PowerBI Data Analyst - Create visualizations and dashboards from scratch
Learn Generative AI, Prompt Engineering, and LLMs for Free
Overview
Google, IBM & Meta Certificates — All 10,000+ Courses at 40% Off
One annual plan covers every course and certificate on Coursera. 40% off for a limited time.
Get Full Access
Discover how to implement generative AI directly on edge devices without requiring cloud connectivity in this 29-minute conference talk from EDGE AI Milan 2025. Learn about NXP's revolutionary approach to bringing private, secure, and multimodal AI experiences to embedded systems through their EIQ GenAI Flow technology. Explore the capabilities of the i.MX family of SoCs and Neutron NPU for on-device inference, fine-tuning, and optimization of large language models. Examine practical implementations including private conversational AI with wake word detection, retrieval-augmented generation (RAG), and natural speech synthesis. Understand how to achieve multimodal inference using LLAMA3 and CLIP models without cloud dependency, and discover real-time, low-power image and language processing techniques using Kinara's accelerator technology. Master advanced optimization strategies including 4-bit and 8-bit quantization methods that enable massive models to run efficiently at the edge. Gain insights into building smart industrial systems and AI-powered embedded interfaces that prioritize security and privacy while delivering scalable, intelligent functionality directly on device.
Syllabus
NXP's Vision for Generative AI at the Edge | Alberto Alvarez, Live at Milan 2025
Taught by
EDGE AI FOUNDATION