Simplifying and Automating Compact Model Process with Machine Learning
13.01.2026, 11:00 Uhr
In this webinar, we’ll show how the Machine Learning Optimizer in Device Modeling Model Builder Pro (MBP) dramatically improves modeling efficiency by automating and simplifying complex workflows. By transforming traditional multi-stage workflow into a few streamlined steps, the ML Optimizer reduces complexity, minimizes manual effort, and consistently delivers a globally optimal solution. Once created, an ML Optimizer flow can be easily reused and adapted for other device types or technologies, accelerating model development for new nodes.
Learn
- How the Machine Learning Optimizer in Device Modeling MBP dramatically improves modeling efficiency by automating and simplifying complex workflows.
- How practical demonstrations of ML Optimizer applied to industry-standard compact models and learn
- How to build efficient, automated flows using MBP’s Python environment.
This webinar is ideal for both experienced model developers and newcomers seeking higher modeling efficiency and interested in exploring AI/ML-assisted modeling methods.
RTN Measurement and Stress-testing using A-LFNA/WaferPro
20.01.2026, 11:00 Uhr
Random Telegraph Noise (RTN) has emerged as a critical reliability concern in advanced semiconductor nodes, particularly in FinFET and advanced CMOS technologies. This webinar presents a comprehensive methodology for Random Telegraph Noise (RTN) characterization and stress testing using the E4727B Advanced Low-Frequency Noise Analyzer (A-LFNA) integrated with Device Modeling WaferPro. The accurate and stable A-LFNA system enables high-sensitivity noise measurements across a wide frequency range and captures discrete switching events indicative of RTN.
Learn
- How to approach stress testing and monitor RTN under various bias and temperature conditions.
- How to approach statistical extraction of RTN parameters such as amplitude and time constants, along with modeling of RTN and flicker noise.
- How to perform RTN evolution and its correlation with device degradation mechanisms.
This webinar is intended for engineers and researchers focused on device reliability, compact modeling, and advanced noise characterization in semiconductor technologies.
Presenters
Yiao Li
Application Engineer in the Device Modeling
She earned her Ph.D. in Electrical Engineering from Auburn University in 2022 and joined Keysight Technologies the same year.
As an Application Engineer in the Device Modeling Marketing group at Keysight Technologies, she specializes in compact model extraction and workflow automation. With extensive experience in IC-CAP, MBP, and MQA, she has supported a wide range of device technologies, particularly heterojunction bipolar transistors (HBTs) and GaN HEMTs. Her work focuses on developing and optimizing modeling methodologies that enhance both the accuracy and efficiency of parameter extraction. Currently, she is driving innovation in AI-assisted device modeling, contributing to the advancement of compact modeling solutions for next-generation semiconductor technologies.
Fahad Usmani
Product Owner
Fahad Usmani is an Expert Application Developer specializing in Device Modeling segment within Keysight EDA. He holds a B.Tech. from Aligarh Muslim University (2009) and a M.S. in Electrical Engineering with a focus on Microelectronics from the University of Florida. As a Senior Member of IEEE, Fahad brings over 15 years of experience driving innovation across leading EDA companies and semiconductor IDMs.
Throughout his career, Fahad has contributed to flagship products and advanced technology nodes, leading cross-functional teams and delivering high-impact solutions. His expertise spans compact modeling, CAD, PDK validation, and 1/f noise characterization. He has authored eight peer-reviewed publications in prestigious IEEE conferences and journals. Currently, Fahad is focused on integrating AI/ML techniques into modeling and design workflows to enhance efficiency and advance noise measurement capabilities at Keysight.
Datum und Uhrzeit
13./20. Jänner 2026
11:00 Uhr
Ort
Online
Teilnahmegebühr
keine
