Symbolic models and emergent models: A review
J Weng - IEEE Transactions on Autonomous Mental …, 2011 - ieeexplore.ieee.org
There exists a large conceptual gap between symbolic models and emergent models for the
mind. Many emergent models work on low-level sensory data, while many symbolic models …
mind. Many emergent models work on low-level sensory data, while many symbolic models …
Dually optimal neuronal layers: Lobe component analysis
Development imposes great challenges. Internal ldquocorticalrdquorepresentations must be
autonomously generated from interactive experiences. The eventual quality of these …
autonomously generated from interactive experiences. The eventual quality of these …
Radar-vision fusion for object classification
Z Ji, D Prokhorov - 2008 11th International Conference on …, 2008 - ieeexplore.ieee.org
We propose an object classification system that incorporates information from a video
camera and an automotive radar. The system implements three processes. The first process …
camera and an automotive radar. The system implements three processes. The first process …
Developmental stereo: Emergence of disparity preference in models of the visual cortex
How our brains develop disparity tuned V 1 and V 2 cells and then integrate binocular
disparity into 3-D perception of the visual world is still largely a mystery. Moreover …
disparity into 3-D perception of the visual world is still largely a mystery. Moreover …
Where-what network 5: Dealing with scales for objects in complex backgrounds
X Song, W Zhang, J Weng - The 2011 International Joint …, 2011 - ieeexplore.ieee.org
The biologically-inspired developmental Where-What Networks (WWN) are general purpose
visuomotor networks for detecting and recognizing objects from complex backgrounds …
visuomotor networks for detecting and recognizing objects from complex backgrounds …
Motor initiated expectation through top-down connections as abstract context in a physical world
Recently, it has been shown that top-down connections improve recognition in supervised
learning. In the work presented here, we show how top-down connections represent …
learning. In the work presented here, we show how top-down connections represent …
Topographic class grouping with applications to 3d object recognition
The cerebral cortex uses a large number of top-down connections, but the roles of the top-
down connections remain unclear. Through end-to-end (sensor-to-motor) multilayered …
down connections remain unclear. Through end-to-end (sensor-to-motor) multilayered …
Five steps of evolution from non-life to life-like robots
M Xie - International Journal of Humanoid Robotics, 2009 - World Scientific
There are many interests in developing life-like robots, or robots which are both intelligent
and autonomous. And, one obvious characteristics of life-like creatures is that they can …
and autonomous. And, one obvious characteristics of life-like creatures is that they can …
一种改进型机器人仿生认知神经网络
钱夔， 宋爱国 - 电子学报, 2015 - ejournal.org.cn
为了更好地模拟人类视觉系统中的注意力选择, 本文提出一种改进型机器人仿生认知神经网络.
首先模拟人类视觉皮层结构, 在已有模型基础上建立改进型仿生认知神经网络模型; …
首先模拟人类视觉皮层结构, 在已有模型基础上建立改进型仿生认知神经网络模型; …
Laterally connected lobe component analysis: Precision and topography
Due to the pressure of evolution, the brains of organisms need to self-organize at different
scales during different developmental stages. In early stages, the brain must organize …
scales during different developmental stages. In early stages, the brain must organize …