Learning perception and planning with deep active inference
- Author
- Ozan Catal (UGent) , Tim Verbelen (UGent) , Johannes Nauta (UGent) , Cedric De Boom (UGent) and Bart Dhoedt (UGent)
- Organization
- Project
- Abstract
- Active inference is a process theory of the brain that states that all living organisms infer actions in order to minimize their (expected) free energy. However, current experiments are limited to predefined, often discrete, state spaces. In this paper we use recent advances in deep learning to learn the state space and approximate the necessary probability distributions to engage in active inference.
- Keywords
- FREE-ENERGY PRINCIPLE, active inference, deep learning, perception, planning
Downloads
-
(...).pdf
- full text (Published version)
- |
- UGent only
- |
- |
- 1.42 MB
-
Catal O et al accepted manuscript.pdf
- full text (Accepted manuscript)
- |
- open access
- |
- |
- 1.50 MB
Citation
Please use this url to cite or link to this publication: http://hdl.handle.net/1854/LU-8662308
- MLA
- Catal, Ozan, et al. “Learning Perception and Planning with Deep Active Inference.” ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), IEEE, 2020, pp. 3952–56, doi:10.1109/ICASSP40776.2020.9054364.
- APA
- Catal, O., Verbelen, T., Nauta, J., De Boom, C., & Dhoedt, B. (2020). Learning perception and planning with deep active inference. In ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) (pp. 3952–3956). New York: IEEE. https://doi.org/10.1109/ICASSP40776.2020.9054364
- Chicago author-date
- Catal, Ozan, Tim Verbelen, Johannes Nauta, Cedric De Boom, and Bart Dhoedt. 2020. “Learning Perception and Planning with Deep Active Inference.” In ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 3952–56. New York: IEEE. https://doi.org/10.1109/ICASSP40776.2020.9054364.
- Chicago author-date (all authors)
- Catal, Ozan, Tim Verbelen, Johannes Nauta, Cedric De Boom, and Bart Dhoedt. 2020. “Learning Perception and Planning with Deep Active Inference.” In ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 3952–3956. New York: IEEE. doi:10.1109/ICASSP40776.2020.9054364.
- Vancouver
- 1.Catal O, Verbelen T, Nauta J, De Boom C, Dhoedt B. Learning perception and planning with deep active inference. In: ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). New York: IEEE; 2020. p. 3952–6.
- IEEE
- [1]O. Catal, T. Verbelen, J. Nauta, C. De Boom, and B. Dhoedt, “Learning perception and planning with deep active inference,” in ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Barcelona, Spain, 2020, pp. 3952–3956.
@inproceedings{8662308,
abstract = {Active inference is a process theory of the brain that states that all living organisms infer actions in order to minimize their (expected) free energy. However, current experiments are limited to predefined, often discrete, state spaces. In this paper we use recent advances in deep learning to learn the state space and approximate the necessary probability distributions to engage in active inference.},
author = {Catal, Ozan and Verbelen, Tim and Nauta, Johannes and De Boom, Cedric and Dhoedt, Bart},
booktitle = {ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)},
isbn = {9781509066315},
issn = {2379-190X},
keywords = {FREE-ENERGY PRINCIPLE,active inference,deep learning,perception,planning},
language = {eng},
location = {Barcelona, Spain},
pages = {3952--3956},
publisher = {IEEE},
title = {Learning perception and planning with deep active inference},
url = {http://dx.doi.org/10.1109/ICASSP40776.2020.9054364},
year = {2020},
}
- Altmetric
- View in Altmetric
- Web of Science
- Times cited: