• 한국경영과학회지
• /
• 제27권1호
• /
• pp.33-51
• /
• 2002

A fully connected Artificial Neural Network (ANN) contains many connections. Compared to the pruned ANN with fewer connections, the fully connected ANN takes longer time to produce solutions end may not provide appropriate solutions to new unseen date. Therefore, by reducing the sloe of ANN, we can overcome the overfitting problem and increase the computing speed. In this research, we reduced the size of ANN by destroying the connections. In other words, we investigated the performance change of the reduced ANN by systematically destroying the connections. Then we found the acceptable level of connection-destruction on which the resulting ANN Performs as well as the original fully connected ANN. In the previous researches on the sloe reduction of ANN, the reduced ANN had to be retrained every time some connections were eliminated. Therefore, It tool lolly time to obtain the reduced ANN. In this research, however, we provide the acceptable level of connection-destruction according to the size of the fully connected ANN. Therefore, by applying the acceptable level of connection-destruction to the fully connected ANN without any retraining, the reduced ANN can be obtained efficiently.

• 대한전기학회논문지:전력기술부문A
• /
• 제48권10호
• /
• pp.1231-1238
• /
• 1999

This paper presents an approach for the optimal heating load Identification using Diagonal Recurrent Neural Networks(DRNN). In this paper, the DRNN captures the dynamic nature of a system and since it is not fully connected, training is much faster than a fully connected recurrent neural network. The architecture of DRNN is a modified model of the fully connected recurrent neural network with one hidden layer. The hidden layer is comprised of self-recurrent neurons, each feeding its output only into itself. In this study, A dynamic backpropagation (DBP) with delta-bar-delta learning method is used to train an optimal heating load identifier. Delta-bar-delta learning method is an empirical method to adapt the learning rate gradually during the training period in order to improve accuracy in a short time. The simulation results based on experimental data show that the proposed model is superior to the other methods in most cases, in regard of not only learning speed but also identification accuracy.

• 통합자연과학논문집
• /
• 제14권4호
• /
• pp.183-188
• /
• 2021

Collaborative filtering is one of the commonly used methods in the web recommendation system. Numerous researches on the collaborative filtering proposed the numbers of measures for enhancing the accuracy. This study suggests the movie recommendation system applied with Word2Vec and ensemble convolutional neural networks. First, user sentences and movie sentences are made from the user, movie, and rating information. Then, the user sentences and movie sentences are input into Word2Vec to figure out the user vector and movie vector. The user vector is input on the user convolutional model while the movie vector is input on the movie convolutional model. These user and movie convolutional models are connected to the fully-connected neural network model. Ultimately, the output layer of the fully-connected neural network model outputs the forecasts for user, movie, and rating. The test result showed that the system proposed in this study showed higher accuracy than the conventional cooperative filtering system and Word2Vec and deep neural network-based system suggested in the similar researches. The Word2Vec and deep neural network-based recommendation system is expected to help in enhancing the satisfaction while considering about the characteristics of users.

• 한국컴퓨터그래픽스학회논문지
• /
• 제27권5호
• /
• pp.73-79
• /
• 2021

최근 컴퓨터 애니메이션 분야에서는 기존의 유한상태기계나 그래프 기반의 방식들에서 벗어나 딥러닝을 이용한 동작 생성 방식이 많이 연구되고있다. 동작 학습에 요구되는 네트워크의 표현력은 학습해야하는 동작의 단순한 길이보다는 그 안에 포함된 동작의 다양성에 더 큰 영향을 받는다. 본 연구는 이처럼 학습해야하는 동작의 종류가 다양한 경우에 효율적인 네트워크 구조를 찾는것을 목표로 한다. 기본적인 fully-connected 구조, 여러개의 fully-connected 레이어를 병렬적으로 사용하는 mixture of experts구조, seq2seq처리에 널리 사용되는 순환신경망(RNN), 그리고 최근 시퀀스 형태의 데이터 처리를 위해 자연어 처리 분야에서 사용되고있는 transformer구조의 네트워크들을 각각 학습하고 비교한다.

• 한국음향학회지
• /
• 제37권1호
• /
• pp.60-65
• /
• 2018

본 논문에서는 양서류 울음소리 구별을 CNN(Convolutional Neural Network)에 적용하기 위한 방법으로 공분산 행렬과 모듈로그램(modulogram)을 제안한다. 먼저, 멸종 위기 종을 포함한 양서류 9종의 울음소리를 자연 환경에서 추출하여 데이터베이스를 구축했다. 구축된 데이터를 CNN에 적용하기 위해서는 길이가 다른 음향신호를 정형화하는 과정이 필요하다. 음향신호를 정형화하기 위해서 분포에 대한 정보를 나타내는 공분산 행렬과 시간에 대한 변화를 내포하는 모듈로그램을 추출하여, CNN의 입력으로 사용했다. CNN은 convolutional layer와 fully-connected layer의 수를 변경해 가며 실험하였다. 추가적으로, CNN의 성능을 비교하기 위해 기존에 음향 신호 분석에서 쓰이는 알고리즘과 비교해보았다. 그 결과, convolutional layer가 fully-connected layer보다 성능에 큰 영향을 끼치는 것을 확인했다. 또한 CNN을 사용하였을 때 99.07 % 인식률로, 기존에 음향분석에 쓰이는 알고리즘 보다 높은 성능을 보인 것을 확인했다.

