Ezekiel ZhaoUnderstanding Reinforcement Learning from Human Feedback (RLHF): Theory and the Mechanism.A Story to Reinforcement Learning……Aug 10Aug 10
Ezekiel ZhaoVector-Quantisation in Wave2Vec 2.0Main points talked in this article:Nov 13, 2023Nov 13, 2023
Ezekiel ZhaoTransformer — Understand how the data is processed in EncoderWhen learning the Transformer model, it is essential to grasp the flow of data, understanding how information is processed. Remember…Jul 17, 2023Jul 17, 2023
Ezekiel ZhaoVisualise how the data is flowed in Machine Translation with Seq2Seq and Attention Models.Machine translation, the task of automatically translating text from one language to another, has seen significant advancements in recent…Jun 16, 2023Jun 16, 2023
Ezekiel ZhaoDetailed explanation: Diving into Leaves classification — An Intermediate Deep Learning Project.5-fold + ensemble = 98.5% acc!! (In order to make this article not too long, I will only show the part of resnext50)Mar 15, 2023Mar 15, 2023
Ezekiel ZhaoNeural Style Transfer — A practice in transfer learningThe picture above is photoed by me in London. There is always an idea that pops up in my mind when I looked at it — what if I make this…Oct 2, 2022Oct 2, 2022
Ezekiel ZhaoDeep Learning — How to do backwards propagation in MLP?In this article, I will detailed go through the process of backwards propagation , and provide a easy calculation process to show how it…Sep 1, 2022Sep 1, 2022
Ezekiel ZhaoRejection Sampling in RRejection sampling is also called the acceptance-rejection method or accept-reject algorithm. It’s a type of exact simulation method and is…Jun 24, 2022Jun 24, 2022
Ezekiel ZhaoMy first step into Data Science — Kaggle TitanicSince when I thought about what to do in the future, I always can not give myself a direction. However, after moving on to the university…Apr 18, 2022Apr 18, 2022