skip to main content
10.1145/3512826.3512827acmotherconferencesArticle/Chapter ViewAbstractPublication PagesaieeConference Proceedingsconference-collections
research-article

An Algorithmic Theory for Conscious Learning

Published: 15 April 2022 Publication History

Abstract

The new conscious learning mode here is end-to-end (3D-to-2D-to-3D) and free from annotations of 2D images and 2D motor images, such as a bounding box for a patch to be attended to. The algorithm directly takes that of the Developmental Networks that has been previously published extensively with rich experimental results. This paper fills the huge gap between 3D world, to 2D sensory images and 2D motor images, back to 3D world so the conscious learning is end-to-end without a need for motor-impositions. This new conscious learning methodology is a major departure from traditional AI—handcrafting symbolic labels that tend to be brittle (e.g., for driverless cars) and then “spoon-feeding” pre-collected “big data”. The analysis here establishes that autonomous imitations as presented are a general mechanism in learning universal Turing machines. Autonomous imitations drastically reduce the teaching complexity compared to pre-collected “big data”, especially because no annotations of training data are needed. This learning mode is technically supported by a new kind of neural networks called Developmental Network-2 (DN-2) as an algorithmic basis, due to its incremental, non-iterative, on-the-fly learning mode along with the optimality (in the sense of maximum likelihood) in learning emergent super Turing machines from the open-ended real physical world. This work is directly related to electronics engineering because it requires large-scale on-the-fly brainoid chips in conscious learning robots.

