• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.20 no.2
• /
• pp.165-170
• /
• 2020

The spiking neural network operates in a different mechanism than the existing neural network. The existing neural network transfers the output value to the next neuron via an activation function that does not take into account the biological mechanism for the input value to the neuron that makes up the neural network. In addition, there have been good results using deep structures such as VGGNet, ResNet, SSD and YOLO. spiking neural networks, on the other hand, operate more like the biological mechanism of real neurons than the existing activation function, but studies of deep structures using spiking neurons have not been actively conducted compared to in-depth neural networks using conventional neurons. This paper proposes the method of loading an deep neural network model made from existing neurons into a conversion tool and converting it into a spiking deep neural network through the method of replacing an existing neuron with a spiking neuron.

• Smart Media Journal
• /
• v.11 no.3
• /
• pp.26-30
• /
• 2022

Spiking neural network is a neural network that applies the working principle of real brain neurons. Due to the biological mechanism of neurons, it consumes less power for training and reasoning than conventional neural networks. Recently, as deep learning models become huge and operating costs increase exponentially, the spiking neural network is attracting attention as a third-generation neural network that connects convolution neural networks and recurrent neural networks, and related research is being actively conducted. However, in order to apply the spiking neural network model to the industry, a lot of research still needs to be done, and the problem of model retraining to apply a new model must also be solved. In this paper, we propose a method to minimize the cost of model retraining by extracting the weights of the existing trained deep learning model and converting them into the weights of the spiking neural network model. In addition, it was found that weight conversion worked correctly by comparing the results of inference using the converted weights with the results of the existing model.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2020.11a
• /
• pp.793-795
• /
• 2020

본 논문에서는 스파이킹 뉴론(Spiking Neuron)들이 쿨롱에너지 포텐셜 (Coulomb Energy Potential)을 가지는 스파이킹 신경회로망에서의 학습알고리즘을 일반화하여 구간연산(Interval Arithmetic)의 학습이 가능한 학습알고리즘을 제안한다. 제안하는 학습알고리즘은 입력 데이터로서 구간(Interval) 데이터와 포인트(Point) 데이터를 모두 학습 할 수 있는 일반화된 학습알고리즘으로서 간단한 컴퓨터 시뮬레이션을 통하여 범위(Lower bound & Upper bound)를 가지는 구간데이터와 포인트데이터의 통합적인 학습이 가능하고 전문가시스템(expert system)에서의 "don't care attributes"의 학습 등에도 활용이 가능함을 보인다.

• Smart Media Journal
• /
• v.11 no.2
• /
• pp.70-76
• /
• 2022

IoT application development using a cloud server causes problems such as data transmission and reception delay, network traffic, and cost for real-time processing support in network connected hardware. To solve this problem, edge cloud-based platforms can use neuromorphic hardware to enable fast data transfer. In this paper, we propose a model optimization method for supporting spiking neural networks on FPGA hardware. We focused on auto-adjusting network model parameters optimized for neuromorphic hardware. The proposed method performs optimization to show higher performance based on user requirements for accuracy. As a result of performance analysis, it satisfies all requirements of accuracy and showed higher performance in terms of expected execution time, unlike the naive method supported by the existing open source framework.

• Smart Media Journal
• /
• v.11 no.11
• /
• pp.32-39
• /
• 2022

As IoT applications that provide AI services increase, various hardware and software that support autonomous learning and inference are being developed. However, as the characteristics and constraints of each hardware increase difficulties in developing IoT applications, the development of an integrated platform is required. In this paper, we propose a tool for automatically generating components based on artificial neural networks and spiking neural networks as well as IoT technologies to be compatible with open platforms. The proposed component automatic generation tool supports the creation of components considering the characteristics of various hardware devices through the virtual component layer of IoT and AI and enables automatic application to open platforms.

