Human-like Learning: A Research Proposal
We propose Human-like Learning, a new machine learning paradigm aiming at training generalist AI systems in a human-like manner with a focus on human-unique skills.
Main Authors: | Liao, Qianli, Poggio, Tomaso |
---|---|
Other Authors: | Center for Brains, Minds, and Machines |
Format: | Working Paper |
Language: | en_US |
Published: |
2017
|
Online Access: | http://hdl.handle.net/1721.1/111654 |
Similar Items
-
Representations That Learn vs. Learning Representations
by: Liao, Qianli, et al.
Published: (2018) -
Object-Oriented Deep Learning
by: Liao, Qianli, et al.
Published: (2017) -
Theory II: Landscape of the Empirical Risk in Deep Learning
by: Poggio, Tomaso, et al.
Published: (2017) -
Bridging the Gaps Between Residual Learning, Recurrent Neural Networks and Visual Cortex
by: Liao, Qianli, et al.
Published: (2016) -
3D Object-Oriented Learning: An End-to-end Transformation-Disentangled 3D Representation
by: Liao, Qianli, et al.
Published: (2018)