Title： Bimodal Incremental Self-Organizing Network (BiSON) with Application to Learning Chinese Characters
Speaker： Dr. Andrew P. Paplinski
Associate Professor in the Clayton School of Information Technology Monash University
Date/Time：2014/4/29(二) 13：20~15：00
Venue：國立交通大學 電子資訊中心第3會議室
Abstract：
We present a recurrent learning system that can incrementally integrate stimuli in two modalities, visual and auditory. The system consists of five self-organizing modules, each mapping input stimuli into respective latent spaces. Two sensory modules convert the input stimuli into an internal 3-D "neuronal code". The central module integrates the bimodal information, and through modulatory top-down feedback influences the organization of data in two unimodal association units.
Two feedback gains control the strength of the feedback connection. As an example we selected a set of Chinese characters and related spoken words. It is shown that the learning system can build a stable neuronal structure for incrementally applied visual and auditory stimuli.
講者簡介（下載）
主辦單位：電腦視覺研發中心、高階繪圖與立體視訊基礎技術研發中心
協辦單位：電腦視覺監控產學研聯盟推動計畫
講題： Bimodal Incremental Self-Organizing Network (BiSON) with Application to Learning Chinese Characters
講者： Dr. Andrew P. Paplinski
Associate Professor in the Clayton School of Information Technology Monash University
時間：2014/4/29(二) 13：20~15：00
地點：國立交通大學 電子資訊中心第3會議室
參加資格：不限
Abstract：
We present a recurrent learning system that can incrementally integrate stimuli in two modalities, visual and auditory. The system consists of five self-organizing modules, each mapping input stimuli into respective latent spaces. Two sensory modules convert the input stimuli into an internal 3-D "neuronal code". The central module integrates the bimodal information, and through modulatory top-down feedback influences the organization of data in two unimodal association units.
Two feedback gains control the strength of the feedback connection. As an example we selected a set of Chinese characters and related spoken words. It is shown that the learning system can build a stable neuronal structure for incrementally applied visual and auditory stimuli.
講者簡介（下載）
主辦單位：電腦視覺研發中心、高階繪圖與立體視訊基礎技術研發中心
協辦單位：電腦視覺監控產學研聯盟推動計畫