Electronics and Telecommunications Trends (전자통신동향분석)

Electronics and Telecommunications Research Institute (한국전자통신연구원)
권호 표지
DOI QR코드

DOI QR Code

Self-Improving Artificial Intelligence Technology

자율성장 인공지능 기술

  • Published : 2019.08.01
Download PDF
⟨ Previous Next ⟩

Abstract

Currently, a majority of artificial intelligence is used to secure big data; however, it is concentrated in a few of major companies. Therefore, automatic data augmentation and efficient learning algorithms for small-scale data will become key elements in future artificial intelligence competitiveness. In addition, it is necessary to develop a technique to learn meanings, correlations, and time-related associations of complex modal knowledge similar to that in humans and expand and transfer semantic prediction/knowledge inference about unknown data. To this end, a neural memory model, which imitates how knowledge in the human brain is processed, needs to be developed to enable knowledge expansion through modality cooperative learning. Moreover, declarative and procedural knowledge in the memory model must also be self-developed through human interaction. In this paper, we reviewed this essential methodology and briefly described achievements that have been made so far.

Keywords

Acknowledgement

Grant : 자율성장형 AI 핵심원천기술 연구

Supported by : 한국전자통신연구원

References

  1. A. Graves et al., "Neural turing machines," arXiv preprint:1410.5401, 2014.
  2. S. Sukhbaatar et al., "End-to-end memory networks," in Proc. NIPS, 2015.
  3. A. Santoro et al., "A simple neural network module for relational reasoning," in Proc. NIPS, 2017.
  4. V. Mnih et al., "Asynchronous Methods for Deep Reinforcement Learning," in Proc. ICML, 2016.
  5. T. Mikolov et al., "Distributed representations of words and phrases and their compositionality," in Proc. NIPS, 2013.
  6. P. Bojanowski et al., "Enriching word vectors with subword information," in Proc. TACL, 2017.
  7. T. Kenter et al., "Siamese CBOW: optimizing word embeddings for sentence representations," in Proc. ACL, 2016.
  8. R. Kiros et al., "Skip-thought vectors," in Proc. NIPS, 2015.
  9. 정의석 외 3인, "한국어 음소열 기반 워드 임베딩 기술," 한국어정보학회 학술대회 논문집, 2017.
  10. S. Park et al., "Subword-level word vector representations for Korean," in Proc. ACL, 2018.
  11. R. S. Feris et al., "Visual Attributes," Springer International Publishing, 2017.
  12. A. Farhadi et al., "Describing Objects by their Attributes," in Proc. IEEE Conf. Comput. Vision Pattern Recogn., 2009, pp. 1778-1785.
  13. O. Russakovsky and F. Li, "Attribute learning in large-scale datasets," in Proc. Eur. Conf. Comput. Vision, 2010, pp. 1-14.
  14. Z. Liu, et al., "DeepFashion: Powering Robust Clothes Recognition and Retrieval with Rich Annotations," in Proc. IEEE Int. Conf. Comput. Vision Pattern Recogn., 2016, pp. 106-1104.
  15. T. Nagarajan and K. Grauman., "Attributes as Operators: Factorizing Unseen Attribute-Object Compositions," in Proc. Eur. Conf. Comput. Vision, 2018, pp. 169-185.
  16. N. Sarafianos et al., "Deep Imbalanced Attribute Classification using Visual Attention Aggregation," in Proc. Eur. Conf. Comput. Vision, 2018, pp. 708-725.
  17. J. Song et al., "Selective Zero-Shot Classification with Augmented Attributes," in Proc. Eur. Conf. Comput. Vision, 2018, pp. 474-490.
  18. K. E. Ak et al., "Learning Attribute Representations with Localization for Flexible Fashion Search," in Proc. IEEE Conf. Comput. Vision Pattern Recogn., 2018, pp. 7708-7717.
  19. E. Gabrilovich and N. Usunier, "Constructing and Mining Web-scale Knowledge Graphs," in Proc. SIGIR, Tutorial Slide, 2016
  20. S. Kumar, "A survey of deep learning methods for relation extraction," arXiv:1705.03645, 2017.
  21. X. Han et al., "FewRel: A Large-Scale Supervised Few-Shot Relation Classification Dataset with State-of-the-Art Evaluation," in Proc. EMNLP, 2018, pp. 4803-4809.
  22. X. Dong et al., "Knowledge vault: A web-scale approach to probabilistic knowledge fusion," in Proc. ACM SIGKDD Int. Conf. Knowledge Discovery Data Mining, 2014, pp. 601-610.
  23. J. Kim and S.H. Myaeng. "Discovering relations to augment a web-scale knowledge base constructed from the web," in Proc. Int. Conf. Web Intell., Mining Semantics, 2016, pp. 16;1-12.
  24. D.Q. Nguyen, "An overview of embedding models of entities and relationships for knowledge base completion," arXiv:1703.08098, 2017.
  25. Q. Wang et al., "Knowledge graph embedding: A survey of approaches and applications," IEEE Trans. Knowledge Data Eng., vol. 29, no. 12, 2017, pp. 2724-2743. https://doi.org/10.1109/TKDE.2017.2754499
  26. 최현영 등, "지식 베이스 임베딩을 활용한 지식 완성 모델링 기법," 한국정보과학회 논문지, 제45권 제9호, 2018.9, pp. 895-903.
  27. H. Al-Mubaid and S. Bettayeb, "An Algorithm for Combining Graphs Based on Shared Knowledge," in Proc. ISCA BICoB, 2012. pp. 137-142.
  28. Q. Xie et al., "An interpretable knowledge transfer model for knowledge base completion," arXiv preprint:1704.05908, 2017.
  29. G. Dihong and D. Z. Wang, "Extracting Visual Knowledge from the Web with Multimodal Learning," in Proc. IJCAI, 2017, pp. 1718-1724.
  30. P. Pouya, L. Chen, and S. Singh, "Embedding multimodal relational data for knowledge base completion," arXiv preprint:1809.01341, 2018.