https://github.com/afondiel/fundamentals-of-qualcomm-ai
Fundamentals of Qualcomm AI: A crash course
https://github.com/afondiel/fundamentals-of-qualcomm-ai
edge-ai embedded-ai on-device-ai qualcomm
Last synced: 3 months ago
JSON representation
Fundamentals of Qualcomm AI: A crash course
- Host: GitHub
- URL: https://github.com/afondiel/fundamentals-of-qualcomm-ai
- Owner: afondiel
- Created: 2025-06-08T21:53:36.000Z (4 months ago)
- Default Branch: main
- Last Pushed: 2025-06-08T22:10:37.000Z (4 months ago)
- Last Synced: 2025-06-20T02:03:06.623Z (4 months ago)
- Topics: edge-ai, embedded-ai, on-device-ai, qualcomm
- Homepage:
- Size: 63.1 MB
- Stars: 0
- Watchers: 0
- Forks: 0
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
Awesome Lists containing this project
README
# Fundamentals of Qualcomm AI (crash course)
## Overview
As an [Edge AI Engineer](https://afondiel.github.io/) constantly exploring state-of-the-art edge AI [solutions](https://github.com/afondiel/computer-science-notebook/blob/master/core/systems/edge-computing/edge-ai/industry-applications/), [Qualcomm](https://qualcomm.com/) is the only[^1] company offering a such robust and comprehensive ecosystem that includes pretrained [models](https://github.com/quic/aimet-model-zoo), [frameworks](https://github.com/quic/aimet), [cloud services](https://qdc.qualcomm.com/), and [on-device AI platforms](https://aihub.qualcomm.com/get-started). This layered ecosystem provides developers with a seamless experience: even without direct access to Qualcomm hardware, models can be run and profiled in the cloud, accelerating prototyping and deployment.
I took this course to gain a deeper and broader understanding of Qualcomm ecosystem. Other Qualcomm Edge AI course includes [Introduction On-Device AI](https://github.com/afondiel/Intro-to-On-Device-AI-Qualcomm) from DeepLearningAI, and more [here](./resources/Qualcomm_Courses_Notes.md).
[^1]: As of June 2025, this may change in the future
## Disclaimer
Screenshots or excerpts from course slides included in this repository are used solely for **educational purposes**, personal learning, and review. For any copyright infringement please review the [DISCLAIMER.md](./DISCLAIMER.md).
## Course Outline
1. [Introduction to Qualcomm AI](./chapters/slides/1_Intro_to_Qualcomm_AI/)
2. [Use Cases Qualcomm AI](./chapters/slides/2_Use_Cases_Qualcomm_AI/)
3. [Connected Intelligent Edge](./chapters/slides/3_Connected_Intelligent_Edge/)
4. [Qualcomm AI Stack Introduction](./chapters/slides/4_Qualcomm_AI_Stack_Introduction/)
5. [AI Model Efficiency Toolkit (AIMET)](./chapters/slides/5_AIMET/)
## Lab: Chapters & Notebooks
|Chapters|Description|Notebooks|
|----------------------------------|------------------------------|--------|
|[1. Introduction to Qualcomm AI](./chapters/slides/1_Intro_to_Qualcomm_AI/)|Qualcomm’s Toolkit, AI Engine Direct, and AI Stack.|-|
|[2. Use Cases Qualcomm AI](./chapters/slides/2_Use_Cases_Qualcomm_AI/) |Use cases for AI in mobile, automotive, compute, IoT, XR, and voice/ music.|-|
|[3. Connected Intelligent Edge](./chapters/slides/3_Connected_Intelligent_Edge/)|The Connected Intelligent Edge and what powers it.| - |
|[4. Qualcomm AI Stack Introduction](./chapters/slides/4_Qualcomm_AI_Stack_Introduction/)| Qualcomm AI Stack, including Qualcomm AI Studio with a graphic user interface, visualization tools, and domain-specific SDK |-|
| [5. AIMET](./chapters/slides/5_AIMET/)|AI Model Efficiency Toolkit (AIMET) that has pretrained models for image classification, semantic segmentation, super resolution, object detection, pose estimation, and speech recognition |-|
## References
- [Main course - Qualcomm Academy](https://academy.qualcomm.com/course-catalog/Fundamentals-of-Qualcomm-AI?cmpid=eml-JhQDNRxsB6&utm_medium=eml&utm_source=MKTO&utm_campaign=QWA-AI-Course-Promo)