In Generative AI : Zero-Shot and Few-Shot

Authors

  • Phani Monogya Katikireddi  Independent Researcher, India
  • Santosh Jaini  Independent Researcher, India

DOI:

https://doi.org/10.32628/CSEIT2390668

Keywords:

Generative AI, Zero-Shot Learning, Few-Shot Learning, Data Scarcity, Model Generalization, Transfer Learning, Meta-Learning, Advanced Architectures, Transformers, Real-Time Applications

Abstract

Generative AI has become a change-maker in many fields, using different text, image, and voice generation modes. One of the profound sub-areas within this domain is the optimum utilization of learning systems with minimal information using zero- and few-shot learning. Zero-shot learning lets models operate on novel classes or tasks for which it has no training sample, while few-shot learning allows models to learn with initial samples. Such approaches are useful when it is difficult or expensive to obtain information, which suggests a technique for providing a direction for developing accurate AI models when data are lacking. This paper explains the background, application, and challenges of generative AI models that use zero-shot/one-shot learning, outlining how these techniques help set new paradigms and raise innovative horizons for AI systems.

References

  1. Bartunov, S., & Vetrov, D. (2018, March). Few-shot generative modeling with generative matching networks. In International Conference on Artificial Intelligence and Statistics (pp. 670-678). PMLR. http://proceedings.mlr.press/v84/bartunov18a/bartunov18a.pdf
  2. Jangampeta, S., Mallreddy, S.R., & Padamati, J.R. (2021). Anomaly Detection for Data Security in SIEM: Identifying Malicious Activity in Security Logs and User Sessions. 10(12), 295-298
  3. Jangampeta, S., Mallreddy, S. R., & Padamati, J. R. (2021). Data Security: Safeguarding the Digital Lifeline in an Era of Growing Threats. International Journal for Innovative Engineering and Management Research, 10(4), 630-632.
  4. Sukender Reddy Mallreddy(2020).Cloud Data Security: Identifying Challenges and Implementing Solutions.JournalforEducators,TeachersandTrainers,Vol.11(1).96 -102.
  5. Vasa, Y. (2021). Robustness and adversarial attacks on generative models. International Journal for Research Publication and Seminar, 12(3), 462–471. https://doi.org/10.36676/jrps.v12.i3.1537
  6. Vasa, Y. (2021). Quantum Information Technologies in cybersecurity: Developing unbreakable encryption for continuous integration environments. International Journal for Research Publication and Seminar, 12(2), 482–490. https://doi.org/10.36676/jrps.v12.i2.1539
  7. Vasa, Y. (2021). Develop Explainable AI (XAI) Solutions For Data Engineers. NVEO - Natural Volatiles & Essential Oils, 8(3), 425–432. https://doi.org/https://doi.org/10.53555/nveo.v8i3.5769
  8. Singirikonda, P., Jaini, S., & Vasa, Y. (2021). Develop Solutions To Detect And Mitigate Data Quality Issues In ML Models. NVEO - Natural Volatiles & Essential Oils, 8(4), 16968–16973. https://doi.org/https://doi.org/10.53555/nveo.v8i4.5771
  9. Vasa, Y., Jaini, S., & Singirikonda, P. (2021). Design Scalable Data Pipelines For Ai Applications. NVEO - Natural Volatiles & Essential Oils, 8(1), 215–221. https://doi.org/https://doi.org/10.53555/nveo.v8i1.5772
  10. Katikireddi, P. M., Singirikonda, P., & Vasa, Y. (2021). Revolutionizing DEVOPS with Quantum Computing: Accelerating CI/CD pipelines through Advanced Computational Techniques. Innovative Research Thoughts, 7(2), 97–103. https://doi.org/10.36676/irt.v7.i2.1482
  11. Kilaru, N. B., Cheemakurthi, S. K. M., & Gunnam, V. (n.d.). Advanced Anomaly Detection In Banking: Detecting Emerging Threats Using Siem. International Journal of Computer Science and Mechatronics, 7(4), 28–33.
  12. Kilaru, N. B., Cheemakurthi, S. K. M., & Gunnam, V. (2021). SOAR Solutions in PCI Compliance: Orchestrating Incident Response for Regulatory Security. ESP Journal of Engineering & Technology Advancements, 1(2), 78–84. https://doi.org/10.56472/25832646/ESP-V1I2P111
  13. Gunnam, V., & Kilaru, N. B. (2021). Securing Pci Data: Cloud Security Best Practices And Innovations. NVEO-NATURAL VOLATILES & ESSENTIAL OILS Journal| NVEO.
  14. Kilaru, N. B., & Cheemakurthi, S. K. M. (2021). Techniques For Feature Engineering To Improve Ml Model Accuracy. NVEO-NATURAL VOLATILES & ESSENTIAL OILS Journal| NVEO, 194-200.
  15. Naresh Babu Kilaru. (2021). AUTOMATE DATA SCIENCE WORKFLOWS USING DATA ENGINEERING TECHNIQUES. International Journal for Research Publication and Seminar, 12(3), 521–530. https://doi.org/10.36676/jrps.v12.i3.1543
  16. Singirikonda, P., Katikireddi, P. M., & Jaini, S. (2021). Cybersecurity In Devops: Integrating Data Privacy And Ai-Powered Threat Detection For Continuous Delivery. NVEO - Natural Volatiles & Essential Oils, 8(2), 215–216. https://doi.org/https://doi.org/10.53555/nveo.v8i2.5770
  17. Katikireddi, P. M., Singirikonda, P., & Vasa, Y. (2021). Revolutionizing DEVOPS with Quantum Computing: Accelerating CI/CD pipelines through Advanced Computational Techniques. Innovative Research Thoughts, 7(2), 97–103. https://doi.org/10.36676/irt.v7.i2.1482

IInternational Journal of Scientific Research in Computer Science, Engineering and Information Technology

Downloads

Published

2022-01-25

Issue

Volume 8, Issue 1, January-February-2022

Section

Research Articles

License

Copyright (c) IJSRCSEIT

Creative Commons License

This work is licensed under a Creative Commons Attribution 4.0 International License.

How to Cite

[1]
Phani Monogya Katikireddi, Santosh Jaini, " In Generative AI : Zero-Shot and Few-Shot" International Journal of Scientific Research in Computer Science, Engineering and Information Technology(IJSRCSEIT), ISSN : 2456-3307, Volume 8, Issue 1, pp.391-397, January-February-2022. Available at doi : https://doi.org/10.32628/CSEIT2390668