Zobrazeno 1 - 10
of 20
pro vyhledávání: '"Matthew Conforth"'
Autor:
Yan Meng, Matthew Conforth
Publikováno v:
Robotics, Automation and Control
One of the most used artificial neural networks (ANNs) models is the well-known MultiLayer Perceptron (MLP) [Haykin, 1998]. The training process of MLPs for pattern classification problems consists of two tasks, the first one is the selection of an a
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::16b8d8a4f5748f0e5305b6c4a072d2fd
http://www.intechopen.com/articles/show/title/an_artificial_neural_network_based_learning_method_for_mobile_robot_localization
http://www.intechopen.com/articles/show/title/an_artificial_neural_network_based_learning_method_for_mobile_robot_localization
Autor:
Matthew Conforth, Yan Meng
Publikováno v:
IJCNN
The CIVS (Civilization-Inspired Vying Societies) system is a novel evolutionary learning multi-agent system loosely inspired by the history of human civilization. CIVS uses artificial life (Alife) methods to produce highly-capable artificial intellig
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::9c83f6d9afa71695bdfc5e2989f4623f
https://doi.org/10.1109/ijcnn.2011.6033453
https://doi.org/10.1109/ijcnn.2011.6033453
Autor:
Yan Meng, Matthew Conforth
Publikováno v:
IJCNN
In this paper, we are developing the CIVS (Civilization-Inspired Vying Societies) system, which is a novel evolutionary learning multi-agent system loosely inspired by the history of human civilization. The main objective of the CIVS system is to dev
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::a68b919b7cb7794b849fc07751cf5ff1
https://doi.org/10.1109/ijcnn.2011.6033455
https://doi.org/10.1109/ijcnn.2011.6033455
Autor:
Matthew Conforth, Yan Meng
Publikováno v:
Neural Networks.
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::579911e556db7dae83105b2a64dfcd8f
https://doi.org/10.1016/j.neunet.2011.07.001
https://doi.org/10.1016/j.neunet.2011.07.001
Publikováno v:
IJCNN
Detecting human activities automatically in a video stream in various scenes is a challenging task. The major difficulty of this task lies in how to extract the spatial and temporal features of video sequences so that the human activities can be reco
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::077b00d39d4e01d9e77008e1cf884255
https://pub.uni-bielefeld.de/record/2978613
https://pub.uni-bielefeld.de/record/2978613
Autor:
Matthew Conforth, Yan Meng
Publikováno v:
ALIFE
Simulation software is vital to ALife research. It is known that stoichiometry is important for modeling real world ecosystems. However, most currently available ALife simulators ignore stoichiometry mechanics. Of course, not all ALife research is tr
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::375eafb292e9eaa3176b1db95f6f6967
https://doi.org/10.1109/alife.2009.4937705
https://doi.org/10.1109/alife.2009.4937705
Publikováno v:
CIBCB
Identification of the most successful strategy for applications in tissue engineering is often confusing, with a wide variety of options and variables available, that can fit into an ideal graft or scaffold. The complexity of the problem is multifold
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::9a50675eaac0c0881315c2147c9f1a3c
https://doi.org/10.1109/cibcb.2009.4925730
https://doi.org/10.1109/cibcb.2009.4925730
Publikováno v:
IROS
Miniature robots have many advantages over their larger counterparts, such as low cost, low power, and easy to build a large scale team for complex tasks. Heterogeneous multi miniature robots could provide powerful situation awareness capability due
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::af0ee8d42454de4a7046f6f6448f91fe
https://doi.org/10.1109/iros.2008.4651001
https://doi.org/10.1109/iros.2008.4651001
Autor:
Matthew Conforth, Yan Meng
Publikováno v:
SIS
In this paper, we propose a swarm intelligence based reinforcement learning (SWIRL) method to train artificial neural networks (ANN). Basically, two swarm intelligence based algorithms are combined together to train the ANN models. Ant Colony Optimiz
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::4dd9b60d2fd06d90bee72b7ac3d43ce4
https://doi.org/10.1109/sis.2008.4668289
https://doi.org/10.1109/sis.2008.4668289
Publikováno v:
SPIE Proceedings.
Miniature robots have many advantages over their larger counterparts, such as low cost, low power, and easy to build a large scale team for complex tasks. Heterogeneous multi miniature robots could provide powerful situation awareness capability due
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::082f732ff23c5e41609e7a942edca045
https://doi.org/10.1117/12.782516
https://doi.org/10.1117/12.782516