0.25
0.5
0.75
1.25
1.5
1.75
2
An Efficient Bit Vector Approach to Semantics-based Machine Perception in Resource-Constrained Devices
Published on Dec 03, 20122895 Views
The primary challenge of machine perception is to define efficient computational methods to derive high-level knowledge from low-level sensor observation data. Emerging solutions are using ontologies
Related categories
Chapter list
Kno.e.sis00:00
The Patient of the Future - MIT Technology Review, 201200:02
What if we could automate this sense making ability?00:45
An Efficient Bit Vector Approach to Semantics-based Machine Perception in Resource-constrained Devices01:13
Sensing is a key enabler of the Internet of Things01:30
People are good at making sense of sensory input02:19
Perception Cycle02:51
Semantic Web technology04:15
The Web is becoming a global knowledge base04:32
Prior knowledge on the Web - 104:48
Prior knowledge on the Web - 205:53
Explanation - 106:14
Explanation - 206:29
Explanation - 307:44
Discrimination - 108:21
Discrimination - 208:35
Discrimination - 309:13
Discrimination - 409:41
Our Motivation10:33
How do we implement machine perception efficiently on a resource-constrained device?11:12
Intelligence at the edge11:54
Efficient execution of machine perception12:58
Lifting and lowering knowledge13:17
Explanation: efficient algorithm13:55
Discrimination: efficient algorithm16:06
Evaluation on a mobile device - 118:19
Evaluation on a mobile device - 218:20
Evaluation on a mobile device - 319:41
3 ideas to takeaway20:03
Thank you21:29