Neuromodulated attention and goal-driven perception in uncertain domains
| Autor: | Jeffrey L. Krichmar, Xinyun Zou, Soheil Kolouri, Praveen K. Pilly |
|---|---|
| Rok vydání: | 2020 |
| Předmět: |
0209 industrial biotechnology
Computer science Cognitive Neuroscience media_common.quotation_subject Models Neurological 02 engineering and technology Task (project management) 020901 industrial engineering & automation Artificial Intelligence Perception Neuromodulation Reaction Time 0202 electrical engineering electronic engineering information engineering medicine Humans Attention media_common Uncertainty Neuromodulation (medicine) medicine.anatomical_structure Action (philosophy) Robot Cholinergic 020201 artificial intelligence & image processing Neural Networks Computer Goals MNIST database Cognitive psychology |
| Zdroj: | Neural Networks. 125:56-69 |
| ISSN: | 0893-6080 |
| Popis: | In uncertain domains, the goals are often unknown and need to be predicted by the organism or system. In this paper, contrastive Excitation Backprop (c-EB) was used in two goal-driven perception tasks - one with pairs of noisy MNIST digits and the other with a robot in an action-based attention scenario. The first task included attending to even, odd, low, and high digits, whereas the second task included action goals, such as "eat", "work-on-computer", "read", and "say-hi" that led to attention to objects associated with those actions. The system needed to increase attention to target items and decrease attention to distractor items and background noise. Because the valid goal was unknown, an online learning model based on the cholinergic and noradrenergic neuromodulatory systems was used to predict a noisy goal (expected uncertainty) and re-adapt when the goal changed (unexpected uncertainty). This neurobiologically plausible model demonstrates how neuromodulatory systems can predict goals in uncertain domains and how attentional mechanisms can enhance the perception for that goal. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|
Full Text from ScienceDirect