Proposes five layers of abstraction for AI with complexity-performance and control-complexity trade-offs as a conceptual framework for organizing subfields and targeting innovation.
Experimental Demonstration and Tolerancing of a Large-Scale Neural Network (165 000 Synapses) Using Phase-Change Memory as the Synaptic Weight Element
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CY 1years
2019 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
A system of different layers of abstraction for artificial intelligence
Proposes five layers of abstraction for AI with complexity-performance and control-complexity trade-offs as a conceptual framework for organizing subfields and targeting innovation.