Brain-like hierarchical data representation model - hierarchical multi-layer NMF = 뇌 인지 과정을 모방한 계층적 정보 처리 모델 - 계층적 다단계 비음수행렬분해법

Cited 0 time in webofscience Cited 0 time in scopus
  • Hit : 527
  • Download : 0
How to train a machine well so that it can develop intelligence like human has been a big issue of arti-ficial intelligence industry. Recently, deep learning has been a hot topic in this field. It is proven by several researches that deep learning, which resembles hierarchical data processing mechanism of our brain, actually does help learning process and improves the performance. In this thesis, we introduce another type of deep learning network, hierarchical multi-layer NMF, where each unit consists of non-negative matrix factorization algorithm, NMF; we extend single unit of learning algorithm NMF into multi-layered structure. With our pro-posed network, we aim to achieve two goals. One is to mimic and model how our brain processes information and represent data in hierarchical manner. The other is to observe the behavior of our multi-layered hierar-chical network and analyze its characteristics compared to shallow structure. Our demonstration shows that proposed multi-layered structure successfully models hierarchical learning mechanism; in the lower layer, very simple and sparse features are extracted at first, and as it proceeds to upper layer, the features develop into complex features by making combinations of simple features. By observing the hierarchical feature ex-traction process of our proposed algorithm, we are able to understand the underlying structure of complex data; we can understand the basic building blocks and how they come together in stages to finally represent data characteristics. With the analysis on image and document data sets, experimental results show that our brain-like information processing model has some strong points in reconstruction and classification tasks compared to single layered structure. Furthermore, our proposed multi-layer network seems to display charac-teristics different from that of shallow architecture in aspect of distribution of data representation. Our pro-posed multi-layer network is expected to demonstra...
Advisors
Lee, Soo-Youngresearcher이수영
Description
한국과학기술원 : 전기및전자공학과,
Publisher
한국과학기술원
Issue Date
2013
Identifier
513381/325007  / 020113710
Language
eng
Description

학위논문(석사) - 한국과학기술원 : 전기및전자공학과, 2013.2, [ vi, 92 p. ]

Keywords

Hierarchical feature extraction; non-negative matrix factorization; multi-layer; deep learning; 계층적 특징 추출; 비음수행렬분해법; 다단계; 깊은 학습; 자율 학습; unsupervised learning

URI
http://hdl.handle.net/10203/180967
Link
http://library.kaist.ac.kr/search/detail/view.do?bibCtrlNo=513381&flag=dissertation
Appears in Collection
EE-Theses_Master(석사논문)
Files in This Item
There are no files associated with this item.

qr_code

  • mendeley

    citeulike


rss_1.0 rss_2.0 atom_1.0