Yu-Cheng Tsai

Built with PyTorch Geometric and using MovieLens DataSet Yu-Cheng Tsai · Follow Published in Towards Data Science · 13 min read · 6 hours ago — Photo by michael podger on Unsplash Graph Modeling A graph is a way to represent relationships between entities, using nodes to represent the entities and edges to represent the connections between them. This structure is versatile and can be applied to a wide range of real-world problems. For instance,

From tokens to labels: Performing classification with large language models Yu-Cheng Tsai · Follow Published in Towards Data Science · 6 min read · 5 hours ago — Photo by Myles Bloomfield on Unsplash Large Language Models (LLMs), trained on vast amounts of internet data, are versatile and can perform a wide range of natural language tasks. One common application is classification, a supervised learning task that categorizes…

A surprising experiment to show that the devil is in the details Yu-Cheng Tsai · Follow Published in Towards Data Science · 5 min read · 13 hours ago — Image by the author using DALL-E With the growing number of embedding models available, choosing the right one for your machine learning applications can be challenging. Fortunately, the MTEB leaderboard provides a comprehensive range of ranking metrics for various natural language processing tasks. Top 5