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 MoreMachine Learning
The 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 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 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 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 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 MoreMy First Week of CS330 at Stanford
Meta Learning is one of the promising lines of work that aim to solve the small data problems in machine learning field. Currently, many people working on AI are thinking day and night about how to scale AI systems and improve their profit margins. One main challenge to solve is how to quickly build an AI model that reaches human-level performance on classes with only a few samples.
Read MoreYour Location Is Gold to Businesses
Business models that leverage location data from mobile devices are part of a growing, multi-billion dollar market. Where you are matters much more than you might think.
Read MoreStanford AI Salon - Deep Reinforcement Learning for Real World Systems
Today I went to Stanford to attend an AI Salon session hosted by the Stanford AI Lab. The topic of the salon today was "Deep Reinforcement Learning for Real World Systems". The speakers were Prof. Sergey Levine & Prof. Mykel Kochenderfer.
Read More从 AutoML 项目看谷歌的战略和人工智能技术的全民普及
AutoML 让机器可以自动化地为每个新的应用场景开发机器学习模型,这是谷歌“人工智能优先”战略的重要一步。
Read MoreExplainability and Trust in Products
For companies developing machine learning products, a key factor is to gain the users’ trust that the products will work for the best interest of the users and protect their privacy and security.
Read MoreAutoML from Google Cloud — Free Up ML Resources to Focus on Harder Things
AutoML and other similar services do have the potential to make AI more accessible to everyone, so that we can focus on much harder problems. We are far from automating the entire pipeline of Machine Learning development.
Read More