딥러닝과 강화학습의 연구 동향 분석
Analysis of trends in deep learning and reinforcement learning
0
조회
0
다운로드
1
인용
0
참고문헌
키워드
초록
본 논문에서는 딥러닝 및 강화학습 연구에 대해 KeyBERT(Keyword extraction with Bidirectional Encoder Representations of Transformers) 알고리즘 기반의 토픽 추출 및 토픽 출현 빈도 분석으로 급변하는 딥러닝 관련 연구 동향 분석을 파악하고자 한다. 딥러닝 알고리즘과 강화학습에 대한 논문초록을 크롤링하여 전반기와 후반기로 나누고, 전처리를 진행한 후 KeyBERT를 사용해 토픽을 추출한다. 그 후 토픽 출현 빈도로 동향 변화에 대해 분석한다. 분석된 알고리즘 모두 전반기와 후반기에 대한 뚜렷한 동향 변화가 나타났으며, 전반기에 비해 후반기에 들어 어느 주제에 대한 연구가활발한지 확인할 수 있었다. 이는 KeyBERT를 활용한 토픽 추출 후 출현 빈도 분석으로 연구 동향변화 분석이 가능함을 보였으며, 타 분야의 연구 동향 분석에도 활용 가능할 것으로 예상한다. 또한 딥러닝의 동향을 제공함으로써 향후 딥러닝의 발전 방향에 대한 통찰력을 제공하며, 최근 주목받는 연구 주제를 알 수 있게 하여 연구 주제 및 방법 선정에 직접적인 도움을 준다.
Abstract
In this paper, we apply KeyBERT(Keyword extraction with Bidirectional Encoder Representations of Transformers) algorithm-driven topic extraction and topic frequency analysis to deep learning and reinforcement learning research to discover the rapidly changing trends in them. First, we crawled abstracts of research papers on deep learning and reinforcement learning, and temporally divided them into two groups. After pre-processing the crawled data, we extracted topics using KeyBERT algorithm, and then analyzed the extracted topics in terms of topic occurrence frequency. This analysis reveals that there are distinct trends in research work of all analyzed algorithms and applications, and we can clearly tell which topics are gaining more interest. The analysis also proves the effectiveness of the utilized topic extraction and topic frequency analysis in research trend analysis, and this trend analysis scheme is expected to be used for research trend analysis in other research fields. In addition, the analysis can provide insight into how deep learning will evolve in the near future, and provide guidance for select research topics and methodologies by informing researchers of research topics and methodologies which are recently attracting attention.
참고문헌 (39)
- B. Park, "GAN Based Image Generation Model Analysis", The Korean Institute of Electrical Engineers Conference Proceedings, pp.1884~1885 (2020)
- H. Lee, "Deep Learning Algorithm for Attention and Selective Noise Reduction Technology", Korean Society for Noise and Vibration Engineering(KSNVE) Conference Proceedings, pp.258~258 (2018)
- 박순욱, "재난문자 분류를 위한 딥러닝 모델", 한국컴퓨터정보학회논문지, 26(12), pp.1~9 (2021), 한국컴퓨터정보학회[DOI]
- 김영준, "자율주행 환경에서 딥러닝 기법의 객체검출과 속도 성능 최적화", 한국통신학회논문지, 45(4), pp.722~729 (2020), 한국통신학회[DOI]
- D. Silver, "Mastering the game of go without human knowledge", nature, 550(7676), pp.354~359 (2017)
- A. Ramesh, "Zero-shot text-to-image generation", Proceedings of the 38th International Conference on Machine Learning. PMLR, 139, pp.8821~8831 (2021)
- "Introducing ChatGPT"[URL]
- E. Holliman, "SWITCHBOARD:telephone speech corpus for research and development", Acoustics, Speech, and Signal Processing, IEEE International Conference on, pp.517~520 (1992)
- J. Deng, "ImageNet: A large-scale hierarchical image database", 2009 IEEE Conference on Computer Vision and Pattern Recognition, pp.248~255 (2009)
- "RISS SAM Academic Relations - Analysis Service Research Trend Analysis"[URL]
- H. Kim, "Deep learning research trend analysis using topic modeling and social network", The Korean Operations Research and Management Science Society Conference Proceedings, pp.1877~1899 (2016)
