Browsing CAS/CNS Technical Reports by Title

OpenBU

Browsing CAS/CNS Technical Reports by Title

Sort by: Order: Results:

  • Anisotropic Interpolation on Graphs: The Combinatorial Dirichlet Problem
    Grady, Leo; Schwartz, Eric (Boston University Center for Adaptive Systems and Department of Cognitive and Neural Systems, 2003-07)
    The combinatorial Dirichlet problem is formulated, and an algorithm for solving it is presented. This provides an effective method for interpolating missing data on weighted graphs of arbitrary connectivity. Image processing ...
  • Application of Biological Learning Theories to Mobile Robot Avoidance and Approach Behaviors
    Chang, Caroilna; Gaudiano, Paolo (Boston University Center for Adaptive Systems and Department of Cognitive and Neural Systems, 1998-02)
    We present a neural network that learns to control approach and avoidance behaviors in a mobile robot using the mechanisms of classical and operant conditioning. Learning, which requires no supervision, takes place as the ...
  • Approaching Visual Search in Photo-Realistic Scenes
    Cunningham, Robert K.; Beck, Jacob; Mingolla, Ennio (Boston University Center for Adaptive Systems and Department of Cognitive and Neural Systems, 1996-11)
    Visual search is extended from the domain of polygonal figures presented on a uniform background to scenes in which search is for a photo-realistic object in a dense, naturalistic background. Scene generation for these ...
  • Are There Universal Principles of Brain Computation?
    Grossberg, Stephen (Boston University Center for Adaptive Systems and Department of Cognitive and Neural Systems, 1995-05)
  • ART 2-A: An Adaptive Resonance Algorithm for Rapid Category Learning and Recognition
    Carpenter, Gail A.; Grossberg, Stephen; Rosen, David (Boston University Center for Adaptive Systems and Department of Cognitive and Neural Systems, 1991-02)
    This article introduces ART 2-A, an efficient algorithm that emulates the self-organizing pattern recognition and hypothesis testing properties of the ART 2 neural network architecture, but at a speed two to three orders ...
  • ART and ARTMAP Neural Networks for Applications: Self-Organizing Learning, Recognition, and Prediction
    Carpenter, Gail A.; Gjaja, Marin N.; Gopal, Sucharita; Markuzon, Natalya; Woodcock, Curtis E. (Boston University Center for Adaptive Systems and Department of Cognitive and Neural Systems, 1996-03)
    ART and ARTMAP neural networks for adaptive recognition and prediction have been applied to a variety of problems. Applications include parts design retrieval at the Boeing Company, automatic mapping from remote sensing ...
  • ART-EMAP: A Neural Network Architecture for Learning and Prediction by Evidence Accumulation
    Carpenter, Gail A.; Ross, William D. (Boston University Center for Adaptive Systems and Department of Cognitive and Neural Systems, 1993-01)
    This paper introduces ART-EMAP, a neural architecture that uses spatial and temporal evidence accumulation to extend the capabilities of fuzzy ARTMAP. ART-EMAP combines supervised and unsupervised learning and a medium-term ...
  • ART-EMAP: A Neural Network Architecture for Object Recognition by Evidence Accumulation
    Carpenter, Gail A.; Ross, William D. (Boston University Center for Adaptive Systems and Department of Cognitive and Neural Systems, 1993-10)
    A new neural network architecture is introduced for the recognition of pattern classes after supervised and unsupervised learning. Applications include spatio-temporal image understanding and prediction and 3-D object ...
  • ARTEX: A Self-Organizing Architecture for Classifying Image Regions
    Grossberg, Stephen; Williamson, James R. (Boston University Center for Adaptive Systems and Department of Cognitive and Neural Systems, 1996-05)
    A self-organizing architect is developed for image region classification. The system consists of a preprocessor that utilizes multi-scale filtering, competition, cooperation, and diffusion to compute a vector of image ...
  • Articulatory Tradeoffs Reduce Acoustic Variability During American English /r/ Production
    Guenther, Frank H.; Epsy-Wilson, Carol Y.; Boyce, Suzanne E.; Matthies, Melanie L.; Zandipour, Majid; Perkell, Joseph S. (Boston University Center for Adaptive Systems and Department of Cognitive and Neural Systems, 1998-01)
    Acoustic and articulatory recordings reveal that speakers utilize systematic articulatory tradeoffs to maintain acoustic stability when producing the phoneme /r/. Distinct articulator configurations used to produce /r/ in ...
  • ARTMAP-DS: Pattern Discrimination by Discounting Similarities
    Carpenter, Gail A.; Wilson, Frank D.M. (Boston University Center for Adaptive Systems and Department of Cognitive and Neural Systems, 1997-6)
    ARTMAP-DS extends fuzzy ARTMAP to discriminate between similar inputs by discounting similarities. When two or more candidate category representations are activated by a given input, features that the candidate representations ...
  • ARTMAP-FD: Familiarity Discrimination Applied to Radar Target Recognition
    Carpenter, Gail A.; Rubin, Mark A.; Streilein, William W. (Boston University Center for Adaptive Systems and Department of Cognitive and Neural Systems, 1996-11)
    ARTMAP-FD extends fuzzy ARTMAP to perform familiarity discrimination. That is, the network learns to abstain from meaningless guesses on patterns not belonging to a class represented in the training set. ARTMAP-FD can also ...
  • ARTMAP-FTR: A Neural Network For Fusion Target Recognition, With Application To Sonar Classification
    Streilein, William W.; Gaudiano, Paolo; Carpenter, Gail A. (Boston University Center for Adaptive Systems and Department of Cognitive and Neural Systems, 1998-05)
    ART (Adaptive Resonance Theory) neural networks for fast, stable learning and prediction have been applied in a variety of areas. Applications include automatic mapping from satellite remote sensing data, machine tool ...
  • ARTMAP-FTR: A Neural Network for Object Recognition Through Sonar on a Mobile Robot
    Streilein, William W.; Gaudiano, Paolo; Carpenter, Gail A. (Boston University Center for Adaptive Systems and Department of Cognitive and Neural Systems, 1998-05)
    ART (Adaptive Resonance Theory) neural networks for fast, stable learning and prediction have been applied in a variety of areas. Applications include automatic mapping from satellite remote sensing data, machine tool ...
  • ARTMAP-IC and Medical Diagnosis: Instance Counting and Inconsistent Cases
    Carpenter, Gail A.; Markuzon, Natalya (Boston University Center for Adaptive Systems and Department of Cognitive and Neural Systems, 1996-05)
    For complex database prediction problems such as medical diagnosis, the ARTMAP-IC neural network adds distributed prediction and category instance counting to the basic fuzzy ARTMAP system. For the ARTMAP match tracking ...
  • ARTMAP Neural Network Classification of Land Use Change
    Shock, Byron; Carpenter, Gail; Gopal, Sucharita; Woodcock, Curtis (Boston University Computer Science Department, 2001-12)
    The ability to detect and monitor changes in land use is essential for assessment of the sustainability of development. In the next decade, NASA will gather high-resolution multi-spectral and multi-temporal data, which ...
  • ARTMAP Neural Networks for Information Fusion and Data Mining: Map Production and Target Recognition Methodologies
    Parsons, Olga; Carpenter, Gail (Boston University Center for Adaptive Systems and Department of Cognitive and Neural Systems, 2002-09)
    The Sensor Exploitation Group of MIT Lincoln Laboratory incorporated an early version of the ARTMAP neural network as the recognition engine of a hierarchical system for fusion and data mining of registered geospatial ...
  • ARTMAP: Supervised Real-Time Learning and Classification of Nonstationary Data by a Self-Organizing Neural Network
    Carpenter, Gail A.; Grossbergy, Stephen; Reynolds, John (Boston University Center for Adaptive Systems and Department of Cognitive and Neural Systems, 1991-02)
    This article introduces a new neural network architecture, called ARTMAP, that autonomously learns to classify arbitrarily many, arbitrarily ordered vectors into recognition categories based on predictive success. This ...
  • ART Neural Networks: Distributed Coding and ARTMAP Applications
    Carpenter, Gail (Boston University Center for Adaptive Systems and Department of Cognitive and Neural Systems, 2000-03)
    ART (Adaptive Resonance Theory) neural networks for fast, stable learning and prediction have been applied in a variety of areas. Applications include airplane design and manufacturing, automatic target recognition, financial ...
  • ART Neural Networks for Medical Data Analysis and Fast Distributed Learning
    Carpenter, Gail; Milenova, Boriana (Boston University Center for Adaptive Systems and Department of Cognitive and Neural Systems, 2000-01)
    ART (Adaptive Resonance Theory) neural networks for fast, stable learning and prediction have been applied in a variety of areas. Applications include airplane design and manufacturing, automatic target recognition, financial ...

Search OpenBU


Advanced Search

Browse

Deposit Materials