fresh bytes
Subscribe Now

Computer learns to write its ABCs

DanqingWangComputerABCs-1449764769234.jpg

A new computer model can now mimic the human ability to learn new concepts from a single example instead of the hundreds or thousands of examples it takes other machine learning techniques, researchers say.

The new model learned how to write invented symbols from the animated show Futurama as well as dozens of alphabets from across the world. It also showed it could invent symbols of its own in the style of a given language.

The researchers suggest their model could also learn other kinds of concepts, such as speech and gestures.
via IEEE Spectrum

Continue reading 

Image: Danqing Wang

Leave a Reply

featured blogs
Apr 2, 2026
Build, code, and explore with your own AI-powered Mars rover kit, inspired by NASA's Perseverance mission....

featured paper

Quickly and accurately identify inter-domain leakage issues in IC designs

Sponsored by Siemens Digital Industries Software

Power domain leakage is a major IC reliability issue, often missed by traditional tools. This white paper describes challenges of identifying leakage, types of false results, and presents Siemens EDA’s Insight Analyzer. The tool proactively finds true leakage paths, filters out false positives, and helps circuit designers quickly fix risks—enabling more robust, reliable chip designs. With detailed, context-aware analysis, designers save time and improve silicon quality.

Click to read more

featured chalk talk

Nexperia GaN Power Proliferating in All Things Motor Control/Drive
Sponsored by Mouser Electronics and Nexperia
In this episode of Chalk Talk, Art Gonsky from Nexperia and Amelia Dalton discuss the biggest challenges of electric motors and controllers and how GaN power solutions can help solve these issues. They  also investigate how silicon, silicon carbide and GaN power solutions compare and how Nexperia and NXP technologies can get your next motor control design up and running in no time!     
Mar 25, 2026
25,690 views