Abstract
Reflection on one’s thought process and making corrections to it if there exists dissatisfaction in its performance is, perhaps, one of the essential traits of intelligence. However, such high-level abstract concepts mandatory for Artificial General Intelligence can be modelled even at the low level of narrow Machine Learning algorithms. Here, we present the self-awareness mechanism emulation in the form of a supervising artificial neural network (ANN) observing patterns in activations of another underlying ANN in a search for indications of the high uncertainty of the underlying ANN and, therefore, the trustworthiness of its predictions. The underlying ANN is a convolutional neural network (CNN) ensemble employed for face recognition and facial expression tasks. The self-awareness ANN has a memory region where its past performance information is stored, and its learnable parameters are adjusted during the training to optimize the performance. The trustworthiness verdict triggers the active learning mode, giving elements of agency to the machine learning algorithm that asks for human help in high uncertainty and confusion conditions.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
Cacioppo, J.T., Berntson, G.G., Larsen, J.T., Poehlmann, K.M., Ito, T.A., et al.: The psychophysiology of emotion. Handb. Emotions 2(01), 2000 (2000)
Chomsky, N.: Powers and Prospects: Reflections on Human Nature and the Social Order. South End Press (1996)
Ekman, P., Friesen, W.V.: Constants across cultures in the face and emotion. J. Pers. Soc. Psychol. 17(2), 124 (1971)
Knowledge, P.: Yoshua Bengio \(\vert \) From System 1 Deep Learning to System 2 Deep Learning \(\vert \) NeurIPS 2019 (2019). www.youtube.com/watch?v=FtUbMG3rlFs. Accessed 11 Apr 2022
LeCun, Y.: A path towards autonomous machine intelligence version 0.9. 2, 2022–06-27 (2022)
Lewis, D.D., Catlett, J.: Heterogeneous uncertainty sampling for supervised learning. In: Machine Learning Proceedings 1994, pp. 148–156. Elsevier (1994)
Li, K., et al.: Mural: meta-learning uncertainty-aware rewards for outcome-driven reinforcement learning. In: International Conference on Machine Learning, pp. 6346–6356. PMLR (2021)
Marcheggiani, D., Artieres, T.: An experimental comparison of active learning strategies for partially labeled sequences. In: Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP), pp. 898–906 (2014)
McCarthy, J., Hayes, P.J.: Some philosophical problems from the standpoint of artificial intelligence. In: Readings in Artificial Intelligence, pp. 431–450. Elsevier (1981)
Qiu, L., et al.: Resisting out-of-distribution data problem in perturbation of xai. arXiv preprint arXiv:2107.14000 (2021)
Selitskaya, N., Sielicki, S., Christou, N.: Challenges in real-life face recognition with heavy makeup and occlusions using deep learning algorithms. In: Nicosia, G., et al. (eds.) LOD 2020. LNCS, vol. 12566, pp. 600–611. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-64580-9_49
Selitskiy, S., Christou, N., Selitskaya, N.: Isolating Uncertainty of the Face Expression Recognition with the Meta-Learning Supervisor Neural Network, pp. 104–112. Association for Computing Machinery, New York, NY, USA (2021). https://doi.org/10.1145/3480433.3480447
Selitskiy, S., Christou, N., Selitskaya, N.: Using statistical and artificial neural networks meta-learning approaches for uncertainty isolation in face recognition by the established convolutional models. In: Nicosia, G., et al. (eds.) Mach. Learn. Optim. Data Sci., pp. 338–352. Springer International Publishing, Cham (2022). https://doi.org/10.1145/3480433.3480447
Thrun, S.: Is learning the n-th thing any easier than learning the first? In: Advances in Neural Information Processing Systems 8 (1995)
Thrun, S., Mitchell, T.M.: Lifelong robot learning. Robot. Auton. Syst. 15(1–2), 25–46 (1995)
Thrun S., P.L.: Learning To Learn. Springer, Boston, MA (1998). https://doi.org/10.1007/978-1-4615-5529-2
Turing, A.M.: I.-computing machinery and intelligence. Mind LIX(236), 433–460 (1950). https://doi.org/10.1093/mind/LIX.236.433
Vanschoren, J.: Meta-learning: a survey. ArXiv abs/1810.03548 (2018)
Williams, D.S., Gadd, M., De Martini, D., Newman, P.: Fool me once: robust selective segmentation via out-of-distribution detection with contrastive learning. In: 2021 IEEE International Conference on Robotics and Automation (ICRA), pp. 9536–9542. IEEE (2021)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2023 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Selitskiy, S. (2023). Elements of Active Continuous Learning and Uncertainty Self-awareness: A Narrow Implementation for Face and Facial Expression Recognition. In: Goertzel, B., Iklé, M., Potapov, A., Ponomaryov, D. (eds) Artificial General Intelligence. AGI 2022. Lecture Notes in Computer Science(), vol 13539. Springer, Cham. https://doi.org/10.1007/978-3-031-19907-3_38
Download citation
DOI: https://doi.org/10.1007/978-3-031-19907-3_38
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-19906-6
Online ISBN: 978-3-031-19907-3
eBook Packages: Computer ScienceComputer Science (R0)