Open Access Journal

ISSN : 2394-2320 (Online)

International Journal of Engineering Research in Computer Science and Engineering (IJERCSE)

Monthly Journal for Computer Science and Engineering

Open Access Journal

International Journal of Engineering Research in Computer Science and Engineering (IJERCSE)

Monthly Journal for Computer Science and Engineering

ISSN : 2394-2320 (Online)

Call For Paper : Vol 11, Issue 03, March 2024

Call for Paper

Vol 11, Issue 03, March 2024

Indexing

Meta Learning challenges and Benefits

Author : Jayashree M Kudari 1 Sugda Hembram 2

PDF

Date of Publication :1st June 2021

Abstract: Learning as a process is very important aspect of growth in nature. Meta-learning in machine learning refers to learning algorithms that learn from other learning algorithms [7]. Meta-learning benefits all the machine learning systems from their repetitive application. But meta-learning differs a lot from the base-learning in the scope of the level of adaptation. It has its own benefits and challenges with gradual growth in its process towards evolution over the year. optimization-based formulation of meta-learning that learns to design an optimization algorithm automatically, which we call Learning to Optimize [8]. Understanding how it actually affects various sectors and making things simpler or difficult is a complex analysis of meta-learning in detail. This paper best bit is the challenges lying in front of us to reach such goal and benefits to use for research. Meta-learning is one of the most vibrant regions of research in the profound learning space. A few ways of thinking inside the Artificial Intelligence(AI) people group buy in to the postulation that meta-learning is one of the venturing stones towards opening Artificial General Intelligence(AGI) [14].

Reference :

    1. Mitchell, T. (1997). Machine Learning, McGraw Hill
    2. Xu, L. and Hutter, F. and Hoos, H. and LeytonBrown, K. (2008). Cross-Disciplinary Perspectives on Meta-Learning for Algorithm Selection. Journal of Artificial Intelligence Research, 32:565--606.
    3. Chelsea Finn, Pieter Abbel, Sergey: Proceedings of the 34th International Conference on Machin Learning
    4. https://research.aimultiple.com/meta-learning/
    5. https://towardsdatascience.com/meta-learninglearning-to-learn-a0365a6a44f0.
    6. David H. Wolpert. Stacked Generalization, Neural Networks, Vol. 5, pp. 241-259, Pergamon Press.
    7. What Is Meta-Learning in Machine Learning? by Jason Brownlee on December 18, 2020 in Ensemble Learning.
    8. Meta-Learning: Why It’s Hard and What We Can Do April 09, 2020, AFFILIATION, Member, School of Mathematics by Ke Li.
    9. Research Directions In Meta-Learning Ricardo Vilalta IBM T.J. Watson Research Center 30 Saw Mill River Rd., Hawthorne, NY., 10532 U.S.A. Youssef Drissi IBM T.J. Watson Research Center 30 Saw Mill River Rd., Hawthorne, NY., 10532 U.S.A. Proceedings of the International Conference on Artificial Intelligence, 2001.
    10. What is Meta Learning? Techniques, Benefits & Examples,( https://research.aimultiple.com/meta-learning/
    11. Doing more with less: meta-reasoning and metalearning in humans and machines, Thomas L Griffiths1, Frederick Callaway, Michael B, Chang, Erin. Grant, Paul M Krueger1 and Falk Lieder.
    12. Learning How to Learn: Meta Learning Approach to Improve Deep Learning, Dr. Ashish Kr. Chakraverti, Sugandha Chakraverti, Dr. Yashpal Singh, Paper ID: IJERTCONV8IS10001, Volume & Issue: ENCADEMS – 2020 (Volume 8 – Issue 10), Published (First Online): 18- 07-2020, ISSN (Online): 2278-0181.Publisher Name: IJERT
    13. Soares, C.: UCI++: Improved support for algorithm selection using datasetoids. In: T. Theeramunkong, B. Kijsirikul, N. Cercone, T.B. Ho (eds.) Advances in Knowledge Discovery and Data Mining, Lecture Notes in Computer Science, vol. 5476, pp. 499–506. Springer Berlin Heidelberg (2009)
    14. Learning How to Learn: Meta Learning Approach to Improve Deep Learning, International Journal of Engineering Research & Technology (IJERT) ISSN: 2278-0181 Published by, www.ijert.org ENCADEMS - 2020 Conference Proceedings
    15. Brazdil, P., Soares, C., de Costa, P.: Ranking learning algorithms: Using IBL and meta learning on accuracy and time results. Machine Learning 50(3), 251– 277 (2003).
    16. Prudencio, R.B., Ludermir, T.B.: Meta-learning approaches to selecting time series mod- els. Neurocomputing 61, 121–137 (2004).
    17. Meta-Learning in Neural Networks: A Survey Timothy Hospedales, Antreas Antoniou, Paul Micaelli, Amos Storkey.
    18. A. Krizhevsky, I. Sutskever, and G. E. Hinton, “Imagenet Classification With Deep Convolutional Neural Networks,” in NeurIPS, 2012.
    19. Vanschoren, J. 2018. Meta-learning: A survey. arXiv preprint arXiv:1810.03548.
    20. A Beginner’s Guide to Meta-Learning, Abacus.AI May 12, 2020. http://www.iaeng.org/IMECS2021/submission.html
    21. Meta-Learning with Implicit Gradients Aravind Rajeswaran, Chelsea Finn, Sham Kakade, Sergey Levine Submitted on 10 Sep 2019].
    22. Pavel Brazdil, LIAAD-INESC Porto L.A./Faculdade de Economia, University of Porto, Portugal Ricardo Vilalta, Department of computer Science, University of Houston, USA Christophe Giraud-Carrier, Department of Computer Science, Brigham Young University, USA.
    23. Brazdil P., Giraud-Carrier, C., Soares, C. and Vilalta, R. (2009). Metalearning – Applications to Data Mining, Springer.
    24. Metalearning: a survey of trends and technologies Christiane Lemke, Marcin Budka & Bogdan Gabrys
    25. Brazdil P, Soares C, de Costa P (2003) Ranking learning algorithms: using IBL and meta-learning on accuracy and time results. Mach Learn 50(3):251–277.
    26. Prudencio RB, Ludermir TB (2004a) Meta-learning approaches to selecting time series models. Neurocomputing 61:121–137

Recent Article