Cargando…
From Continuous Observations to Symbolic Concepts: A Discrimination-Based Strategy for Grounded Concept Learning
Autonomous agents perceive the world through streams of continuous sensori-motor data. Yet, in order to reason and communicate about their environment, agents need to be able to distill meaningful concepts from their raw observations. Most current approaches that bridge between the continuous and sy...
Autores principales: | Nevens, Jens, Van Eecke, Paul, Beuls, Katrien |
---|---|
Formato: | Online Artículo Texto |
Lenguaje: | English |
Publicado: |
Frontiers Media S.A.
2020
|
Materias: | |
Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC7806012/ https://www.ncbi.nlm.nih.gov/pubmed/33501251 http://dx.doi.org/10.3389/frobt.2020.00084 |
Ejemplares similares
-
Semantic Mapping Based on Spatial Concepts for Grounding Words Related to Places in Daily Environments
por: Katsumata, Yuki, et al.
Publicado: (2019) -
Symbolic Representation and Learning With Hyperdimensional Computing
por: Mitrokhin, Anton, et al.
Publicado: (2020) -
Combining Unsupervised and Supervised Learning for Sample Efficient Continuous Language Grounding
por: Roesler, Oliver
Publicado: (2022) -
Symbolic Learning and Reasoning With Noisy Data for Probabilistic Anchoring
por: Zuidberg Dos Martires, Pedro, et al.
Publicado: (2020) -
Symbolic-Based Recognition of Contact States for Learning Assembly Skills
por: Al-Yacoub, Ali, et al.
Publicado: (2019)