000060064 001__ 60064
000060064 005__ 20181118044347.0
000060064 02470 $$2DAR$$a6616
000060064 037__ $$aARTICLE
000060064 245__ $$aThree Dimensional Frames of References Transformations  using Recurrent Populations of Neurons
000060064 269__ $$a2005
000060064 260__ $$c2005
000060064 336__ $$aJournal Articles
000060064 500__ $$aSponsor: Swiss National Science Foundation
000060064 520__ $$aThis work investigates whether population vector coding, a  distributed computational paradigm, could be a principle  mechanism for performing sensorimotor and frames of  reference transformations. This paper presents a multilayer  neural network that can perform arbitrary three-dimensional  rotations and translations. We demonstrate, both formally  and numerically, that the non-linearity of these  transformations can be resolved thanks to the recurrent and  concurrent activities of continuous populations of neurons.
000060064 6531_ $$aLearning by Imitation - Neural Modelling
000060064 700__ $$0240845$$aSauser, E.$$g119102
000060064 700__ $$0240594$$aBillard, A.$$g115671
000060064 773__ $$j64$$q5-24$$tNeurocomputing
000060064 8564_ $$zURL
000060064 8564_ $$s578316$$uhttps://infoscience.epfl.ch/record/60064/files/SB_Neurocomputing05.pdf$$zn/a
000060064 909C0 $$0252119$$pLASA$$xU10660
000060064 909CO $$ooai:infoscience.tind.io:60064$$pSTI$$pGLOBAL_SET$$particle
000060064 937__ $$aLSA3-ARTICLE-2005-001
000060064 970__ $$a534/LSA3
000060064 973__ $$aEPFL$$rREVIEWED$$sPUBLISHED
000060064 980__ $$aARTICLE