• 제목/요약/키워드: Hierarchical Artificial Neural Networks

검색결과 11건 처리시간 0.027초

계층적 인공신경망을 이용한 구성을 갖춘 곡의 자동생성 (Automatic Generation of a Configured Song with Hierarchical Artificial Neural Networks)

  • 김경환;정성훈
    • 디지털콘텐츠학회 논문지
    • /
    • 제18권4호
    • /
    • pp.641-647
    • /
    • 2017
  • 본 논문에서는 자동작곡에서 계층적 인공신경망을 이용하여 전/중/후 별로 곡의 멜로디가 전개되는 구성을 갖춘 곡을 자동으로 생성하는 방법을 제안한다. 첫 번째 계층에서는 하나의 인공신경망을 사용하여 기존의 곡을 학습시키거나 혹은 무작위 멜로디를 학습시키고 박자후처리를 하여 곡을 출력한다. 두 번째 계층에서는 첫 번째 인공신경망이 만든 멜로디를 전/중/후별로 세 개의 인공신경망에 학습한 후 곡을 출력한다. 두 번째 계층의 세 개의 인공신경망에서는 반복을 만들기 위하여 전/중/후 별로 마디구분을 이용한 반복을 적용하며 이후 박자/화성/조성후처리를 수행하여 곡을 완성한다. 실험결과 구성을 갖춘 곡이 생성됨을 확인하였다.

Neural network-based generation of artificial spatially variable earthquakes ground motions

  • Ghaffarzadeh, Hossein;Izadi, Mohammad Mahdi;Talebian, Nima
    • Earthquakes and Structures
    • /
    • 제4권5호
    • /
    • pp.509-525
    • /
    • 2013
  • In this paper, learning capabilities of two types of Arterial Neural Networks, namely hierarchical neural networks and Generalized Regression Neural Network were used in a two-stage approach to develop a method for generating spatial varying accelerograms from acceleration response spectra and a distance parameter in which generated accelerogram is desired. Data collected from closely spaced arrays of seismographs in SMART-1 array were used to train neural networks. The generated accelerograms from the proposed method can be used for multiple support excitations analysis of structures that their supports undergo different motions during an earthquake.

Deep Structured Learning: Architectures and Applications

  • Lee, Soowook
    • International Journal of Advanced Culture Technology
    • /
    • 제6권4호
    • /
    • pp.262-265
    • /
    • 2018
  • Deep learning, a sub-field of machine learning changing the prospects of artificial intelligence (AI) because of its recent advancements and application in various field. Deep learning deals with algorithms inspired by the structure and function of the brain called artificial neural networks. This works reviews basic architecture and recent advancement of deep structured learning. It also describes contemporary applications of deep structured learning and its advantages over the treditional learning in artificial interlligence. This study is useful for the general readers and students who are in the early stage of deep learning studies.

Hierarchical neural network for damage detection using modal parameters

  • Chang, Minwoo;Kim, Jae Kwan;Lee, Joonhyeok
    • Structural Engineering and Mechanics
    • /
    • 제70권4호
    • /
    • pp.457-466
    • /
    • 2019
  • This study develops a damage detection method based on neural networks. The performance of the method is numerically and experimentally verified using a three-story shear building model. The framework is mainly composed of two hierarchical stages to identify damage location and extent using artificial neural network (ANN). The normalized damage signature index, that is a normalized ratio of the changes in the natural frequency and mode shape caused by the damage, is used to identify the damage location. The modal parameters extracted from the numerically developed structure for multiple damage scenarios are used to train the ANN. The positive alarm from the first stage of damage detection activates the second stage of ANN to assess the damage extent. The difference in mode shape vectors between the intact and damaged structures is used to determine the extent of the related damage. The entire procedure is verified using laboratory experiments. The damage is artificially modeled by replacing the column element with a narrow section, and a stochastic subspace identification method is used to identify the modal parameters. The results verify that the proposed method can accurately detect the damage location and extent.

Phrase-Chunk Level Hierarchical Attention Networks for Arabic Sentiment Analysis

  • Abdelmawgoud M. Meabed;Sherif Mahdy Abdou;Mervat Hassan Gheith
    • International Journal of Computer Science & Network Security
    • /
    • 제23권9호
    • /
    • pp.120-128
    • /
    • 2023
  • In this work, we have presented ATSA, a hierarchical attention deep learning model for Arabic sentiment analysis. ATSA was proposed by addressing several challenges and limitations that arise when applying the classical models to perform opinion mining in Arabic. Arabic-specific challenges including the morphological complexity and language sparsity were addressed by modeling semantic composition at the Arabic morphological analysis after performing tokenization. ATSA proposed to perform phrase-chunks sentiment embedding to provide a broader set of features that cover syntactic, semantic, and sentiment information. We used phrase structure parser to generate syntactic parse trees that are used as a reference for ATSA. This allowed modeling semantic and sentiment composition following the natural order in which words and phrase-chunks are combined in a sentence. The proposed model was evaluated on three Arabic corpora that correspond to different genres (newswire, online comments, and tweets) and different writing styles (MSA and dialectal Arabic). Experiments showed that each of the proposed contributions in ATSA was able to achieve significant improvement. The combination of all contributions, which makes up for the complete ATSA model, was able to improve the classification accuracy by 3% and 2% on Tweets and Hotel reviews datasets, respectively, compared to the existing models.

