{"id":927837,"date":"2026-01-15T11:10:44","date_gmt":"2026-01-15T16:10:44","guid":{"rendered":"https:\/\/www.marketnewsdesk.com\/index.php\/keysight-unveils-machine-learning-toolkit-to-accelerate-device-modeling-and-pdk-development\/"},"modified":"2026-01-15T11:10:44","modified_gmt":"2026-01-15T16:10:44","slug":"keysight-unveils-machine-learning-toolkit-to-accelerate-device-modeling-and-pdk-development","status":"publish","type":"post","link":"https:\/\/www.marketnewsdesk.com\/index.php\/keysight-unveils-machine-learning-toolkit-to-accelerate-device-modeling-and-pdk-development\/","title":{"rendered":"Keysight Unveils Machine Learning Toolkit to Accelerate Device Modeling and PDK Development"},"content":{"rendered":"

<\/p>\n

Keysight Unveils Machine Learning Toolkit to Accelerate Device Modeling and PDK Development<\/b><\/p>\n

\nArtificial intelligence\/Machine Learning-driven modeling reduces time-to-market for faster Design Technology Co-Optimization development and accelerates model parameter extraction for advanced nodes, RF, and power applications<\/p>\n

SANTA ROSA, Calif.–(BUSINESS WIRE<\/a>)–Keysight Technologies, Inc.<\/a> (NYSE: KEYS) today announced the release of the new Machine Learning Toolkit<\/a> in the latest Keysight Device Modeling Software Suite. This new solution reduces model development and extraction time from weeks to hours, enabling faster Process Design Kit (PDK) delivery and Design Technology Co-Optimization (DTCO) applications.<\/p>\n

This press release features multimedia. View the full release here: https:\/\/www.businesswire.com\/news\/home\/20260115914104\/en\/<\/a><\/p>\n

\"Machine<\/p>\n

Machine Learning Toolkit speeds up model development time from weeks to hours.<\/p>\n<\/div>\n

\nThe semiconductor industry is undergoing rapid transformation, driven by advanced architectures such as gate-all-around (GAA) transistors, wide-bandgap materials such as GaN and SiC, and heterogeneous integration strategies including chiplets and 3D stacking. While these innovations drive performance, they also create complex modeling and parameter extraction challenges. Traditional workflows rely on physics-based compact models and manual parameter extraction, forcing engineers to adjust hundreds of interconnected parameters across multiple operating conditions, a process that can take weeks and often struggles to achieve optimal results. With increasingly tight schedules, faster, more predictive, and automated artificial intelligence\/Machine Learning (AI\/ML)-driven modeling solutions are now essential.<\/p>\n

\nKeysight\u2019s new Machine Learning Toolkit, featuring an ML optimizer, auto-extraction flows, and utilities within Device Modeling MBP 2026<\/a>, tackles these challenges by introducing a framework that combines advanced neural network architectures with ML-based optimization. Using this toolkit, auto-extraction can reduce the parameter extraction steps from over 200 to fewer than 10, accelerating PDK delivery, automating DTCO, and speeding up time-to-market.<\/p>\n

Key Features and Benefits:<\/b><\/p>\n