Behavior Is Everything: Towards Representing Concepts with Sensorimotor Contingencies
By Nick J. Hay, Michael Stark, Alexander A. Schlegel, Carter Wendelken, Dennis Park, E. Purdy, Tom Silver, D. Scott Phoenix, Dileep George. 2018
25 citations recorded by the source corpus.
AI has seen remarkable progress in recent years, due to a switch from hand-designed shallow representations, to learned deep representations. While these methods excel with plentiful training data, they are still far from the human ability to learn concepts from just a few examples by reusing previously learned conceptual knowledge in new contexts. We argue that this gap might come from a fundamental misalignment between human and typical AI representations: while the former are grounded in rich sensorimotor experience, the latter are typically passive and limited to a few modalities such as vision and text. We take a step towards closing this gap by proposing an interactive, behavior-based model that represents concepts using sensorimotor contingencies grounded in an agent's experience. On a novel conceptual learning and benchmark suite, we demonstrate that conceptually meaningful behaviors can be learned, given supervision via training curricula.
Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition, Control and Systems Engineering
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Artificial Intelligence
- Yoshua Bengio
- Sergey Levine
- Ruslan Salakhutdinov
- Quoc V. Le
- Mohit Bansal
- Jianfeng Gao
- Kyunghyun Cho
- Percy Liang
In Computer Vision and Pattern Recognition
- Luc Van Gool
- Dacheng Tao
- Trevor Darrell
- Xiaogang Wang
- Andrew Zisserman
- Jitendra Malik
- Ming-Hsuan Yang
- Li Fei-Fei
In Control and Systems Engineering
- Razvan Pascanu
- Nicolas Manfred Otto Heess
- Peter W. Battaglia
- Oriol Vinyals
- Kelsey R. Allen
- Jessica B. Hamrick
- Miguel L'azaro-Gredilla
- Pushmeet Kohli
Citations in the corpus
- Relational inductive biases, deep learning, and graph networks (2018, background): “, 2018), developing model-based approaches with an emphasis on abstraction (Kansky et al., 2017; Konidaris et al., 2018; Zhang et al., 2018; Hay et al., 2018), investing more heavily in meta-learning (Wang et al.”
- Beyond imitation: Zero-shot task transfer on robots by learning concepts as cognitive programs (2018, background): “Perhaps some of the primitives could be learned by having an agent interact with the environment using mechanisms we elaborated earlier (69).”