Browsing CAS/CNS Technical Reports by Title

OpenBU

Browsing CAS/CNS Technical Reports by Title

Sort by: Order: Results:

  • dARTMAP: A Neural Network for Fast Distributed Supervised Learning
    Carpenter, Gail A.; Milenova, Boriana L.; Noeske, Benjamin W. (Boston University Center for Adaptive Systems and Department of Cognitive and Neural Systems, 1997-12)
    Distributed coding at the hidden layer of a multi-layer perceptron (MLP) endows the network with memory compression and noise tolerance capabilities. However, an MLP typically requires slow off-line learning to avoid ...
  • Default ARTMAP
    Carpenter, Gail (Boston University Center for Adaptive Systems and Department of Cognitive and Neural Systems, 2003-04)
    The default ARTMAP algorithm and its parameter values specified here define a ready-to-use general-purpose neural network system for supervised learning and recognition.
  • Default ARTMAP 2
    Amis, Gregory P.; Carpenter, Gail A. (Boston University Center for Adaptive Systems and Department of Cognitive and Neural Systems, 2007-01)
    Default ARTMAP combines winner-take-all category node activation during training , distributed activation during testing, and a set of default parameter values that define a ready-to-use, general-purpose neural network ...
  • Development in a Biologically Inspired Spinal Neural Network for Movement Control
    van Heijst, J.J.; Vos, J.E.; Bullock, D. (Boston University Center for Adaptive Systems and Department of Cognitive and Neural Systems, 1997-11)
    In two phases, we develop neural network models of spinal circuitry which self-organises into networks with opponent channels for the control of an antagonistic muscle pair. The self-organisation is enabled by spontaneous ...
  • DISCOV: A Neural Model of Colour Vision, with Applications to Image Processing and Classification
    Chelian, Suhas; Carpenter, Gail (Boston University Center for Adaptive Systems and Department of Cognitive and Neural Systems, 2005-03)
    The DISCOV (Dimensionless Shunting Colour Vision) system models a cascade of primate colour vision cells: retinal ganglion, thalamic single opponent, and two classes of cortical double opponents. A unified model fotmalism ...
  • Distributed Activation, Search, and Learning by ART and ARTMAP Neural Networks
    Carpenter, Gail A. (Boston University Center for Adaptive Systems and Department of Cognitive and Neural Systems, 1996-02)
    Adaptive resonance theory (ART) models have been used for learning and prediction in a wide variety of applications. Winner-take-all coding allows these networks to maintain stable memories, but this type of code representation ...
  • Distributed ARTMAP
    Carpenter, Gail A.; Milenova, Boriana L. (Boston University Center for Adaptive Systems and Department of Cognitive and Neural Systems, 1999-05)
    Distributed coding at the hidden layer of a multi-layer perceptron (MLP) endows the network with memory compression and noise tolerance capabilities. However, an MLP typically requires slow off-line learning to avoid ...
  • Distributed ART Networks for Learning, Recognition, and Prediction
    Carpenter, Gail A. (Boston University Center for Adaptive Systems and Department of Cognitive and Neural Systems, 1996-02)
    Adaptive resonance theory (ART) models have been used for learning and prediction in a wide variety of applications. Winner-take-all coding allows these networks to maintain stable memories, but this type of code representation ...
  • Distributed Hypothesis Testing, Attention Shifts and Transmitter Dynatmics During the Self-Organization of Brain Recognition Codes
    Carpenter, Gail A.; Grossberg, Stephen (Boston University Center for Adaptive Systems and Department of Cognitive and Neural Systems, 1991-02)
  • Distributed Learning, Recognition, and Prediction by ART and ARTMAP Neural Networks
    Carpenter, Gail A. (Boston University Center for Adaptive Systems and Department of Cognitive and Neural Systems, 1996-01)
    A class of adaptive resonance theory (ART) models for learning, recognition, and prediction with arbitrarily distributed code representations is introduced. Distributed ART neural networks combine the stable fast learning ...
  • A Distributed Outstar Network for Spatial Pattern Learning
    Carpenter, Gail A. (Boston University Center for Adaptive Systems and Department of Cognitive and Neural Systems, 1993-03)
    The distributed outstar, a generalization of the outstar neural network for spatial pattern learning, is introduced. In the outstar, signals from a source node cause weights to learn and recall arbitrary patterns across a ...
  • Does Binocular Rivalry Emerge from Cortical Mechanisms of 3D Vision
    Grossberg, Stephen; Yazdanbakhsh, Arash; Swaminathan, Guru; Cao, Yongqiang (Boston University Center for Adaptive Systems and Department of Cognitive and Neural Systems, 2006-10)
    Under natural viewing conditions, a single depthful percept of the world is consciously seen. When dissimilar images are presented to corresponding regions of the two eyes, binocular rivalry may occur, during which the ...
  • A Dopamine-Acetylcholine Cascade: Simulating Learned and Lesion-Induced Behavior ff Striatal Cholinergic Interneurons
    Tan, Can Ozan; Bullock, Daniel (Boston University Center for Adaptive Systems and Department of Cognitive and Neural Systems, 2007-02)
    The "teaching signal" that modulates reinforcement learning at cortico-striatal synapses may be a sequence composed of an adaptively scaled DA burst, a brief ACh burst, and a scaled ACh pause. Such an interpretation is ...
  • Dopaminergic and Non-Dopaminergic Value Systems in Conditioning and Outcome-Specific Revaluation
    Dranias, Mark R.; Grossberg, Stephen; Bullock (Boston University Center for Adaptive Systems and Department of Cognitive and Neural Systems, 2007-12)
    Animals are motivated to choose environmental options that can best satisfy current needs. To explain such choices, this paper introduces the MOTIVATOR (Matching Objects To Internal Values Triggers Option Revaluations) ...
  • Dynamic Binding of Visual Contours Without Temporal Coding
    Williamson, James (Boston University Center for Adaptive Systems and Department of Cognitive and Neural Systems, 1993-01)
    Recognition of objects in complex visual scenes is greatly simplified by the ability to segment features belonging to different objects while grouping features belonging to the same object. This feature-binding process can ...
  • Dynamic Programming for Optimal Control of Set-Up Scheduling with Neural Network Modifications
    Bradski, Gary (Boston University Center for Adaptive Systems and Department of Cognitive and Neural Systems, 1992-02)
    This paper demonstrates an optimal control solution to change of machine set-up scheduling based on dynamic programming average cost per stage value iteration as set forth by Cararnanis et. al. [2] for the 2D case. The ...
  • Dynamics of Attention in Depth: Evidence from Mutli-Element Tracking
    Viswanathan, Lavanya; Mingolla, Ennio (Boston University Center for Adaptive Systems and Department of Cognitive and Neural Systems, 1999-04)
    The allocation of attention in depth is examined using a multi-element tracking paradigm. Observers are required to track a predefined subset of from two to eight elements in displays containing up to sixteen identical ...
  • Effects of Highlights on Gloss Perception
    Berzhanskaya, Julia; Swaminathan, Gurumurthy; Beck, Jacob; Mingolla, Ennio (Boston University Center for Adaptive Systems and Department of Cognitive and Neural Systems, 2003-02)
    The perception of a glossy surface in a static monochromatic image can occur when a bright highlight is embedded in a compatible context of shading and a bounding contour. Some images naturally give rise to the impression ...
  • The Effects of L(+), D(-), and DL-2-amino-4-phosphonobutyrate (APB) on Electroretinogram and Ganglopn Cell Activity in the Cat Retina
    Przybyszewski, A.W.; Sucher, N.J.; Grüsser, O.-J. (Boston University Center for Adaptive Systems and Department of Cognitive and Neural Systems, 1995-01)
    L(+)-, D(-)-, or DL-2-amino-4-phosphonobutyric acid (APB; 2.5- 16 μmol) were injected into the vitreous body of anesthetized adult cats. The retina was stimulated by diffuse square wave light flashes (10- 60 ms). The ...
  • Eliminating Redundant Training Data Using Unsupervised Clustering Techniques
    Gonsalves, Paul G.; Snorrason, Magnus; Caglayan, Alper K. (Boston University Center for Adaptive Systems and Department of Cognitive and Neural Systems, 1993-01)
    Training data for supervised learning neural networks can be clustered such that the input/output pairs in each cluster are redundant. Redundant training data can adversely affect training time. In this paper we apply two ...

Search OpenBU


Advanced Search

Browse

Deposit Materials