Today at Stanford, we released Levanter, a Jax-based framework for training foundation models. It is now open-source on Github under Apache 2.0.
Read MoreThings I Learned at Landing AI
Over the past four and a half years at Landing AI, I have had the incredible opportunity to work with Andrew Ng, Dillon Laird and other amazing people to build AI applications across various industries. Each project has brought its unique challenges, pushing me to dive deeper into the ever-evolving world of AI. As I look back at this enriching journey, I am grateful and humble to share the lessons that I've learned in the hope of inspire others in the field.
Read MoreFast and Simple Image Search with Foundation Models
In this blog post, I will walk you through how to build a fast and simple image search tool. I developed an image search application that uses multimodal foundation models to search for highly accurate and relevant results. By following this blog post and our code base, you can easily build one yourself!
Read MoreThe Making of LandingLens AI Platform: Motivation and My Favorite Features
Last week, at Landing AI, we publicly launched our flagship AI platform, LandingLens. This all-in-one platform empowers users to build a computer vision application from start to deployment. In this blog, I want to share the motivation behind building this AI platform as well as highlight a few key features that I truly enjoy!
Read MoreSide Project Ideas with Large Pretrained Foundation Models
I have been brainstorming with friends possible side project ideas to try with Foundation Models. In this blog, I’ll share some of the interesting and practical side project ideas that utilize pre-trained foundation models. Whether you're a seasoned developer or a beginner, hope this will inspire you to unleash your creativity and build something amazing.
Read More做新年计划时,我想你看向未来十年
临近年末,人们纷纷在社交网络上开始回顾过去一年、开始新一年的计划,这是很好的习惯。吴恩达老师在他新一期newsletter里则提供了一种新的思路:与其以2023年这一年为单位去计划,不如站在更长远的视角,将2023年视作一个开始,做更长期的人生规划。
Read MorePaper Explained - LAION-5B
In this blog post, I cover one of the awarded papers in NeurIPS 2022. This paper presents LAION-5B, a dataset consisting of 5.9 billion image-text pairs, to further push the scale of open datasets for training and studying state-of-the-art language-vision models. With this large scale, it gives strong increases to zero-shot transfer and robustness.
Read MoreBuild an Automated Cross-Domain Question Answering System
Question Answering models are often used to automate the response to human questions by leveraging a knowledge base. My team at Stanford aims to build a robust question answering system that works across datasets from multiple domains. We explore two transformer-based Sparsely-Gated Mixture-of-Experts architectures and conduct an extensive ablation study to reach the best performance.
Read MoreThe Importance of Metrics in Machine Learning and How to Use Them
Metrics are critical in machine learning projects. They help a team to prioritize their resources and concentrate on a single, clear objective. I am always amazed to see that, once my team is aligned on a single metric to optimize, the speed and momentum we will be able to execute. In the end, we will usually be able to accomplish the goals that seem impossible in the beginning.
Read More2022年的第一个旅程
我最终还是成功地在2022年第一天踏上了去新加坡的航班,意外之余旅行依然按照原定的计划前进着。希望2022年,我和读着这篇文章的朋友们,都可以按着自己想要走的道路前行,完成新年定下的目标,走向一个更广阔的世界。
Read MoreModel Training with Machine Learning
Based on our past experience at Landing AI we have developed best practices for model training and evaluation. In this article, I share a few high-priority tasks during model training. We openly share our guiding principles to help machine learning engineers (MLEs) through model training and evaluation.
Read MoreData Labeling of Images for Supervised Learning
At Landing AI we observed how many projects took an unnecessarily long and painful process to complete. It was due to ambiguous defect definitions or poor labeling quality. In comparison, it will make the life of machine learning engineers much easier, and the whole project lifespan much shorter, by having a dataset with high quality labels. Therefore, it is very important to invest the time in the project’s early stage to clarify defect definitions and formalize labeling.
Read MoreData Validation for Machine Learning - Paper Reading Note
This paper reminds me of many time where our model in production perform strangely, so engineers have to spend hours investigate root causes and roll back or push for fixes. Lots of late night works as result of such mistakes. I agree with this paper that such data validation systems, if implemented correctly, can really help save significant amount of engineer hours by catching important errors proactively and diagnose model errors more efficiently.
Read MoreCoursera’s IPO Day
Coursera帮我在很多领域打开了门,让我可以顺着好奇心去探索不同的学科,其中也包括我现在从事且热爱的ML。恭喜吴老师带着Coursera成功上市、打开了一个新篇章。希望#COUR 能帮助更多的人实现终生学习的理想。
Read More职业思考 - 过去一段时间我所做的和接下来我需要做的
我最近的一些职业思考,主要是想要帮助自己理清自己的职业发展目标,然后想清楚自己接下来想要着重发展的能力,来帮助自己利用未来一两年的时间更好地为创业做准备。
Read MoreDesigning Image Acquisition for Machine Vision
At Landing AI, I have gone through several projects where we developed an end-to-end machine-learning system from “scratch'“. That means before we started on the project, there was no existing data collection procedure, so we had to start from zero and set up cameras.
Read MoreApple Fitness+
I am looking forward to a more radical redesign of gym space that well integrates with these virtual workout services and elevate the users’ experience around workout.
Read MoreTech Talk on Lean Six Sigma
I did a tech talk on Lean Six Sigma at Landing AI this week. I’d like to share the presentation slide and the note that I made for the tech talk.
Read MoreMy Statement of Purpose
I want to build things that can generate tremendous and long lasting values for the society. These are the things that won’t expire or go outdated quickly, things whose value can grow and accumulate over a long period of time, and things that can continuously generate positive values for people and the society.
Read MoreTwo Types of Full Stack Machine Learning Engineering
There are two types of Full Stack Machine Learning Engineering in my mind — one vertical and one horizontal
Read More