Zobrazeno 1 - 10
of 114
pro vyhledávání: '"Byeong-Gyu Nam"'
Publikováno v:
IEEE Access, Vol 12, Pp 96552-96564 (2024)
Deep neural network (DNN) is becoming pervasive in today’s applications with intelligent autonomy. Nonetheless, the ever-increasing complexity of modern DNN models caused several challenges on edge devices, struggling to support the intensive compu
Externí odkaz:
https://doaj.org/article/8887401f535643c9815ec104d79705e4
Publikováno v:
IEEE Access, Vol 9, Pp 117554-117564 (2021)
This paper proposes design strategies for a low-cost quantized neural network. To prevent the classification accuracy from being degraded by quantization, a structure-design strategy that utilizes a large number of channels rather than deep layers is
Externí odkaz:
https://doaj.org/article/f24af48fe02b428b9247bf369bc643c1
Publikováno v:
Electronics Letters, Vol 57, Iss 15, Pp 573-575 (2021)
Abstract Convolutional neural network (CNN) is widely used for various deep learning applications because of its best‐in‐class classification performance. However, CNN needs several multiply‐accumulate (MAC) operations to realize human‐level
Externí odkaz:
https://doaj.org/article/6164b18bd5f44b5cb6db21f4ee378d67
Publikováno v:
IEEE Transactions on Circuits and Systems I: Regular Papers. 67:5189-5199
This paper demonstrates a compact mixed-signal (MS) convolutional neural network (CNN) design procedure by proposing a MS modular neuron unit that alleviates analog circuit related design issues such as noise. Through the first step of the proposed p
Publikováno v:
Electronics Letters, Vol 57, Iss 15, Pp 573-575 (2021)
Convolutional neural network (CNN) is widely used for various deep learning applications because of its best‐in‐class classification performance. However, CNN needs several multiply‐accumulate (MAC) operations to realize human‐level cognition
A Low-power Real-time Hidden Markov Model Accelerator for Gesture User Interface on Wearable Devices
Publikováno v:
A-SSCC
A low-power and real-time hidden Markov model (HMM) accelerator is proposed for gesture user interfaces on wearable smart devices. HMM algorithm is widely used for sequence recognitions such as speech recognition and gesture recognition due to its be
Autor:
Byeong-Gyu Nam
Publikováno v:
JOURNAL OF SEMICONDUCTOR TECHNOLOGY AND SCIENCE. 19:97-108
Publikováno v:
JSTS:Journal of Semiconductor Technology and Science. 17:162-166
Publikováno v:
Circuits at the Nanoscale ISBN: 9781315218762
Circuits at the Nanoscale
Circuits at the Nanoscale
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::ab6a4f2724dd80ecaacaf11b1b69f32b
https://doi.org/10.1201/9781315218762-27
https://doi.org/10.1201/9781315218762-27
Publikováno v:
JSTS:Journal of Semiconductor Technology and Science. 16:251-254
An energy-efficient object matching accelerator is proposed for mobile object recognition based on matching prediction scheme. Conventionally, vocabulary tree has been used to save the external memory bandwidth in object matching process but involved