References

[1]
M. Cole and S. R. Cole. 1996. The Development of Children(3rd ed.). Freeman, New York.
[2]
M. B. Feller, D. P. Wellis, D. Stellwagen, F. S. Werblin, and C. J. Shatz. 1996. Requirement for cholinergic synaptic transmission in the propagation of spontaneous retinal waves. Science 272, 5265 (1996), 1182–1187.
[3]
K. Fukushima, S. Miyake, and T. Ito. 1983. Neocognitron: A neural network model for a mechanism of visual pattern recognition. IEEE Trans. Systems, Man and Cybernetics 13, 5 (1983), 826–834.
[4]
A. Graves, G. Wayne, and I. Danihelka. 2014. Neural Turing Machines. Technical Report arXiv:1410.5401. Google DeepMind, London, UK.
[5]
A. Graves, G. Wayne, M. Reynolds, T. Harley, I. Danihelka, A. Grabska-Barwinska, S. G. Colmenarejo, E. Grefenstette, T. Ramalho, J. Agapiou, A. P. Badia, K. M. Hermann, Y. Zwols, G. Ostrovski, A. C., H. King, C. Summerfield, P. Blunsom, K. Kavukcuoglu, and D. Hassabis. 2016. Hybrid computing using a neural network with dynamic external memory. Nature 538(2016), 471–476.
[6]
E. H. Hess. 1973. Imprinting: Early Experience and the Developmental Psychobiology of Attachment. Van Nostrand Reinhold Company, New York.
[7]
S. Hochreiter and J. Schmidhuber. 1997. Long Short-Term Memory. Neural Computation 9, 8 (1997), 1735–1780.
[8]
J. E. Hopcroft, R. Motwani, and J. D. Ullman. 2006. Introduction to Automata Theory, Languages, and Computation. Addison-Wesley, Boston, MA.
[9]
A. Hussein, M. M. Gaber, E. Elyan, and C. Jayne. 2017. Imitation Learning: A Survey of Learning Methods. Comput. Surveys 50 (June 2017), 1–35.
[10]
A. Krizhevsky, I. Sutskever, and G. E. Hinton. 2012. ImageNet classification with deep convolutional neural networks. In Advances in Neural Information Processing Systems, Vol. 25. 1106–1114.
[11]
Y. LeCun, L. Bengio, and G. Hinton. 2015. Deep Learning. Nature 521(2015), 436–444.
[12]
Y. LeCun, L. Bottou, Y. Bengio, and P. Haffner. 1998. Gradient-Based Learning Applied to Document Recognition. Proceedings of IEEE 86, 11 (1998), 2278–2324.
[13]
J. C. Martin. 2003. Introduction to Languages and the Theory of Computation (3rd ed.). McGraw Hill, Boston, MA.
[14]
A. N. Meltzoff and M. K. Moore. 1977. Imitation of Facial and Manual Gestures by Human Neonates. Science 198, 4312 (Oct. 7 1977), 74–78.
[15]
J. Moran and R. Desimone. 1985. Selective attention gates visual processing in the extrastrate cortex. Science 229, 4715 (1985), 782–784.
[16]
B. A. Olshausen, C. H. Anderson, and D. C. Van Essen. 1993. A neurobiological model of visual attention and invariant pattern recognition based on dynamic routing of information. Journal of Neuroscience 13, 11 (1993), 4700–4719.
[17]
S. Pinker. 1994. The Language Instinct: How the Mind Creates Language. William Morrow, New York.
[18]
O. Russakovsky, J. Deng, H. Su, J. Krause, S. Satheesh, S. Ma, Z. Huang, A. Karpathy, A. Khosla, M. Bernstein, A. C. Berg, and L. Fei-Fei. 2015. ImageNet Large Scale Visual Recognition Challenge. International Journal of Computer Vision 115 (2015), 211–252.
[19]
T. Serre, L. Wolf, S. Bileschi, M. Riesenhuber, and T. Poggio. 2007. Robust object recognition with cortex-like mechanisms. IEEE Trans. Pattern Analysis and Machine Intelligence 29, 3(2007), 411–426.
[20]
M. Tomasello. 1988. The role of joint attentional processes in early language development. Language Sciences 10(1988), 69–88.
[21]
M. Tomasello. 2003. Constructing a Language: A Usage-Based Theory of Language Acquisition. Harvard University Press, Cambridge, MA.
[22]
A. M. Turing. 1936. On computable numbers with an application to the Entscheidungsproblem. Proc. London Math. Soc., 2nd series 42 (1936), 230–265. A correction, ibid., 43, 544-546.
[23]
J. Weng. 2015. Brain as an Emergent Finite Automaton: A Theory and Three Theorems. International Journal of Intelligence Science 5, 2 (2015), 112–131.
[24]
J. Weng. 2020. Autonomous Programming for General Purposes: Theory. International Journal of Huamnoid Robotics 17, 4 (August 2020), 1–36.
[25]
J. Weng. 2020. Conscious Intelligence Requires Developmental Autonomous Programming For General Purposes. In Proc. IEEE Int. Conf. on Dev. Learning and Epigenetic Robotics. Valparaiso, Chile, 1–7.
[26]
J. Weng. 2021. On Post Selections Using Test Sets (PSUTS) in AI. In Proc. International Joint Conference on Neural Networks. Shengzhen, China, 1–8.
[27]
J. Weng, N. Ahuja, and T. S. Huang. 1997. Learning recognition and segmentation using the Cresceptron. International Journal of Computer Vision 25, 2 (Nov. 1997), 109–143.
[28]
J. Weng and M. Luciw. 2009. Dually Optimal Neuronal Layers: Lobe Component Analysis. IEEE Trans. Autonomous Mental Development 1, 1 (2009), 68–85.
[29]
J. Weng, J. McClelland, A. Pentland, O. Sporns, I. Stockman, M. Sur, and E. Thelen. 2001. Autonomous Mental Development by Robots and Animals. Science 291, 5504 (2001), 599–600.
[30]
J. Weng, Z. Zheng, and X. Wu. 2019. Developmental Network Two, Its Optimality, and Emergent Turing Machines. U.S. Patent Application Number: 16265212. Approval pending.
[31]
J. Weng, Z. Zheng, X. Wu, J. Castro-Garcia, S. Zhu, Q. Guo, and X. Wu. 2018. Emergent Turing Machines and Operating Systems for Brain-Like Auto-Programming for General Purposes. In Proc. AAAI 2018 Fall Symposium: Gathering for AI and Natural Systems. Arlington, Virginia, 1–7.
[32]
P. J. Werbos. 1994. The Roots of Backpropagation: From Ordered Derivatives to Neural Networks and Political Forecasting. Wiley, Chichester.
[33]
X. Wu and J. Weng. 2019. Neuron-wise inhibition zones and auditory experiments. IEEE Transactions on Industrial Electronics 66, 12 (2019), 9581–9590.
[34]
X. Wu and J. Weng. 2020. Muscle Vectors as Temporally “Dense Labels”. In Proc. International Joint Conference on Neural Networks. Glasgow, UK, 1–8.
[35]
X. Wu and J. Weng. 2021. On Machine Thinking. In Proc. International Joint Conf. Neural Networks. IEEE Press, Shenzhen, China, 1–8.

