Learning both weights and connections2 [논문 구현] Learning both weights and connections for efficient Neural Network 해당 코드를 참고하여 작성하였습니다. https://github.com/jack-willturner/deep-compression GitHub - jack-willturner/deep-compression: Learning both Weights and Connections for Efficient Neural Networks https://arxiv.org Learning both Weights and Connections for Efficient Neural Networks https://arxiv.org/abs/1506.02626 - GitHub - jack-willturner/deep-compression: Learning both Weights and Connections for Efficien.. 2022. 6. 2. [논문 리뷰] Learningn both Weights and Connections for Efficient Neural Network https://arxiv.org/pdf/1506.02626.pdf Learning both Weights and Connections for Efficient Neural Network, 논문을 바탕으로 작성하였습니다. https://github.com/jack-willturner/deep-compression 코드 참고 1 Abstract 기존 Network들은 학습을 하기 이전에 architecture들을 고정시키기 때문에 학습 단계에서 구조를 발전시키는 방법에 제한이 있었다. 이 제한을 해결하기 위해서 본 논문은 Accuracy를 낮추지 않으면서, 중요한 connection만 학습시켜 저장공간을 줄이고 계산량을 줄이는 방법을 제안한다. 불필요한 connections 들을 없애는 작업인 pruning.. 2022. 5. 23. 이전 1 다음
