Extremely Fast Neural Computation Using Tally Numeral Arithmetic

2019 ◽  
pp. 205-212
Author(s):  
Kosuke Imamura
Keyword(s):  
Neural Computation

Mixture of principal axes registration: a neural computation approach

2002 ◽  
Author(s):  
Rujirutana Srikanchana ◽  
Jianhua Xuan ◽  
Kun Huang ◽  
Matthew T. Freedman ◽  
Yue J. Wang
Keyword(s):  
Neural Computation ◽  
Principal Axes

scholarly journals Neural computation of visual imaging based on Kronecker product in the primary visual cortex

2010 ◽  
Vol 11 (1) ◽  
pp. 43 ◽  
Author(s):  
Zhao Songnian ◽  
Zou Qi ◽  
Jin Zhen ◽  
Yao Guozheng ◽  
Yao Li
Keyword(s):  
Visual Cortex ◽  
Primary Visual Cortex ◽  
Kronecker Product ◽  
Neural Computation ◽  
Visual Imaging

Coherent Compound Motion: Corners and Nonrigid Configurations

1990 ◽  
Vol 2 (1) ◽  
pp. 44-57 ◽  
Author(s):  
Steven W. Zucker ◽  
Lee Iverson ◽  
Robert A. Hummel
Keyword(s):  
Neural Computation ◽  
Coherent Motion ◽  
Natural Scenes ◽  
Motion Patterns ◽  
Motion System ◽  
Sinusoidal Gratings ◽  
Single Compound ◽  
Sharp Corners ◽  
Wire Gratings ◽  
Planar Motions

Consider two wire gratings, superimposed and moving across each other. Under certain conditions the two gratings will cohere into a single, compound pattern, which will appear to be moving in another direction. Such coherent motion patterns have been studied for sinusoidal component gratings, and give rise to percepts of rigid, planar motions. In this paper we show how to construct coherent motion displays that give rise to nonuniform, nonrigid, and nonplanar percepts. Most significantly, they also can define percepts with corners. Since these patterns are more consistent with the structure of natural scenes than rigid sinusoidal gratings, they stand as interesting stimuli for both computational and physiological studies. To illustrate, our display with sharp corners (tangent discontinuities or singularities) separating regions of coherent motion suggests that smoothing does not cross tangent discontinuities, a point that argues against existing (regularization) algorithms for computing motion. This leads us to consider how singularities can be confronted directly within optical flow computations, and we conclude with two hypotheses: (1) that singularities are represented within the motion system as multiple directions at the same retinotopic location; and (2) for component gratings to cohere, they must be at the same depth from the viewer. Both hypotheses have implications for the neural computation of coherent motion.

scholarly journals Memristors for the Curious Outsiders

Technologies ◽  
2018 ◽  
Vol 6 (4) ◽  
pp. 118 ◽  
Author(s):  
Francesco Caravelli ◽  
Juan Carbajal
Keyword(s):  
Machine Learning ◽  
Physical Mechanism ◽  
Neural Computation ◽  
Dynamic Resistance ◽  
Passive Component ◽  
Internal Parameter ◽  
New Approaches ◽  
Memristive Behavior ◽  
Memristive Circuits

We present both an overview and a perspective of recent experimental advances and proposed new approaches to performing computation using memristors. A memristor is a 2-terminal passive component with a dynamic resistance depending on an internal parameter. We provide an brief historical introduction, as well as an overview over the physical mechanism that lead to memristive behavior. This review is meant to guide nonpractitioners in the field of memristive circuits and their connection to machine learning and neural computation.

scholarly journals Explainable Neural Computation via Stack Neural Module Networks

2018 ◽  
pp. 55-71 ◽  
Author(s):  
Ronghang Hu ◽  
Jacob Andreas ◽  
Trevor Darrell ◽  
Kate Saenko
Keyword(s):  
Neural Computation

scholarly journals Erratum: Normalization as a canonical neural computation

2013 ◽  
Vol 14 (2) ◽  
pp. 152-152 ◽  
Author(s):  
Matteo Carandini ◽  
David J. Heeger
Keyword(s):  
Neural Computation
Sign in / Sign up

Export Citation Format

Share Document