Cited By

View all
  • (2024)Perspective Chapter: Deep Learning Misconduct and How Conscious Learning Avoids ItDeep Learning - Recent Findings and Research10.5772/intechopen.113359Online publication date: 29-May-2024
  • (2024)Conscious Learning without Post-Selection MisconductInternational Journal of Humanoid Robotics10.1142/S021984362350031721:01Online publication date: 19-Feb-2024
  • (2024)On Skull-Closed Machine Thinking Based on Emergent Turing MachinesIEEE Transactions on Artificial Intelligence10.1109/TAI.2023.33373225:6(3057-3071)Online publication date: Jun-2024
  • Show More Cited By

Recommendations

Comments

Information & Contributors

Information

Published In

cover image ACM Other conferences
AIEE '22: Proceedings of the 2022 3rd International Conference on Artificial Intelligence in Electronics Engineering
January 2022
149 pages
ISBN:9781450395489
DOI:10.1145/3512826
Permission to make digital or hard copies of all or part of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. Copyrights for components of this work owned by others than the author(s) must be honored. Abstracting with credit is permitted. To copy otherwise, or republish, to post on servers or to redistribute to lists, requires prior specific permission and/or a fee. Request permissions from [email protected].

Publisher

Association for Computing Machinery

New York, NY, United States

Publication History

Published: 15 April 2022

Permissions

Request permissions for this article.

Check for updates

Author Tags

  1. conscious machines
  2. imitation
  3. inverse kinematics
  4. neural networks
  5. sensorimotor learning
  6. universal Turing machines

Qualifiers

  • Research-article
  • Research
  • Refereed limited

Conference

AIEE 2022

Contributors

Other Metrics

Bibliometrics & Citations

Bibliometrics

Article Metrics

  • Downloads (Last 12 months)11
  • Downloads (Last 6 weeks)0
Reflects downloads up to 16 Feb 2025

Other Metrics

Citations

Cited By

View all
  • (2024)Perspective Chapter: Deep Learning Misconduct and How Conscious Learning Avoids ItDeep Learning - Recent Findings and Research10.5772/intechopen.113359Online publication date: 29-May-2024
  • (2024)Conscious Learning without Post-Selection MisconductInternational Journal of Humanoid Robotics10.1142/S021984362350031721:01Online publication date: 19-Feb-2024
  • (2024)On Skull-Closed Machine Thinking Based on Emergent Turing MachinesIEEE Transactions on Artificial Intelligence10.1109/TAI.2023.33373225:6(3057-3071)Online publication date: Jun-2024
  • (2024)Misconduct in Post-Selections and Deep Learning2023 8th International Conference on Control, Robotics and Cybernetics (CRC)10.1109/CRC60659.2023.10488526(235-243)Online publication date: 22-Dec-2024
  • (2024)On Necessity of Conscious Learning: From Robots to HumansAdvances in Automation, Mechanical and Design Engineering10.1007/978-3-031-62664-7_4(33-55)Online publication date: 19-Jun-2024
  • (2023)Do You Mind? User Perceptions of Machine ConsciousnessProceedings of the 2023 CHI Conference on Human Factors in Computing Systems10.1145/3544548.3581296(1-19)Online publication date: 19-Apr-2023
  • (2023)A Protocol for Testing Conscious Learning Robots2023 International Joint Conference on Neural Networks (IJCNN)10.1109/IJCNN54540.2023.10191945(1-9)Online publication date: 18-Jun-2023
  • (2022)20 Million-Dollar Problems for Any Brain Models and a Holistic Solution: Conscious Learning2022 International Joint Conference on Neural Networks (IJCNN)10.1109/IJCNN55064.2022.9892445(1-9)Online publication date: 18-Jul-2022

View Options

Login options

View options

PDF

View or Download as a PDF file.

PDF

eReader

View online with eReader.

eReader

HTML Format

View this article in HTML Format.

HTML Format

Figures

Tables

Media

Share

Share

Share this Publication link

Share on social media