딥러닝8 [ML/DL] Explainability vs. Interpretability in AI 안녕하세요! Robert 입니다. 이번 포스트 에서는 Explainable AI (XAI) vs. Interpretable AI 에 대한 내용을 다뤄보고자 합니다. 주로 참고한 포스트는 Richard Gall 님 께서 KD Nuggets 에 올려주신 Machine Learning Explainability vs Interpretability: Two concepts that could help restore trust in AI 입니다. * 원문도 읽어보시는 것을 추천드립니다! Explainable AI? Interpretable AI? 에 대한 개인적인 호기심을 위주로 조사해봤습니다. 1. AI (Deep learning) Explainability 가 필요한 이유 2. Explainability vs.. 2020. 11. 26. [Medical Imaging/Computer Vision] Introduction to Medical Imaging and Computer Vision Hello, I'm Robert Sangwook Kim I'm planning to make a brief introduction for Medical Imaging and Computer Vision (Title : MICV) For the next 10 weeks, I would like to talk about topics related to medical image analysis, computer vision, and deep learning. Presentation files will be delivered in Korean and/or English via Youtube, Github, and Tistory (Or Notion). * If time allows, I will summarize.. 2020. 11. 15. [DL] Interpretability, Model Inspection and Representation Analysis Identifying underlying mechanisms giving rise to observed patterns in the data. When applying deep learning in scientific settings, we can use these observed phenomena as prediction targets, but the ultimate goal remains to understand what attributes give rise to these observations - A survey of Deep Learning for Scientific Discovery ( Maithra Raghu, Eric Schmidt 2020 ) 이 포스트는 A survey of Deep Le.. 2020. 4. 5. [DL] SuperResolution in Magnetic Resonance Imaging 1. Super-resolution MRI through Deep Learning (Qing Lyu et al, 2018 ) Two SOTA NN for CT denoting and deblurring, transfering them for super-resolution MRI Two-fold resolution enhancement 2. CT Super-resolution GAN Constrained by the Identical, Residual, and Cycle Learning Ensemble(GAN-CIRCLE) Reference of [1] 3. MRI Super-Resolution with Ensemble Learning and Complementary Priors ( Qing Lyu et .. 2020. 4. 1. 이전 1 2 다음
