Skip to main content
SpringerLink
Log in

Vision System for AGI: Problems and Directions

  • Conference paper
  • First Online:
Artificial General Intelligence (AGI 2018)

Part of the book series: Lecture Notes in Computer Science ((LNAI,volume 10999))

Included in the following conference series:

Abstract

What frameworks and architectures are necessary to create a vision system for AGI? In this paper, we propose a formal model that states the task of perception within AGI. We show the role of discriminative and generative models in achieving efficient and general solution of this task, thus specifying the task in more detail. We discuss some existing generative and discriminative models and demonstrate their insufficiency for our purposes. Finally, we discuss some architectural dilemmas and open questions.

This is a preview of subscription content, log in via an institution to check access.

Access this chapter

Log in via an institution
Chapter
USD 29.95
Price excludes VAT (USA)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever
eBook
USD 49.99
Price excludes VAT (USA)
  • Available as EPUB and PDF
  • Read on any device
  • Instant download
  • Own it forever
Softcover Book
USD 64.99
Price excludes VAT (USA)
  • Compact, lightweight edition
  • Dispatched in 3 to 5 business days
  • Free shipping worldwide - see info

Tax calculation will be finalised at checkout

Purchases are for personal use only

Institutional subscriptions

References

  1. Hutter, M.: Universal Artificial Intelligence: Sequential Decisions Based on Algorithmic Probability. Springer, Heidelberg (2005). https://doi.org/10.1007/b138233

    Book  MATH  Google Scholar 

  2. Veness, J., et al.: A Monte Carlo AIXI Approximation. arXiv:0909.0801 [cs.AI] (2010)

  3. Solomonoff, R.: A formal theory of inductive inference, part 1 and part 2. In: Information and Control, vol. 7, pp. 1–22, 224–254 (1964)

    Google Scholar 

  4. Lake, B.M., et al.: Building Machines That Learn and Think Like People. arXiv:1604.00289 [cs.AI] (2016)

  5. Potapov, A., Rodionov, S.: Making universal induction efficient by specialization. In: Goertzel, B., Orseau, L., Snaider, J. (eds.) AGI 2014. LNCS (LNAI), vol. 8598, pp. 133–142. Springer, Cham (2014). https://doi.org/10.1007/978-3-319-09274-4_13

    Chapter  Google Scholar 

  6. Grossberg, S.: Adaptive pattern classification and universal recoding (I, II). Parallel development and coding of neural feature detectors. Biol. Cybernet. 23, 121–134, 187–202 (1976)

    Google Scholar 

  7. Parisotto, E., et al.: Global Pose Estimation with an Attention-based Recurrent Network. arXiv:1802.06857 [cs.CV] (2018)

  8. Liao, Q., Poggio, T.A.: Object-Oriented Deep Learning. CBMM Memo, No. 070 (2017)

    Google Scholar 

  9. Graves, A., Wayne, G., Danihelka, I.: Neural Turing Machines. arXiv:1410.5401 [cs.NE] (2014)

  10. Sabour, S., Frosst, N., Hinton, G.E.: Dynamic Routing Between Capsules. arXiv:1710.09829 [cs.CV] (2017)

  11. Hinton, G.E., Sabour, S., Frosst, N.: Matrix capsules with EM routing. In: ICLR Conference (2018)

    Google Scholar 

  12. Ha, D., Schmidhuber, J.: World Models. arXiv:1803.10122 [cs.LG] (2018)

Download references

Author information

Authors and Affiliations

  1. SingularityNET Foundation, Amsterdam, The Netherlands

    Alexey Potapov, Sergey Rodionov, Maxim Peterson, Oleg Scherbakov, Innokentii Zhdanov & Nikolai Skorobogatko

  2. ITMO University, St. Petersburg, Russia

    Alexey Potapov, Maxim Peterson, Oleg Scherbakov & Innokentii Zhdanov

  3. Novamente LLC, Rockville, USA

    Sergey Rodionov & Nikolai Skorobogatko

Authors
  1. Alexey Potapov
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Sergey Rodionov
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Maxim Peterson
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Oleg Scherbakov
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. Innokentii Zhdanov
    View author publications

    You can also search for this author in PubMed Google Scholar

  6. Nikolai Skorobogatko
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Alexey Potapov .

Editor information

Editors and Affiliations

  1. Adams State University, Alamosa, Colorado, USA

    Matthew Iklé

  2. Odessa Competence Center for Artificial Intelligence (OCCAM), Odessa, Ukraine

    Arthur Franz

  3. Hokkaido University, Sapporo, Japan

    Rafal Rzepka

  4. SingularityNET; OpenCog; Hanson Robotics, Hong Kong, China

    Ben Goertzel

Rights and permissions

Reprints and permissions

Copyright information

© 2018 Springer Nature Switzerland AG

About this paper

Check for updates. Verify currency and authenticity via CrossMark

Cite this paper

Potapov, A., Rodionov, S., Peterson, M., Scherbakov, O., Zhdanov, I., Skorobogatko, N. (2018). Vision System for AGI: Problems and Directions. In: Iklé, M., Franz, A., Rzepka, R., Goertzel, B. (eds) Artificial General Intelligence. AGI 2018. Lecture Notes in Computer Science(), vol 10999. Springer, Cham. https://doi.org/10.1007/978-3-319-97676-1_18

Download citation

  • DOI: https://doi.org/10.1007/978-3-319-97676-1_18

  • Published:

  • Publisher Name: Springer, Cham

  • Print ISBN: 978-3-319-97675-4

  • Online ISBN: 978-3-319-97676-1

  • eBook Packages: Computer ScienceComputer Science (R0)

Publish with us

Policies and ethics

Search

Navigation