- 박홍진, "‘인공지능’, ‘기계학습’, ‘딥 러닝’ 분야의 국내 논문 동향 분석", 한국정보전자통신기술학회 논문지, 13(4), pp.283~292 (2020), 한국정보전자통신기술학회
- 이지영, "Deep Learning Research Trend Analysis using Text Mining", The International Journal of Advanced Culture Technology, 7(4), pp.295~301 (2019), 국제문화기술진흥원
- 김창식, "머신러닝 및 딥러닝 연구동향 분석: 토픽모델링을 중심으로", (사)디지털산업정보학회 논문지, 15(2), pp.19~28 (2019), (사)디지털산업정보학회
- D. Blei, "Latent dirichlet allocation", the Journal of machine Learning research, 3, pp.993~1022 (2003)
- D. Sharma, "Trend Analysis in Machine Learning Research Using Text Mining", 2018 International Conference on Advances in Computing, Communication Control and Networking (ICACCCN), pp.136~141 (2018)
- 이재윤, "자기 인용 네트워크와 인용 정체성을 이용한 연구자의 연구 이력 분석에 관한 연구", 정보관리학회지, 29(1), pp.157~174 (2012), 한국정보관리학회[DOI]
- 이재윤, "자아 중심 주제 인용분석을 활용한 딥러닝 연구동향 분석", 정보관리학회지, 34(4), pp.7~32 (2017), 한국정보관리학회[DOI]
- William Grant Hatcher, "A Survey of Deep Learning: Platforms, Applications and Emerging Research Trends", IEEE Access, 6, pp.24411~24432 (2018), Institute of Electrical and Electronics Engineers (IEEE)[DOI]
- Kaylani Bochie, "A survey on deep learning for challenged networks: Applications and trends", Journal of Network and Computer Applications, 194, pp.103213~ (2021), Elsevier BV[DOI]
- Surjeet Balhara, "A survey on deep reinforcement learning architectures, applications and emerging trends", IET Communications (2022), Institution of Engineering and Technology (IET)[DOI]
- A. Vaswani, "Attention is all you need", Advances in neural information processing systems 30, ~ (2017)
- Kenton, "Bert : Pre-training of deep bidirectional transformers for language understanding", Proceedings of NAACL-HLT, pp.2~ (2019)
- N. Reimers, "Sentence-bert: Sentence embeddings using siamese bert-networks", Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP) (2019)
- "keyBERT: Minimal keyword extraction with BERT"[URL]
- Ricardo Campos, "YAKE! Keyword extraction from single documents using multiple local features", Information Sciences, 509, pp.257~289 (2020), Elsevier BV[DOI]
- S. Rose, "Text mining:applications and theory", pp.1~20 (2010), John Wiley & Sons, Ltd
- R. Mihalcea, "Textrank: Bringing order into text", Proceedings of the 2004 conference on empirical methods in natural language processing, pp.404~411 (2004)
- M. Q. Khan, "Impact analysis of keyword extraction using contextual word embedding", PeerJ Computer Science, 8 (2022)
- "Auto-encoding variational bayes"[URL]
- J. Park, "BAM: Bottleneck Attention Module" (2018), British Machine Vision Conference (BMVC)
- S. Woo, "Cbam: Convolutional block attention module", Proceedings of the European conference on computer vision (ECCV), pp.3~19 (2018)
- S. Akcay, "GANomaly: Semi-supervised Anomaly Detection via Adversarial Training", Computer Vision–ACCV 2018: 14th Asian Conference on Computer Vision, pp.622~637 (2018)
- T. Schlegl, "Unsupervised anomaly detection with generative adversarial networks to guide marker discovery", Information processing in medical imaging, pp.146~157 (2017)
- 황철현, "미세먼지 예측 성능 개선을 위한 CNN-LSTM 결합 방법", 한국정보통신학회논문지, 24(1), pp.57~64 (2020), 한국정보통신학회[DOI]
- 이선민, "LSTM과 GRU 딥러닝 IoT 파워미터 기반의 단기 전력사용량 예측", 한국인터넷방송통신학회 논문지, 19(5), pp.79~85 (2019), 한국인터넷방송통신학회[DOI]
- "Proximal policy optimization algorithms"[URL]