Transformers EXPLAINED! Neural Networks | | Encoder | Decoder | Attention

===== Likes: 16 👍: Dislikes: 0 👎: 100.0% : Updated on 01-21-2023 11:57:17 EST ===== Transformers Explained! This architecture came from this amazing paper: Attention is all you need. Link here: https://arxiv.org/abs/1706.03762 Parts of this architecture is used for state-of-the-art technologies such as GPT-3 and variations of BERT. So, you must know what a transformer model is if you want to dive further into the more advanced methods since they all build upon the principles of the transformer model! I explain what you NEED to know and nothing more! Feel free to support me! Do know that just viewing my content is plenty of support! 😍 ☕Consider supporting me! https://ko-fi.com/spencerpao ☕ Watch Next? Named Entity Recognition → https://youtu.be/4pCB1lZrBcQ Text Cleaning and Preprocessing → https://youtu.be/ZucclQNVBlo 🔗 My Links 🔗 Github: https://github.com/SpencerPao/spencerpao.github.io My Website: https://spencerpao.github.io/ Notebook: https://github.com/SpencerPao/Natural-Language-Processing/tree/main/Transformers 📓 Requirements 🧐 Python Jupyter notebok ⌛ Timeline ⌛ 0:00 - What is a Transformer? Additional Resources 1:41 - Why use a Transformer architecture? 3:17 - Encoder Block 7:52 - Decoder Block 10:20 - Multi-head Attention Mechanisms Explained Further 🏷️Tags🏷️: Python,Transformers,Transformer,Machine Learning, Deep Learning, Encoder, Decoder, Attention, multi-head attention, embedding, Natural Language Processing, natural, language, processing, word, token, Normalization,Positional encoding,layers,softmax,output,probabilities,feed-forward network,network,tutorial,how to,instruction,gpt-3,building block,BERT 🔔Current Subs🔔: 2,906