• Massively Parallel Methods for Deep Reinforcement Learning

    WHY? A single agent usually takes too long to train. WHAT? Stacking experience with multiple agents would boost-up the speed of training. In addition, parralell gradient calculation can be used if multiple GPUs are available. This paper called this framework Gorila(General Reinforcement Learning Architecture). Gorilla consists of 4 parts: Actors,...


  • Spatial Transformer Networks

    WHY? Former CNNs were not spatially invariant. WHAT? Spatial Transformer Module can make a former CNN model invariant to cropping, translation, scale, rotation and skew without greatly increasing the computation cost. ST module consists of 3 parts: localisation network, grid generator, and sampler. Localisation network takes input feature map (...


  • Reservoir Dogs (1992)

    평점: 4.5 사건보다 더 몰입되는 끊임없는 수다. 그리고 그 수다로 그려내는 캐릭터들.


  • Star Wars: The Last Jedi (2017)

    평점: 4 캐릭터에는 5점 서사에는 3점. 모순적이고 고뇌하는 캐릭터가 좋다.


  • Rogue One (2016)

    평점: 4 서사는 5점 캐릭터는 3점. 스타’워즈’ 시리즈중 가장 전쟁 영화 같았지만 단편이라 캐릭터들을 살릴 새가 없었던 것이 아쉬움.