Zobrazeno 1 - 10
of 34
pro vyhledávání: '"Matthew Luciw"'
Publikováno v:
Artificial Intelligence. 247:313-335
In the absence of external guidance, how can a robot learn to map the many raw pixels of high-dimensional visual inputs to useful action sequences? We propose here Continual Curiosity driven Skill Acquisition (CCSA). CCSA makes robots intrinsically m
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::63b65f7a178fae5606cd01655ef0d683
https://doi.org/10.1016/j.artint.2015.02.001
https://doi.org/10.1016/j.artint.2015.02.001
Autor:
Matthew Luciw, Juyang Weng
Publikováno v:
IEEE Intelligent Systems. 29:14-22
It's unclear how our brain's concepts emerge sequentially, and how the brain abstracts and generalizes each concept internally. The artificial intelligence field has seen the rise of model-based methods, where, starting from a predefined set of tasks
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::9ad8b71db023e138958d1e942b66361e
https://doi.org/10.1109/mis.2014.75
https://doi.org/10.1109/mis.2014.75
Publikováno v:
ACM Transactions on Interactive Intelligent Systems. 4:1-25
We introduce a novel algorithm called upper confidence - weighted learning (UCWL) for online multiclass learning from binary feedback (e.g., feedback that indicates whether the prediction was right or wrong). UCWL combines the upper confidence bound
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::f64de1e3f4e4293ba8cc52df93bfdf4e
https://doi.org/10.1145/2629631
https://doi.org/10.1145/2629631
Publikováno v:
IEEE Transactions on Autonomous Mental Development. 5:89-116
Informed by brain anatomical studies, we present the developmental network (DN) theory on brain-like temporal information processing. The states of the brain are at its effector end, emergent and open. A finite automaton (FA) is considered an externa
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::c1c1dc10f445f28acdb467b9e68abe74
https://doi.org/10.1109/tamd.2013.2258398
https://doi.org/10.1109/tamd.2013.2258398
Publikováno v:
Neural computation. 28(8)
Consider a self-motivated artificial agent who is exploring a complex environment. Part of the complexity is due to the raw high-dimensional sensory input streams, which the agent needs to make sense of. Such inputs can be compactly encoded through a
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::8f5cfaa35df4407a54d0a8bc3b85a386
https://pubmed.ncbi.nlm.nih.gov/27348735
https://pubmed.ncbi.nlm.nih.gov/27348735
Autor:
Matthew Luciw, Juyang Weng
Publikováno v:
IEEE Transactions on Autonomous Mental Development. 4:161-185
This is a theoretical, modeling, and algorithmic paper about the spatial aspect of brain-like information processing, modeled by the developmental network (DN) model. The new brain architecture allows the external environment (including teachers) to
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::a84db6db42caf9bf685bdede85b8bdc0
https://doi.org/10.1109/tamd.2011.2174636
https://doi.org/10.1109/tamd.2011.2174636
Publikováno v:
IEEE Transactions on Intelligent Transportation Systems. 12:402-411
In this paper, we propose an object learning system that incorporates sensory information from an automotive radar system and a video camera. The radar system provides coarse attention for the focus of visual analysis on relatively small areas within
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::1d28d7e01e866a9f3704edd96bd2fa67
https://doi.org/10.1109/tits.2010.2094188
https://doi.org/10.1109/tits.2010.2094188
Autor:
Juyang Weng, Matthew Luciw
Publikováno v:
IEEE Transactions on Autonomous Mental Development. 2:248-261
We investigate the effects of top-down input connections from a later layer to an earlier layer in a biologically inspired network. The incremental learning method combines optimal Hebbian learning for stable feature extraction, competitive lateral i
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::ec72cd9bfad49d40783985f520d51683
https://doi.org/10.1109/tamd.2010.2072150
https://doi.org/10.1109/tamd.2010.2072150
Autor:
Matthew Luciw, Juyang Weng
Publikováno v:
IEEE Transactions on Autonomous Mental Development. 1:68-85
Development imposes great challenges. Internal ldquocorticalrdquorepresentations must be autonomously generated from interactive experiences. The eventual quality of these developed representations is of course important. Additionally, learning must
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::929f679319f6f90ec143f7bce630a0e5
https://doi.org/10.1109/tamd.2009.2021698
https://doi.org/10.1109/tamd.2009.2021698
Publikováno v:
Paladyn: Journal of Behavioral Robotics, Vol 6, Iss 1 (2015)
In order to proceed along an action sequence, an autonomous agent has to recognize that the intended final condition of the previous action has been achieved. In previous work, we have shown how a sequence of actions can be generated by an embodied a
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::208a2e30b671a4850fa71d86f266dba2
https://doaj.org/article/0e54079367cd4722bceb12c190811a7d
https://doaj.org/article/0e54079367cd4722bceb12c190811a7d