News

May 1, 2019

Facebook Open-sources Ax and BoTorch to Simplify AI Model Optimization

Facebook has used the two tools for tasks that vary from optimizing Instagram’s back-end infrastructure to improving survey response rates .

May 1, 2019

Deep InfoMax: Learning Good Representations Through Mutual Information Maximization

As researchers apply machine learning to more complex real-world problems, they’ll need to rely less on algorithms that require annotation.

April 30, 2019

Microsoft Releases Windows Vision Skills Preview to Streamline Computer Vision Development

Microsoft's Windows Vision Skills include prebuilt models, APIs, and a robust set of deployment options.

April 29, 2019

Announcing the 6th Fine-Grained Visual Categorization Workshop

In recent years, such competitions have spurred progress in the development of relevant image detection and classification models.

April 26, 2019

Train and Deploy State-of-the-art Mobile Image Classification Models Via Cloud TPU

As organizations use ML more frequently, training and deploying small, fast, accurate machine learning models becomes increasingly important

April 24, 2019

Evaluating the Unsupervised Learning of Disentangled Representations

Understanding high-dimensional data and distilling that knowledge into useful representations in an unsupervised manner remains challenging.

April 24, 2019

What’s In an Image: Fast, Accurate Image Segmentation With Cloud TPUs

Performance and cost metrics for two segmentation models can help you choose the right model and TPU configuration for your needs.

April 24, 2019

AI In Depth: Creating Preprocessing-model Serving Affinity With Custom Online Prediction On AI Platform Serving

AI Platform Serving now lets you deploy your trained machine learning (ML) model with custom online prediction Python code, in beta.

April 18, 2019

Advancing Accessibility On the Web, In Virtual Reality, and In the Classroom

Papers & demos explore how to design technologies more inclusively, to support accessibility by users with cognitive & sensory disabilities.

April 17, 2019

MorphNet: Towards Faster and Smaller Neural Networks

Designing a suitable deep neural network (DNN) architecture for a given problem continues to be a challenging task.