DST

2000년 도입 · 논문 205편에서 사용

Dynamic sparse training methods train neural networks in a sparse manner, starting with an initial sparse mask, and periodically updating the mask based on some criteria.

출처: Scalable Training of Artificial Neural Networks with Adaptive Sparse Connectivity inspired by Network Science

소개 논문: Scalable Training of Artificial Neural Networks with Adaptive Sparse Connectivity inspired by Network Science