• Journal of Electrical Engineering and information Science
• /
• 제1권1호
• /
• pp.108-117
• /
• 1996

In this paper, we propose a new type of recurrent neural network architecture in which each output unit is connected with itself and fully-connected with other output units and all hidden units. The proposed recurrent network differs from Jordan's and Elman's recurrent networks in view of functions and architectures because it was originally extended from the multilayer feedforward neural network for improving the discrimination and generalization power. We also prove the convergence property of learning algorithm of the proposed recurrent neural network and analyze the performance of the proposed recurrent neural network by performing recognition experiments with the totally unconstrained handwritten numeral database of Concordia University of Canada. Experimental results confirmed that the proposed recurrent neural network improves the discrimination and generalization power in recognizing spatial patterns.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 2004년도 ICCAS
• /
• pp.1033-1036
• /
• 2004

The study on speech recognition and understanding has been done for many years. In this paper, we propose a new type of recurrent neural network architecture for speech recognition, in which each output unit is connected to itself and is also fully connected to other output units and all hidden units [1]. Besides that, we also proposed the new architecture and the learning algorithm of recurrent neural network such as Backpropagation Through Time (BPTT, which well-suited. The aim of the study was to observe the difference of Arabic's alphabet like "alif" until "ya". The purpose of this research is to upgrade the people's knowledge and understanding on Arabic's alphabet or word by using Recurrent Neural Network (RNN) and Backpropagation Through Time (BPTT) learning algorithm. 4 speakers (a mixture of male and female) are trained in quiet environment. Neural network is well-known as a technique that has the ability to classified nonlinear problem. Today, lots of researches have been done in applying Neural Network towards the solution of speech recognition [2] such as Arabic. The Arabic language offers a number of challenges for speech recognition [3]. Even through positive results have been obtained from the continuous study, research on minimizing the error rate is still gaining lots attention. This research utilizes Recurrent Neural Network, one of Neural Network technique to observe the difference of alphabet "alif" until "ya".

• 한국정보전자통신기술학회논문지
• /
• 제12권1호
• /
• pp.92-98
• /
• 2019

본 논문에서는 몰포러지 연산을 기본으로 하는 몰포러지 신경망(MNN: Morphological Neural Network) 기반 딥러닝 시스템을 제안하였다. 딥러닝에 사용되는 레이어는 몰포러지 레이어, 풀링 레이어, ReLU 레이어, Fully connected 레이어 등이다. 몰포러지 레이어에서 사용되는 연산은 에로전, 다이레이션, 에지검출 등이다. 본 논문에서 새롭게 제안한 MNN은 기존의 CNN(Convolutional Neural Network)을 이용한 딥러닝 시스템과는 달리 히든 레이어의 수와 각 레이어에 적용되는 커널 수가 제한적이다. 레이어 단위 처리시간이 감소하고, VLSI 칩 설계가 용이하다는 장점이 있으므로 모바일 임베디드 시스템에 딥러닝을 다양하게 적용할 수 있다. MNN에서는 제한된 수의 커널로 에지와 형상검출 등의 연산을 수행하기 때문이다. 데이터베이스 영상을 대상으로 행한 실험을 통해 MNN의 성능 및 딥러닝 시스템으로의 활용 가능성을 확인하였다.

• 한국항공우주학회지
• /
• 제49권3호
• /
• pp.197-204
• /
• 2021

유도탄의 비행 시험 중 고장 또는 비정상적인 기동이 발생하는 경우 비행을 계속하지 않도록 의도적으로 자폭한다. 이때 파편이 발생하며 안전 지역을 벗어났는지 여부를 실시간으로 추정하는 것이 중요하다. 본 논문에서는 Fully-Connected Neural Network(FCNN)를 이용하여 실시간으로 파편의 예상 낙하 영역 및 낙하 시간을 추정하는 방법을 제안한다. 많은 양의 학습 데이터 생성을 위해 Unscented Transform(UT)를 적용하였으며 신뢰도 확보를 위해 Monte-Carlo(MC) 시뮬레이션과 비교하여 파라미터를 선정하였다. 또한 제안한 방법의 추정 결과를 MC와 비교하여 성능을 분석하였다.

• 대한전기학회:학술대회논문집
• /
• 대한전기학회 1991년도 추계학술대회 논문집 학회본부
• /
• pp.189-192
• /
• 1991

This paper presents a modular structure design of analog Hopfield neural network. Each multiplier consists of four MOS transistors which are connected to an op-amp at the front end of a neuron. A pair of MOS transistor is used in order to maintain linear operation of the synapse and can produce positive or negative synaptic weight. This architecture can be expandable to any size neural network by forming tree structure. By altering the connections, other nework paradigms can also be implemented using this basic modules. The stength of this approach is the expandability and the general applicability. The layout design of a four-neuron fully connected feedback neural network is presented and is simulated using SPICE. The network shows correct retrival of distorted patterns.