• ETRI Journal
• /
• 제40권4호
• /
• pp.421-434
• /
• 2018

The application of deep neural networks (DNNs) to connect the world with cyber physical systems (CPSs) has attracted much attention. However, DNNs require a large amount of memory and computational cost, which hinders their use in the relatively low-end smart devices that are widely used in CPSs. In this paper, we aim to determine whether DNNs can be efficiently deployed and operated in low-end smart devices. To do this, we develop a method to reduce the memory requirement of DNNs and increase the inference speed, while maintaining the performance (for example, accuracy) close to the original level. The parameters of DNNs are decomposed using a hybrid of canonical polyadic-singular value decomposition, approximated using a tensor power method, and fine-tuned by performing iterative one-shot hybrid fine-tuning to recover from a decreased accuracy. In this study, we evaluate our method on frequently used networks. We also present results from extensive experiments on the effects of several fine-tuning methods, the importance of iterative fine-tuning, and decomposition techniques. We demonstrate the effectiveness of the proposed method by deploying compressed networks in smartphones.

• 대한기계학회논문집
• /
• 제18권2호
• /
• pp.339-350
• /
• 1994

This paper presents a method for automatic generation of line balanced assembly sequences based on disassemblability and proposes a method of evaluating an assembly work time using neural networks. Since a line balancing problem in flexible assembly system requires a sophisticated planning method, reasoning about line balanced assembly sequences is an important field of concern for planning assembly lay-out. For the efficient inference of line balanced assembly sequences, many works have been reported on how to evaluate an assembly work time at each work station. However, most of them have some limitations in that they use cumbersome user query or approximated assembly work time data without considering assembly conditions. To overcome such criticism, this paper proposes a new approach to mathematically verify assembly conditions based on disassemblability. Based upon the results, we present a method of evaluating assembly work time using neural networks. The proposed method provides an effective means of solving the line balancing problem and gives a design guidance of planning assembly lay-out in flexible assembly application. An example study is given to illustrate the concepts and procedure of the proposed scheme.

• 정보보호학회논문지
• /
• 제33권6호
• /
• pp.861-868
• /
• 2023

보안을 유지하는 가운데 딥 러닝을 이용하여 데이터 분석 결과를 제공하는 서비스의 핵심적인 기술 중의 하나로 완전 동형 암호가 있다. 완전 동형 암호화된 데이터 간의 연산의 제약으로 인해 딥 러닝에 사용되는 비산술 함수를 다항식으로 근사해야 한다. 현재까지는 합성 미니맥스 다항식을 사용하여 비산술 함수를 근사한 다항식을 컨볼루션 뉴럴 네트워크에 적용했을 때 계층별로 같은 차수의 다항식만 적용하였는데, 이는 완전 동형 암호를 위한 효과적인 네트워크의 설계에 어려움을 준다. 본 연구는 합성 미니맥스 다항식으로 설계한 근사 다항식의 차수를 계층별로 서로 다르게 설정하여도 컨볼루션 뉴럴 네트워크에서 데이터의 분석에 문제가 없음을 이론적으로 증명하였다.