From neural networks to the brain: autonomous mental development Export

@article{citeulike:2681347, abstract = {Artificial neural networks can model cortical local learning and signal processing, but they are not the brain, neither are many special purpose systems to which they contribute. Autonomous mental development models all or part of the brain (or the central nervous system) and how it develops and learns autonomously from infancy to adulthood. Like neural network research, such modeling aims to be biologically plausible. This paper discusses why autonomous development is necessary according to a concept called task muddiness. Then it introduces results for a series of research issues, including the new paradigm for autonomous development, mental architectures, developmental algorithm, a refined classification of types of machine learning, spatial complexity and time complexity. Finally, the paper presents some experimental results for applications, including: vision-guided navigation, object finding, object-based attention (eye-pan), and attention-guided pre-reaching, tour tasks that infants learn to perform early but very perceptually challenging for robots}, author = {Weng, Juyang and Hwang, Wey-Shinan}, booktitle = {Computational Intelligence Magazine, IEEE}, citeulike-article-id = {2681347}, citeulike-linkout-0 = {http://dx.doi.org/10.1109/MCI.2006.1672985}, citeulike-linkout-1 = {http://ieeexplore.ieee.org/xpls/abs_all.jsp?arnumber=1672985}, doi = {10.1109/MCI.2006.1672985}, journal = {Computational Intelligence Magazine, IEEE}, keywords = {developmental, mental, robotics}, number = {3}, pages = {15--31}, posted-at = {2008-04-17 11:09:35}, priority = {0}, title = {From neural networks to the brain: autonomous mental development}, url = {http://dx.doi.org/10.1109/MCI.2006.1672985}, volume = {1}, year = {2006} }

TY - JOUR ID - citeulike:2681347 L3 - citeulike-article-id:2681347 N2 - Artificial neural networks can model cortical local learning and signal processing, but they are not the brain, neither are many special purpose systems to which they contribute. Autonomous mental development models all or part of the brain (or the central nervous system) and how it develops and learns autonomously from infancy to adulthood. Like neural network research, such modeling aims to be biologically plausible. This paper discusses why autonomous development is necessary according to a concept called task muddiness. Then it introduces results for a series of research issues, including the new paradigm for autonomous development, mental architectures, developmental algorithm, a refined classification of types of machine learning, spatial complexity and time complexity. Finally, the paper presents some experimental results for applications, including: vision-guided navigation, object finding, object-based attention (eye-pan), and attention-guided pre-reaching, tour tasks that infants learn to perform early but very perceptually challenging for robots IS - 3 JF - Computational Intelligence Magazine, IEEE EP - 31 TI - From neural networks to the brain: autonomous mental development VL - 1 T2 - Computational Intelligence Magazine, IEEE SP - 15 KW - developmental KW - mental KW - robotics AU - Weng, Juyang AU - Hwang, Wey-Shinan PY - 2006/// UR - http://dx.doi.org/10.1109/MCI.2006.1672985 ER -