Blog

How to improve model performance with less data

This data-centric ML method can reduce the required amount of training data by 10% to 50%.

Optimizing labeling operations: People and processes

How to hire your labeling operations team, find your vendors, and optimize your labeling processes.

Stop labeling data blindly

ML teams need to know "what data will improve model performance fastest?" These best practices will help teams identify model errors and prioritize better data.

Lessons for AI builders from Accelerate 2021

Accelerate 2021 featured speakers from ARK Invest, the United States Navy, NASA/JPL, Genentech, Stryker, and many more.

You’re probably doing data discovery wrong

Learn best practices for storing, evaluating, and visualizing labeled and unlabeled data so you can accelerate your model iteration cycles and simplify your training data pipeline.

CAPE Analytics tackles catastrophe and property analyses for insurance with AI

CAPE Analytics creates AI applications, primarily for insurance organizations, that extracts information from aerial or satellite geospatial images.

ImageBiopsy Lab uses model-assisted labeling to increase efficiency by 160%

ImageBiopsy Lab builds AI applications to help doctors better diagnose musculoskeletal diseases.

Genentech develops breakthrough labeling process for medical imagery ML

Genentech researchers are building convolutional neural networks to help diagnose illnesses and aid medical professionals.

How to improve model performance with active learning

Let's dive into some of the specific challenges of data-centric ML and how your team can address them by employing active learning methods.

How to build trust in your machine learning models

Getting buy-in from stakeholders can be a tough challenge for ML teams who want to build transformative, enterprise models that support major operations.