Minoru Asada<\/a><\/p>\n\n\n\nAbstract:
The ability of the brain to generate complex spatiotemporal patterns with a specific timing is essential for motor learning and time series prediction. An approach that tries to replicate this ability using the self-sustained neural activity of a randomly connected recurrent neural network (RNN), i.e., reservoir, meets the difficulty of orbital instability. We proposed a novel model that learns an arbitrary time series as the linear sum of stable trajectories produced by a large number of small random RNN modules. Our experimental results show that the trajectories of the module outputs are orthogonal to each other, that is, the reservoir self-organizes an orthogonal basis, that enables the model to learn the timing of extremely long intervals and complex time series of Lorenz system.<\/p>\n","protected":false},"featured_media":0,"template":"","acf":[],"_links":{"self":[{"href":"http:\/\/cinetjp-static3.nict.go.jp\/english\/wp-json\/wp\/v2\/event\/713"}],"collection":[{"href":"http:\/\/cinetjp-static3.nict.go.jp\/english\/wp-json\/wp\/v2\/event"}],"about":[{"href":"http:\/\/cinetjp-static3.nict.go.jp\/english\/wp-json\/wp\/v2\/types\/event"}],"wp:attachment":[{"href":"http:\/\/cinetjp-static3.nict.go.jp\/english\/wp-json\/wp\/v2\/media?parent=713"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}