• Vanilla Sky (2001)

    평점: 4 결말을 대책없이 열어놨다면 꽤나 골치가 아팠을텐데 결말에 친절한 설명으로 가닥을 잡아주어 고마웠다. 그럼에도 불구하고 현실을 택하는 결말이 조금 아쉽다. 현실의 가치는 거짓일지도 모르는 것에 대하여 느끼는 찝찝함과 언젠가 현실을 자각해야하는 개연성이 높은데서 나타난다. 이 두가지가 전제되지 않는다면 굳이 아픈 현실을 택해야 하는 이유가 있을까?


  • Design of Digital Circuits

    Summary of Design of Digital Circuits course by Onur Mutlu in ETH Zurich. Thank you very much for opening up the great lectures and materials for self-learners like me. This course provided me invaluable insight to understand computers. Introduction and Basics Mysteries in Comp Arch Meltdown and Spectre RowHammer Introduction...


  • Distributed Prioritized Experience Replay

    WHY? Gorila framework separated several actors and learners with a centralized parameter server to parrallelize the learning process. This framework required one GPU per learner. WHAT? Ape-X architecture only consists of two parts: many actors and one learner. Given a model from model, many actors generate experience simultaneously. The learner...


  • A Hierarchical Latent Variable Encoder-Decoder model for Generating Dialogues

    WHY? Hierarchical recurrent encoder-decoder model(HRED) that aims to capture hierarchical structure of sequential data tends to fail because model is encouraged to capture only local structure and LSTM often has vanishing gradient effect. WHAT? Latent Variable Hierarchical Recurrent Encoder-Decoder(VHRED) tried to improve HRED by forcing to learn z with variational...


  • Forward-Backward Reinforcement Learning

    WHY? Reinforcement learning with sparse reward often suffer from finding rewards. WHAT? Forward-Backward Reinforcement Learning(FBRL) consists of forward and backward process. Forward process is like normal rl using memory to update Q function. In backward process, new model is introduced called backward model b. b is a neural network that...