This Week in Machine Learning, 23 September 2016

This week’s top Machine Learning stories, including catching cybercriminals, screening for speech disorders, and … sorting cucumbers?

Machine Learning is one of the most exciting fields in the world. Every week we discover something new, something amazing, something revolutionary. It’s incredible, but it can also be overwhelming. That’s why we created This Week in Machine Learning! Each week we publish a curated list of Machine Learning stories as a resource to help you keep pace with all these exciting developments. New posts will be published here first, and previous posts are archived on the Udacity blog.

Whether you’re currently enrolled in our Machine Learning Nanodegree program, already working in the field, or just pursuing a burgeoning interest in the subject, there will always be something here to inspire you!


British cybersecurity firm Darktrace leverages machine learning to address the growing problem of cybercriminals stealing money by infecting ATMs with malware.


Apple acquires another machine learning firm, purchasing India-based Tuplejump and its open-source FiloDB project for analyzing massive amounts of complex data.


Evernote shifts its data from private servers to Google’s cloud infrastructure in large part to take advantage of Google’s artificial intelligence infrastructure.


Researchers at MIT create a machine learning-based system for automatically screening children for speech and language disorders through an accessible mobile app.


Facebook launches a new feature, powered by machine learning, that automatically infers when a message suggests a transaction and prompts the recipient to pay.

Food & Beverage

Makoto Koike, a Japanese farmer, uses TensorFlow with a Raspberry Pi 3 to create a system that automatically sorts cucumbers based on photos from low-resolution webcams.