TITLE

NEURAL OBJECT RECOGNITION BY HIERARCHICAL APPEARANCE LEARNING

AUTHOR(S)
OBERHOFF, DANIEL; KOLESNIK, MARINA
PUB. DATE
August 2008
SOURCE
International Journal of Pattern Recognition & Artificial Intell;Aug2008, Vol. 22 Issue 5, p883
SOURCE TYPE
Academic Journal
DOC. TYPE
Article
ABSTRACT
We present a system for object recognition that is largely inspired by physiologically identified processing streams in the visual cortex, specifically in the ventral stream. It consists of neural units organized in a hierarchy of layers with encoding features of increasing complexity. A key feature of the system is that the neural units learn their preferred patterns from visual input alone. Through this "soft wiring" of neural units the system becomes tuned for target object classes through passive visual experience and no labels are required in this stage. Object labels are only introduced in the last step to train a classifier on the system's output. While this tuning process is purely feed-forward we also present a neural mechanism for back projection of the learned image patterns down the hierarchical layers, and demonstrate how this feedback can be used to stabilize the system in the presence of noise. We test the neural system with natural images from publicly available data-sets of natural scenes and handwritten digits.
ACCESSION #
34172894

 

Related Articles

  • Radial Basis Probabilistic Neural Networks: Model and Application. Huang, De-Shuang // International Journal of Pattern Recognition & Artificial Intell;Nov1999, Vol. 13 Issue 7, p1083 

    This paper investigates the capabilities of radial basis function networks (RBFN) and kernel neural networks (KNN), i.e. a specific probabilistic neural networks (PNN), and studies their similarities and differences. In order to avoid the huge amount of hidden units of the KNNs (or PNNs) and...

  • Investigation by Simulation of Closed-Loop Optimal Control Law Implementation Using Artificial Neural Network. Matieni, Xavier; Dodds, Stephen J.; Sin Wee Lee // International Review on Modelling & Simulations;Oct2012, Vol. 5 Issue 5, p2119 

    The main contribution of the paper is the investigation of the possibility of implementing a nonlinear optimal state feedback control law using an Artificial Neural Network (ANN). Time optimal control (TOC) of a double integrator plant is selected as its state trajectories are easily computed...

  • ARABIC SCRIPT WEB PAGE LANGUAGE IDENTIFICATION USING HYBRID-KNN METHOD. SELAMAT, ALI; SUBROTO, IMAM MUCH IBNU; CHOON-CHING NG // International Journal of Computational Intelligence & Applicatio;Sep2009, Vol. 8 Issue 3, p315 

    In this paper, we proposed hybrid-KNN methods on the Arabic script web page language identification. One of the crucial tasks in the text-based language identification that utilizes the same script is how to produce reliable features and how to deal with the huge number of languages in the...

  • AN OPTICAL FUZZY MATRIX-VECTOR PROCESSOR FOR IMPLEMENTING FUZZY ASSOCIATIVE MEMORY. Shuqun Zhang; Senmao Lin; Caisheng Chen // Microwave & Optical Technology Letters;11/1/93, Vol. 6 Issue 14, p792 

    An optical fuzzy matrix-vector processor is designed to implement fuzzy associative memory. By spatial encoding and thresholding operation, the two basic operations needed by fuzzy associative memory, maximization and minimization, are realized optically. Experimental results are given as well.

  • Mechatronic Implementation of an Intelligent Active Force Control Scheme via a Hardware-in-the-Loop Configuration. Mailah, M.; Priyandoko, Gigih // International Review of Mechanical Engineering;Nov2010, Vol. 4 Issue 7, p899 

    The paper focuses on the practical real-time implementation of a hybrid intelligent active force control (AFC) method via a hardware-in-the-loop (HIL) scheme to a vehicle suspension system. It serves as a new and novel method of regulating the dynamic system through a feedback closed loop...

  • NEW METHOD OF NEURON DESIGN BASED ON DISCRETE Z-FUNCTION TO ADAPT THE CHANGE OF INTEGRATED VEHICLE STABILITY CONTROL ORDER. HARLY, M.; SUTANTRA, I. N.; MAURIDHI, H. P. // International Journal of Computational Intelligence & Applicatio;Sep2009, Vol. 8 Issue 3, p253 

    Fixed order neural networks (FONN), such as high order neural network (HONN), in which its architecture is developed from zero order of activation function and joint weight, regulates only the number of weight and their value. As a result, this network only produces a fixed order model or...

  • Multi Area Load Frequency Regulation in Co-Ordination with HVDC Links: an ANN Tuned PID Controller Design. Karthikeyan, G.; Chandrasekar, S. // International Review of Automatic Control;Mar2012, Vol. 5 Issue 2, p113 

    The Load Frequency Control (LFC) problem has been a major subject in electrical power system operation and is becoming more significant recently with increasing size, changing structure and complexity in interconnected power systems. In this study, the power systems with three areas connected...

  • Design of fuzzy neural network-based robust gain scheduling controllers. Sato, Yoshishige // Electrical Engineering in Japan;Dec2009, Vol. 169 Issue 4, p21 

    This paper proposes a method of robust gain scheduling control design by intelligent control that uses a fuzzy neural network without a model. We create a system that is robust and capable of automatic gain control against the conventional fixed PID control system, design a neural network which...

  • Prediction of Wear Behavior of Epoxy-MWCNTS Nanocomposites Using Artificial Neural Networks. Sabarinathan, C.; Muthu, S.; Arunkumar, R. // International Review on Modelling & Simulations;Oct2013, Vol. 6 Issue 5, p1665 

    The potential of using Artificial Neural Networks (ANN) for predicting the dry sliding wear behavior of Multiwall Carbon Nanotubes (MWCNTs) reinforced epoxy material was investigated in this work. The effects of reinforcement content 0.1%, 0.5%, 1.25%, 2.5% and 5% weight fraction of MWCNTs...

Share

Read the Article

Courtesy of THE LIBRARY OF VIRGINIA

Sorry, but this item is not currently available from your library.

Try another library?
Sign out of this library

Other Topics