I.Jeong | Log

  • Ai
  • Algorithm
  • bit
  • BNN
  • BOJ
  • C/C++
  • devenv
  • Error
  • for interview
  • git
  • jupyter
  • latex
  • Machine Learning
  • node.js
  • Python
  • stl
  • SUMMARY
  • untitled
  • VS Code
  • web
  • WSL
  • 논문 리뷰
  • Categories (31)
    • Computer Theory (1)
      • Data Structure (0)
      • Algorithm (1)
    • Programming (9)
      • C·C++ (7)
      • Node.js (1)
      • Web (1)
    • Dev Env (6)
      • Git (2)
      • Windows (1)
    • Untitled (9)
      • Summary (4)
      • Error (5)
      • Tistory (0)
    • Artificial Intelligence (1)
      • Review (1)
      • Math (0)

write POST

Manage

  • trevi_
  • Korea
  • isuu.jeong@gmail.com
  • https://github.com/ijgit

Binarized Neural Networks: Training Neural Networks with Weights and Activations Constrained to +1 or -1 (1)

2020. 11. 9.
Artificial Intelligence/Review
Abstract BNNs (Binarized Neural Networks) neural networks with binary wrights and activations at run-time at trining-time the binary weights and activations are userd for computing the gradients 방법 forward pass 동안, 메모리 사이즈와 접근을 줄이고, 대부분의 산술 연산을 비트 연산으로 대체함으로써 전력 효율성을 개선할 수 있다. 검증 two sets of experiments on Torch7 and Theano frameworks 검증 결과 MNIST, CIFAR-10, SVHN datasets 에서 매우 좋은 결과를 얻었다. binary..

티스토리툴바