webinar register page

Machine intelligence based on intelligence operating architecture
This talk introduces recent research outcomes of the Robot Intelligence Technology Laboratory (RITL) on MIL (Machine Intelligence Learning) for active knowledge acquisition and adaptive knowledge application. MIL has been applied to an agent-embedded robot, Mybot develop in the RITL, to build Machine Intelligence (MI) based on intelligence Operating Architecture (iOA). For natural interactions with users, Mybot employs imaginary keyboard (I-Keyboard), hand gesture recognition using a short-range radar sensor, and an air writing system, Air-Text three all for interface, CNN-DM (Developmental Memory) for continual learning for object recognition, Face-OICRN for online face registraton and recognition, WS-DNN (Word Similarity-DNN) and 3D Scene Graph both as semantic memory, SimVODIS for Simultaneous Visual Odometry, Object Detection, and Instance Segmentation, FSHMN (Full Sentence VQA Highway Memory Network) for VQA, EM-DRN (Episodic Memory-Developmental Resonance Network) as a long-term episodic memory, EM-DRN-Map for recommendation, e.g., the recipes of dishes. SF (Stabilized Feedback)-EM is developed for IoT-based Mybot as well. For temporal and spatiotemporal anomaly detections, RRN (Recurrent Reconstruction Network) and CRRN (Convolutional RRN) are introduced, respectively, and for multi-label classification, MarsNet and D3PointNet are also introduced. Lastly, a brand new world event, AI World Cup (http://aiworldcup.org) is introduced, which has three categories, AI Soccer, AI Commentator, and AI Journalist.

Sep 23, 2021 10:00 AM in Eastern Time (US and Canada)

Webinar logo
Webinar is over, you cannot register now. If you have any questions, please contact Webinar host: Andrea Pinos, Communications and Awards Officer.