第二回 Deep Learning Acceleration 勉強会(DLAccel #2) での発表資料 https://idein.connpass.com/event/139074/ 高速化技術を下記の6観点で紹介 - 畳み込みの分解 (Factorization) - 枝刈り (Pruning) - アーキテクチャ探索 (Neural Architecture Search; NAS) - 早期終了、動的計算グラフ�(Early Termination, Dynamic Computation Graph) - 蒸留 (Distillation) - 量子化 (Quantization)
![論文紹介: Fast R-CNN&Faster R-CNN](https://cdn-ak-scissors.b.st-hatena.com/image/square/0bc54c4c9bfdb93090d6e0165cd14db49d998af6/height=288;version=1;width=512/https%3A%2F%2Fcdn.slidesharecdn.com%2Fss_thumbnails%2Ffastrcnnrpn-150725041955-lva1-app6892-thumbnail.jpg%3Fwidth%3D640%26height%3D640%26fit%3Dbounds)