논문 리뷰

    [논문 리뷰] Asynchronous Methods for Deep Reinforcement Learning (A3C)

    [논문 리뷰] Asynchronous Methods for Deep Reinforcement Learning (A3C)

    이번 논문에서는 강화학습을 비동기적이게 학습을 하게 만든 논문을 들고 왔다. 이 논문의 특이점이라고 한다면 보통의 학습에서 쓰이는 GPU를 사용하지 않고 CPU 코어들을 통한 병렬학습을 한다는 것이다. 이를 통해 Atari 벤치마크에서 새로운 기록을 세웠고 다른 도메인에서도 좋은 결과를 보여주는 모습이다. [1602.01783] Asynchronous Methods for Deep Reinforcement Learning (arxiv.org) Asynchronous Methods for Deep Reinforcement Learning We propose a conceptually simple and lightweight framework for deep reinforcement learning that..

    [논문 리뷰] Rainbow: Combining Improvements in Deep Reinforcement Learning (Rainbow DQN)

    [논문 리뷰] Rainbow: Combining Improvements in Deep Reinforcement Learning (Rainbow DQN)

    [1710.02298] Rainbow: Combining Improvements in Deep Reinforcement Learning (arxiv.org) Rainbow: Combining Improvements in Deep Reinforcement Learning The deep reinforcement learning community has made several independent improvements to the DQN algorithm. However, it is unclear which of these extensions are complementary and can be fruitfully combined. This paper examines six extensions to the ..

    [논문 리뷰] Noisy Networks for Exploration (NoisyNet)

    [논문 리뷰] Noisy Networks for Exploration (NoisyNet)

    [1706.10295] Noisy Networks for Exploration (arxiv.org) Noisy Networks for Exploration We introduce NoisyNet, a deep reinforcement learning agent with parametric noise added to its weights, and show that the induced stochasticity of the agent's policy can be used to aid efficient exploration. The parameters of the noise are learned with grad arxiv.org 이번 논문에는 DQN에 있는 fully connected layer에 param..

    [논문 리뷰] On the detection of synthetic images generated by diffusion models

    [논문 리뷰] On the detection of synthetic images generated by diffusion models

    저번 글에 이어 이번에는 GAN에 한정하지 않고 어떻게 diffusion 모델들도 진짜 이미지인지 가짜 이미지인지 판별할 수 있는지에 대한 논문을 리뷰할 것이다. GAN과 diffusion은 아키텍처 구조적으로 다르기 때문에 이를 어떻게 다루는지를 보자. [2211.00680] On the detection of synthetic images generated by diffusion models (arxiv.org) On the detection of synthetic images generated by diffusion models Over the past decade, there has been tremendous progress in creating synthetic media, mainly tha..

    [논문 리뷰] Are GAN generated images easy to detect? A critical analysis of the state-of-the-art

    [논문 리뷰] Are GAN generated images easy to detect? A critical analysis of the state-of-the-art

    AI CONNECT에서 진행하는 Fake or Real: AI 생성 이미지 판별 경진대회를 참가하기 위해 여러 가지 논문을 뒤적이던 중에 괜찮은 논문이 있어서 리뷰를 해보려고 한다. https://arxiv.org/abs/2104.02617 Are GAN generated images easy to detect? A critical analysis of the state-of-the-art The advent of deep learning has brought a significant improvement in the quality of generated media. However, with the increased level of photorealism, synthetic media are becomi..