Building AI based, secure IoT devices using ModusToolbox™ and PSoC™ 64 MCUs webinar
Implementing AI in IoT is more than training ML data and creating a model. Bridging the gap between the tooling used to create models and the process to validate and optimize it for an embedded microcontroller device is extremely complex and leads to slow time-to-market. That is why Infineon has introduced ModusToolbox™ Machine Learning Tools enabling rapid evaluation/deployment of ML models onto Infineon MCUs.
Join this webinar to learn how ModusToolbox™ ML enables:
- Import of models from popular training frameworks such as TensorFlow™
- Optimization of models for embedded platforms to reduce the size and complexity
- Validation of performance of optimized model by benchmarking
- Generation of optimized model code and libraries which are integrated with ModusToolbox™ microcontroller, connectivity, and security development flows
As well as a hands-on technical demo and to get started quickly and easily with Infineon PSoC™ 64 MCUs and Arrow Electronics.
Speakers:
Sree Harsha Angara
Product Marketing Manager | Cypress Semiconductor
Sree Harsha Angara is a Product Marketing Manager at Infineon for the PSoC 64 line of Secure MCU’s. He drives secure manufacturing, cloud eco-system compliance for IoT applications. In the past, he has designed and implemented firmware for a variety of different products, from consumer grade audio devices to high reliability server system management.
Nicholas Sharp
Senior Applications Engineer | Infineon
Nicholas Sharp is a Senior Applications Engineer at Infineon in the MCU division. Currently he is working on developing Machine Learning with Infineon MCU's and designs firmware for digital systems. Nicholas holds a Computer Engineering degree from Seattle Pacific University.

Locations/Dates:
Date: Wednesday, August 25, 2021
Time: 9:00am PDT| 12:00pm EDT| 18:00 CEST
Upcoming Events
Analog Devices' webinar: Edge to Cloud, Connect & Control with Remote IO modules
This Analog Devices webinar will explain how such modules can be leveraged in the automation system and implemented today to provide more flexibility, edge node insights and connectivity to fit into an edge-to-cloud based AI-driven system.