Главная
Study mode:
on
1
Introduction
2
Qualcomm AI research
3
Selfsupervised learning
4
Proof of concept
5
Challenges
6
Agenda
7
FewShot Learning
8
Keyword Spotting
9
Personalization
10
Continuous learning
11
Semantic segmentation
12
Solution
13
State of progress
14
Aggregation
15
User verification
16
User verification without embeddings
17
User verification with embeddings
18
Federated learning
19
Back propagation
20
Back propagation implementation
21
Quantized training
22
Reducing memory
23
Questions
24
Conclusion
Description:
Explore the future of AI-powered personalized experiences in this 37-minute webinar by Joseph Soriaga, Sr. Director of Technology at Qualcomm. Dive into the world of on-device learning and its potential to revolutionize data processing on edge devices while maintaining user privacy. Discover the latest research in few-shot learning, continuous learning, and federated learning. Gain insights into the challenges and solutions for moving from research to commercialization in on-device learning. Learn about self-supervised learning, keyword spotting, semantic segmentation, and user verification techniques. Understand the implementation of back propagation, quantized training, and memory reduction strategies for efficient on-device learning at scale.

Enabling On-Device Learning at Scale

tinyML
Add to list
0:00 / 0:00