Blog

All hands on deck: A student team's annual quest to build the world's best autonomous underwater robot with AI

The story of one team's quest to win the annual RoboSub competition using the latest advances in AI and training data as part of their advantage.

Active Learning: Speed up training data cycles with uncertainty sampling

Machine learning engineers often rely on an active learning framework to surface the most informative data to learn from.

Using model-assisted labeling to speed up annotation efficiency with Labelbox

Recently, a team of researchers at the Institute of Industrial Science, a part of The University of Tokyo, leveraged Labelbox's model-assisted labeling features in order to speed up their machine learning processes by 2-3x.

Asking good questions isn’t the first step to building enterprise ML, it’s step 0

When email first came on the scene, it was revolutionary. People were excited to try a faster method of communicating with friends and business contacts. But of course, someone quickly found a way to ruin it. Spam (unwanted bulk emails, not the canned meat product) started popping up in huge numbers, slowing down network speeds and people’s productivity. If we wanted to improve internet speeds, we’d have to identify spam before it clogged up inboxes. Enter machine learning. Trained machine lea

Managing a Labeling Team and Building a High-Impact Deep Learning Model for Tree Identification

I participated in an amazing AI challenge through Omdena’s community where we built a classification model for trees to prevent fires and save lives using satellite imagery. Omdena brings together AI enthusiasts from around the world to address real-world challenges through AI models.

Introducing Image Segmentation at Labelbox

We set out to create a tool that makes image segmentation fast and accurate to make it accessible to more computer vision teams and projects.

Labelbox Adapts to Support American Family Insurance Automation

In this article, we discuss why and how we built a new labeling ontology feature to support American Family's use case. Labeling ontology is critical for machine learning applications. It determines what the labeler can label and, in turn, the categories the model will be able to identify.

Model Predictions, Semi-Automatic Labeling and Quality Assurance in Production

Model predictions play two vital roles in a machine learning pipeline. Predictions can be used to accelerate labeling speed as well as test and improve the accuracy of production models.

How to Measure Quality when Training Machine Learning Models

With quality assurance processes data scientists can monitor overall consistency and accuracy of training data, quickly troubleshoot quality errors, improve instructions, on-boarding, and training of labelers, and better understand the project specifics on what and how to label.

The Internet of Cows: AI in Agriculture with SomaDetect

SomaDetect SomaDetect provides dairy farmers with the information they need to produce the highest quality milk with the resources they have today, for a more sustainable dairy food system. An important part of making this happen is is machine learning and computer vision. We spoke with Bharath Sudarsan, Director of AI, who went into a little more detail about how SomaDetect is making a splash through the internet of cows. “Our basic business goal is to make better milk. We have IoT devices t