• Geophysics and Geophysical Exploration
• /
• v.13 no.4
• /
• pp.323-329
• /
• 2010

Three deconvolution methods were applied to stacked seismic data obtained to investigate gas-hydrates in the Ulleung Basin, East Sea: (1) minimum-phase spiking deconvolution, (2) minimum-phase spiking deconvolution using an averaged wavelet from all traces, and (3) deterministic deconvolution using a wavelet with phases computed from well-logs. We analyzed the resolving property of these methods for lithological boundaries. The first deconvolution method increases temporal resolution but decreases lateral continuity. The second method shows, in an overall sense, similar results to the spiking deconvolution using a minimum phase wavelet for each trace; however, it results in a more consistent and continuous bottom-simulating reflector (BSR) and better resolved sub-BSR reflectors. The results from the third method reveal more detailed internal structures of debris-flow deposits and increased continuity of reflectors; in addition, the seafloor reflection and the BSR appear to have changed to a zero-phase waveform. These properties help more precisely estimate the distribution and reserves of gas hydrates in the exploration area by improving analysis of facies and amplitude of the BSR.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2021.05a
• /
• pp.347-350
• /
• 2021

본 논문에서는 지도학습(Supervised Learning)알고리즘을 사용하는 모듈러 스파이킹 신경회로망(Modular Spiking Neural Networks)에서 학습의 진행 상황에 맞추어 학습용 데이터를 사용하는 다중 단계 학습알고리즘을 제안한다. 또한 컴퓨터 시뮬레이션에 의하여 항공영상 클러스터링 문제에 적용한 결과를 보임으로써 실제적인 문제에서의 적용 타당성과 가능성을 보인다.

• The Journal of the Acoustical Society of Korea
• /
• v.39 no.4
• /
• pp.286-291
• /
• 2020

In this paper, we propose a system that recommends music through tempo-oriented music classification and sensor-based human activity recognition. The proposed method indexes music files using tempo-oriented music classification and recommends suitable music according to the recognized user's activity. For accurate music classification, a dynamic classification based on a modulation spectrum and a sequence classification based on a Mel-spectrogram are used in combination. In addition, simple accelerometer and gyroscope sensor data of the smartphone are applied to deep spiking neural networks to improve activity recognition performance. Finally, music recommendation is performed through a mapping table considering the relationship between the recognized activity and the indexed music file. The experimental results show that the proposed system is suitable for use in any practical mobile device with a music player.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.21 no.5
• /
• pp.71-77
• /
• 2021

Recently, there is a demand for efficient program development of an IoT application support frameworks considering heterogeneous hardware characteristics. In addition, the scope of hardware support is expanding with the development of neuromorphic architecture that mimics the human brain to learn on their own and enables autonomous computing. However, most existing IoT IDE(Integrated Development Environment), it is difficult to support AI(Artificial Intelligence) or to support services combined with various hardware such as neuromorphic architectures. In this paper, we design an AI component abstract model that supports the second-generation ANN(Artificial Neural Network) and the third-generation SNN(Spiking Neural Network), and implemented an autonomous IoT IDE based on the proposed model. IoT developers can automatically create AI components through the proposed technique without knowledge of AI and SNN. The proposed technique is flexible in code conversion according to runtime, so development productivity is high. Through experimentation of the proposed method, it was confirmed that the conversion delay time due to the VCL(Virtual Component Layer) may occur, but the difference is not significant.

• Journal of the Korean Institute of Telematics and Electronics A
• /
• v.31A no.12
• /
• pp.115-121
• /
• 1994

Aluminum films were chemically vapor deposited for the metallization of the integrated circuits and the spiking characteristics of the direct CVD Al/Si contacts were investigated. When the aluminum was formed by CVD uniform consumption of the substrate silicon was observed, which is quite different from the phenomena observed in sprttered Al. Silicon consumption occured during the deposition of CVD Al and the erosion depth of the silicon was several hundred $\AA$ when the continuous films were formed on the substrate while much less erosion of the silicon occured when the Al were formed in islands. When the submicron contacts were selectively plugged, contact resistances were very low and the erosion depth of the silicon was trivial.