiko;Watanabe, Tatsumi;Gouhara, Kazutoshi
    • Proceedings of the Korean Institute of Intelligent Systems Conference
    • /
    • 1993.06a
    • /
    • pp.1005-1008
    • /
    • 1993
  • Supervised learnmg 01 recurrent neural networks (RNNs) is discussed. First, we review the present state of art, featuring their major properties in contrast of those of the multilayer neural networks. Then, we concisely describe one of the most practical learning algorithms, i.e. backpropagation through time. Revising the basic formulation of the learning algorithms, we derive a general formula to solve for the exact solution(s) of the whole connection weights w of RNNs. On this basis we introduce a novel interpretation of the supervised learning. Namely, we define a multidimensional Euclidean space, by assigning the cost function E(w) and every component of w to each coordinate axis. Since E=E(w) turns up as a hyper surface in this space, we refer to the surface as learning surface. We see that topological features of the learning surface are valleys and hills. Finally, after explicating that the numerical procedures of learning are equivalent to descending slopes of the learning surface along the steepest gradient, we show that a minimal value of E(w) is the intersection of curved valleys.

  • PDF

Impact parameter prediction of a simulated metallic loose part using convolutional neural network

  • Moon, Seongin;Han, Seongjin;Kang, To;Han, Soonwoo;Kim, Kyungmo;Yu, Yongkyun;Eom, Joseph
    • Nuclear Engineering and Technology
    • /
    • v.53 no.4
    • /
    • pp.1199-1209
    • /
    • 2021
  • The detection of unexpected loose parts in the primary coolant system in a nuclear power plant remains an extremely important issue. It is essential to develop a methodology for the localization and mass estimation of loose parts owing to the high prediction error of conventional methods. An effective approach is presented for the localization and mass estimation of a loose part using machine-learning and deep-learning algorithms. First, a methodology was developed to estimate both the impact location and the mass of a loose part at the same times in a real structure in which geometric changes exist. Second, an impact database was constructed through a series of impact finite-element analyses (FEAs). Then, impact parameter prediction modes were generated for localization and mass estimation of a simulated metallic loose part using machine-learning algorithms (artificial neural network, Gaussian process, and support vector machine) and a deep-learning algorithm (convolutional neural network). The usefulness of the methodology was validated through blind tests, and the noise effect of the training data was also investigated. The high performance obtained in this study shows that the proposed methodology using an FEA-based database and deep learning is useful for localization and mass estimation of loose parts on site.

Development of Semi-Active Control Algorithm Using Deep Q-Network (Deep Q-Network를 이용한 준능동 제어알고리즘 개발)

  • Kim, Hyun-Su;Kang, Joo-Won
    • Journal of Korean Association for Spatial Structures
    • /
    • v.21 no.1
    • /
    • pp.79-86
    • /
    • 2021
  • Control performance of a smart tuned mass damper (TMD) mainly depends on control algorithms. A lot of control strategies have been proposed for semi-active control devices. Recently, machine learning begins to be applied to development of vibration control algorithm. In this study, a reinforcement learning among machine learning techniques was employed to develop a semi-active control algorithm for a smart TMD. The smart TMD was composed of magnetorheological damper in this study. For this purpose, an 11-story building structure with a smart TMD was selected to construct a reinforcement learning environment. A time history analysis of the example structure subject to earthquake excitation was conducted in the reinforcement learning procedure. Deep Q-network (DQN) among various reinforcement learning algorithms was used to make a learning agent. The command voltage sent to the MR damper is determined by the action produced by the DQN. Parametric studies on hyper-parameters of DQN were performed by numerical simulations. After appropriate training iteration of the DQN model with proper hyper-parameters, the DQN model for control of seismic responses of the example structure with smart TMD was developed. The developed DQN model can effectively control smart TMD to reduce seismic responses of the example structure.