Input Noise Immunity of Multilayer Perceptrons

  • Lee, Young-Jik;Oh, Sang-Hoon
    • ETRI Journal
    • /
    • 제16권1호
    • /
    • pp.35-43
    • /
    • 1994
  • In this paper, the robustness of the artificial neural networks to noise is demonstrated with a multilayer perceptron, and the reason of robustness is due to the statistical orthogonality among hidden nodes and its hierarchical information extraction capability. Also, the misclassification probability of a well-trained multilayer perceptron is derived without any linear approximations when the inputs are contaminated with random noises. The misclassification probability for a noisy pattern is shown to be a function of the input pattern, noise variances, the weight matrices, and the nonlinear transformations. The result is verified with a handwritten digit recognition problem, which shows better result than that using linear approximations.

  • PDF

Predicting the Performance of Forecasting Strategies for Naval Spare Parts Demand: A Machine Learning Approach

  • Moon, Seongmin
    • Management Science and Financial Engineering
    • /
    • 제19권1호
    • /
    • pp.1-10
    • /
    • 2013
  • Hierarchical forecasting strategy does not always outperform direct forecasting strategy. The performance generally depends on demand features. This research guides the use of the alternative forecasting strategies according to demand features. This paper developed and evaluated various classification models such as logistic regression (LR), artificial neural networks (ANN), decision trees (DT), boosted trees (BT), and random forests (RF) for predicting the relative performance of the alternative forecasting strategies for the South Korean navy's spare parts demand which has non-normal characteristics. ANN minimized classification errors and inventory costs, whereas LR minimized the Brier scores and the sum of forecasting errors.

VS3-NET: Neural variational inference model for machine-reading comprehension

  • Park, Cheoneum;Lee, Changki;Song, Heejun
    • ETRI Journal
    • /
    • 제41권6호
    • /
    • pp.771-781
    • /
    • 2019
  • We propose the VS3-NET model to solve the task of question answering questions with machine-reading comprehension that searches for an appropriate answer in a given context. VS3-NET is a model that trains latent variables for each question using variational inferences based on a model of a simple recurrent unit-based sentences and self-matching networks. The types of questions vary, and the answers depend on the type of question. To perform efficient inference and learning, we introduce neural question-type models to approximate the prior and posterior distributions of the latent variables, and we use these approximated distributions to optimize a reparameterized variational lower bound. The context given in machine-reading comprehension usually comprises several sentences, leading to performance degradation caused by context length. Therefore, we model a hierarchical structure using sentence encoding, in which as the context becomes longer, the performance degrades. Experimental results show that the proposed VS3-NET model has an exact-match score of 76.8% and an F1 score of 84.5% on the SQuAD test set.

대용량 데이터 처리를 위한 하이브리드형 클러스터링 기법 (A Hybrid Clustering Technique for Processing Large Data)

  • 김만선;이상용
    • 정보처리학회논문지B
    • /
    • 제10B권1호
    • /
    • pp.33-40
    • /
    • 2003
  • 데이터 마이닝은 지식발견 과정에서 중요한 역할을 수행하며, 여러 데이터 마이닝의 알고리즘들은 특정의 목적을 위하여 선택될 수 있다. 대부분의 전통적인 계층적 클러스터링 방법은 적은 양의 데이터 집합을 처리하는데 적합하여 제한된 리소스와 부족한 효율성으로 인하여 대용량의 데이터 집합을 다루기가 곤란하다. 본 연구에서는 대용량의 데이터에 적용되어 알려지지 않은 패턴을 발견할 수 있는 하이브리드형 신경망 클러스터링 기법의 PPC(Pre-Post Clustrering) 기법을 제안한다. PPC 기법은 인공지능적 방법인 자기조직화지도(SOM)와 통계적 방법인 계층적 클러스터링을 결합하여 두 과정에서는 군집의 내부적 특징을 나타내는 응집거리와 군집간의 외부적 거리를 나타내는 인접거리에 따라 유사도를 측정한다. 최종적으로 PPC 기법은 측정된 유사도를 이용하여 대용량 데이터 집합을 군집화한다. PPC 기법은 UCI Repository 데이터를 이용하여 실험해 본 결과, 다른 클러스터링 기법들 보다 우수한 응집도를 보였다.