Rice YangThe Great TransformersUnderstand the design and application of the Transformer-styled models14 min read·Nov 3, 2023----
Rice YangA Comparison between RNN, LSTM, and GRUA Note for the basic designs of the Recurrent Neural Networks5 min read·Dec 7, 2022----
Rice YangAn Overview of Contrastive LearningSimCLR, MoCo, SwAV, BYOL, CLIP, DeepCluster, PIRL, Barlow Twins. Understanding Contrastive Learning and its mainstream works.12 min read·Dec 2, 2022----
Rice YangCan AI Replace Human Designers? The Magic of Diffusion ModelsFrom VAE to Diffusion Models, understanding the Zero-Shot Text-to-Image through the versions of AIGC software DALL-E8 min read·Dec 1, 2022----
Rice Yang對比學習 Contrastive Learning 主流方法一覽SimCLR, MoCo, SwAV, BYOL, CLIP, DeepCluster, PIRL, Barlow Twins,一覽各種模型的底層邏輯18 min read·Nov 24, 2022--1--1
Rice YangAI 能取代設計師嗎?擴散模型 Diffusion Model是什麼黑魔法?講解圖片生成軟體 DALL-E 的演算法進化路徑,理解 VAE, Diffusion Model, Zero-Shot Text-to-Image 技術原理14 min read·Nov 12, 2022----
Rice Yang在實務中用生成網路 VAE 做半監督學習的原理與技巧詳解 NIPS 論文:Semi-supervised Learning with Deep Generative Models11 min read·Oct 5, 2022----