<html xmlns:v="urn:schemas-microsoft-com:vml" xmlns:o="urn:schemas-microsoft-com:office:office" xmlns:w="urn:schemas-microsoft-com:office:word" xmlns:m="http://schemas.microsoft.com/office/2004/12/omml" xmlns="http://www.w3.org/TR/REC-html40"><head><meta http-equiv=Content-Type content="text/html; charset=us-ascii"><meta name=Generator content="Microsoft Word 14 (filtered medium)"><style><!--
/* Font Definitions */
@font-face
{font-family:"MS Gothic";
panose-1:2 11 6 9 7 2 5 8 2 4;}
@font-face
{font-family:"MS Gothic";
panose-1:2 11 6 9 7 2 5 8 2 4;}
@font-face
{font-family:"MS Gothic";
panose-1:2 11 6 9 7 2 5 8 2 4;}
/* Style Definitions */
p.MsoNormal, li.MsoNormal, div.MsoNormal
{margin:0mm;
margin-bottom:.0001pt;
text-align:justify;
text-justify:inter-ideograph;
font-size:10.5pt;
font-family:"Arial","sans-serif";}
a:link, span.MsoHyperlink
{mso-style-priority:99;
color:blue;
text-decoration:underline;}
a:visited, span.MsoHyperlinkFollowed
{mso-style-priority:99;
color:purple;
text-decoration:underline;}
span.17
{mso-style-type:personal-compose;
font-family:"Arial","sans-serif";
color:windowtext;}
.MsoChpDefault
{mso-style-type:export-only;
font-family:"Arial","sans-serif";}
/* Page Definitions */
@page WordSection1
{size:612.0pt 792.0pt;
margin:99.25pt 30.0mm 30.0mm 30.0mm;}
div.WordSection1
{page:WordSection1;}
--></style><!--[if gte mso 9]><xml>
<o:shapedefaults v:ext="edit" spidmax="1026">
<v:textbox inset="5.85pt,.7pt,5.85pt,.7pt" />
</o:shapedefaults></xml><![endif]--><!--[if gte mso 9]><xml>
<o:shapelayout v:ext="edit">
<o:idmap v:ext="edit" data="1" />
</o:shapelayout></xml><![endif]--></head><body lang=JA link=blue vlink=purple style='text-justify-trim:punctuation'><div class=WordSection1><p class=MsoNormal><span lang=EN-US style='font-size:10.0pt'>We announce a newly published paper which investigates how spatio-temporal hierarchy can be self-organized in learning of dynamic visual patterns by imposing multi-scales spatio-temporal constraints on neural activity in a dynamic neural network model.<o:p></o:p></span></p><p class=MsoNormal><span lang=EN-US style='font-size:10.0pt'><o:p> </o:p></span></p><p class=MsoNormal><span lang=EN-US style='font-size:10.0pt'>The following web page contains PDF, demonstrative video and source code.<o:p></o:p></span></p><p class=MsoNormal><span lang=EN-US style='font-size:10.0pt'><a href="http://neurorobot.kaist.ac.kr/project.html">http://neurorobot.kaist.ac.kr/project.html</a><o:p></o:p></span></p><p class=MsoNormal><span lang=EN-US style='font-size:10.0pt'><o:p> </o:p></span></p><p class=MsoNormal><span lang=EN-US style='font-size:10.0pt'>Jung, M., Hwang, J., & Tani, J. (2015). Self-organization of spatio-temporal hierarchy via learning of dynamic visual image patterns on action sequences. PLoS One 10(7): e0131214. doi: 10.1371/journal.pone.0131214.<o:p></o:p></span></p><p class=MsoNormal><span lang=EN-US style='font-size:10.0pt'><a href="http://www.plosone.org/article/fetchObject.action?uri=info:doi/10.1371/journal.pone.0131214&representation=PDF">http://www.plosone.org/article/fetchObject.action?uri=info:doi/10.1371/journal.pone.0131214&representation=PDF</a><o:p></o:p></span></p><p class=MsoNormal><span lang=EN-US style='font-size:10.0pt'><o:p> </o:p></span></p><p class=MsoNormal><span lang=EN-US style='font-size:10.0pt'>Abstract:<o:p></o:p></span></p><p class=MsoNormal><span lang=EN-US style='font-size:10.0pt'>It is well known that the visual cortex efficiently processes high-dimensional spatial information by using a hierarchical structure. Recently, computational models that were inspired by the spatial hierarchy of the visual cortex have shown remarkable performance in image recognition. Up to now, however, most biological and computational modeling studies have mainly focused on the spatial domain and do not discuss temporal domain processing of the visual cortex. Several studies on the visual cortex and other brain areas associated with motor control support that the brain also uses its hierarchical structure as a processing mechanism for temporal information. Based on the success of previous computational models using spatial hierarchy and temporal hierarchy observed in the brain, the current report introduces a novel neural network model for the recognition of dynamic visual image patterns based solely on the learning of exemplars. This model is characterized by the application of both spatial and temporal constraints on local neural activities, resulting in the self-organization of a spatio-temporal hierarchy necessary for the recognition of complex dynamic visual image patterns. The evaluation with the Weizmann dataset in recognition of a set of prototypical human movement patterns showed that the proposed model is significantly robust in recognizing dynamically occluded visual patterns compared to other baseline models. Furthermore, an evaluation test for the recognition of concatenated sequences of those prototypical movement patterns indicated that the model is endowed with a remarkable capability for the contextual recognition of long-range dynamic visual image patterns.<o:p></o:p></span></p><p class=MsoNormal><span lang=EN-US style='font-size:10.0pt'><o:p> </o:p></span></p><p class=MsoNormal><span lang=EN-US style='font-size:10.0pt'><o:p> </o:p></span></p><p class=MsoNormal><span lang=EN-US>Jun Tani, Ph.D<o:p></o:p></span></p><p class=MsoNormal><span lang=EN-US>Professor, Department of Electrical Engineering, KAIST<o:p></o:p></span></p><p class=MsoNormal><span lang=EN-US>Building: N1, room: 516<o:p></o:p></span></p><p class=MsoNormal><span lang=EN-US>http://neurorobot.kaist.ac.kr/tani.htm<o:p></o:p></span></p><p class=MsoNormal><span lang=EN-US>tani1216jp@gmail.com<o:p></o:p></span></p><p class=MsoNormal><span lang=EN-US>042-350-7428<o:p></o:p></span></p><p class=MsoNormal><span lang=EN-US><o:p> </o:p></span></p></div></body></html>