On the Implementation of Fixed-Point Exponential Function for Machine Learning and Signal- Processing Accelerators

被引：1
|
作者：
Chandra, Mahesh [1 ]
机构：
[1] NXP Semicond India Ltd, Noida 201301, India
来源：
IEEE DESIGN & TEST | 2022年 / 39卷 / 04期
关键词：
Table lookup; Hardware; Taylor series; Arithmetic; Adders; Optimization; Neural networks; Digital integrated circuit; natural exponential; activation function; Gaussian function;
D O I：
10.1109/MDAT.2021.3133373
中图分类号：
TP3 [计算技术、计算机技术];
学科分类号：
0812 ;
摘要：
Editor's notes: The natural exponential function appears in a broad range of conventional and emerging applications, including the activation functions used in deep learning applications. This article presents an optimized implementation of exponential function for variable precision fixed-point negative inputs. Hence, this design can boost the performance and energy efficiency of a vast amount of hardware accelerators and systems. -Umit Ogras, Arizona State University
引用
收藏
页码：64 / 70
页数：7
相关论文
共 50 条
  • [1] Implementation of Machine Learning Applications on a Fixed-Point DSP
    Bharati, Swetha K.
    Jhunjhunwala, Ashok
    2015 IEEE 28TH CANADIAN CONFERENCE ON ELECTRICAL AND COMPUTER ENGINEERING (CCECE), 2015, : 1458 - 1463
  • [2] An introduction to fixed-point signal processing
    Linebarger, DA
    Bryan, TA
    IEEE 11TH DIGITAL SIGNAL PROCESSING WORKSHOP & 2ND IEEE SIGNAL PROCESSING EDUCATION WORKSHOP, 2004, : 19 - 23
  • [3] Hardware Implementation of Approximate Fixed-point Divider for Machine Learning Optimization Algorithm
    Han, Gandong
    Zhang, Weiyi
    Niu, Liting
    Zhang, Chun
    Wang, Zhihua
    Wang, Ziqiang
    2022 IEEE ASIA PACIFIC CONFERENCE ON POSTGRADUATE RESEARCH IN MICROELECTRONICS AND ELECTRONICS, PRIMEASIA, 2022, : 22 - 25
  • [4] Introduction to Fixed-point Multiplication and Signal Processing Application
    Fryza, Tomas
    PROCEEDINGS OF 19TH INTERNATIONAL CONFERENCE RADIOELEKTRONIKA 2009, 2009, : 281 - 284
  • [5] Fixed-Point Evaluation of Extreme Learning Machine for Classification
    Xu, Yingnan
    Jiang, Jingfei
    Jiang, Juping
    Liu, Zhiqiang
    Xu, Jinwei
    PROCEEDINGS OF ELM-2015, VOL 1: THEORY, ALGORITHMS AND APPLICATIONS (I), 2016, 6 : 27 - 38
  • [6] Synthesizing Optimal Fixed-Point Arithmetic for Embedded Signal Processing
    Hass, K. Joseph
    53RD IEEE INTERNATIONAL MIDWEST SYMPOSIUM ON CIRCUITS AND SYSTEMS, 2010, : 61 - 64
  • [7] Fixed-point DSP implementation of Wavelet decomposition for image processing
    Frassi, G
    Bellini, A
    Proceedings of the Fourth IEEE International Symposium on Signal Processing and Information Technology, 2004, : 373 - 376
  • [8] A Novel Fixed-Point Conversion Methodology For Digital Signal Processing Systems
    Dinh, Phuong T. K.
    Dinh, Linh T. T.
    Tran, Tung T.
    Pham, Lam S.
    Le, Han D.
    Hoang, Chi P.
    Nguyen, Minh D.
    IEICE TRANSACTIONS ON FUNDAMENTALS OF ELECTRONICS COMMUNICATIONS AND COMPUTER SCIENCES, 2022, E105 (08)
  • [9] A Novel Fixed-Point Conversion Methodology For Digital Signal Processing Systems
    Dinh, Phuong T. K.
    Dinh, Linh T. T.
    Tran, Tung T.
    Pham, Lam S.
    Le Duc, Han
    Hoang, Chi P.
    Nguyen, Minh D.
    IEICE TRANSACTIONS ON FUNDAMENTALS OF ELECTRONICS COMMUNICATIONS AND COMPUTER SCIENCES, 2022, E105A (12) : 1537 - 1550
  • [10] Quantization analysis for fixed-point implementation of speech processing for the hearing impaired
    Magotra, N
    Bangalore, S
    Savadatti, S
    Kasthuri, P
    Divakar, S
    Stetzler, T
    Gelabert, P
    42ND MIDWEST SYMPOSIUM ON CIRCUITS AND SYSTEMS, PROCEEDINGS, VOLS 1 AND 2, 1999, : 688 - 691
12345