Master ML Papers without Losing Your Shit

Summary In this video, the author shares tips to master machine and deep learning research papers without feeling overwhelmed. Outlines Things to read first in the paper Great details to find in the paper How to parse the content and take good notes Some deep skills to learn Highlights [00:03] Expect that these papers are complex and sophisticated, so don’t expect to master them in five minutes. [00:22] Create a process to help you understand the papers faster and more efficiently....

April 1, 2023 · 4 min · 823 words · Cony Chun, Ted Chun

Fine-tuning vs.Prompting: Two Types of Usage Derived from Different Expectations for LLMs

Summary This video introduces two different expectations about large language models: Fine-tuning and Prompting, corresponding to different techniques. Fine-tuning uses training data to fine-tune the model for a specific task; Prompting provides the model with instructions described in human language, with the expectation that the model will correctly understand the instructions and generate the correct answers. Both approaches have advantages and disadvantages. In this part, we discuss further about instruction learning and in-context learning in natural language processing....

10 min · 2044 words · Cony Chun, Ted Chun