Parallel distributed processing: explorations in the microstructure of cognition, vol. 1: foundations
Computational Explorations in Cognitive Neuroscience: Understanding the Mind by Simulating the Brain
Computational Explorations in Cognitive Neuroscience: Understanding the Mind by Simulating the Brain
Sequence Learning in the ACT-R Cognitive Architecture: Empirical Analysis of a Hybrid Model
Sequence Learning - Paradigms, Algorithms, and Applications
On Intelligence
Children and robots learning to play hide and seek
Proceedings of the 1st ACM SIGCHI/SIGART conference on Human-robot interaction
Engines of the brain: the computational instruction set of human cognition
AI Magazine - Special issue on achieving human-level AI through integrated systems and research
Bimodal spatial reasoning with continuous motion
AAAI'08 Proceedings of the 23rd national conference on Artificial intelligence - Volume 3
Simple games as dynamic, coupled systems: randomness and other emergent properties
Cognitive Systems Research
Transparent neural networks: integrating concept formation and reasoning
AGI'12 Proceedings of the 5th international conference on Artificial General Intelligence
| Hi-index | 0.00 |
Current perceptual algorithms are error-prone and require the use of additional ad hoc heuristic methods that detect and recover from these errors. In this paper we explore how existing architectural mechanisms in a high-level cognitive architecture like ACT-R can be used instead of such ad hoc measures. In particular, we describe how implicit learning that results from ACT-R's architectural features of partial matching and blending can be used to recover from errors in object identification, tracking and action prediction. We demonstrate its effectiveness by building a model that can identify and track objects as well as predict their actions in a simple checkpoint scenario.