Главная
Study mode:
on
1
Introduction
2
What kind of AI do we need
3
Current neural network architectures
4
Hardware acceleration for neural networks
5
Power efficiency
6
Summary
7
Intel
8
Etienne
9
Commercial applications
10
Is TinyML a disruptive technology
11
How do we know if a use case is doable
12
Negative use cases
13
Positive use cases
14
Tradeoffs
15
Use cases
16
Question
17
Point of view
18
IoT
19
Voice Command
20
Face ID
21
System Dimensions
22
The Problem
23
Conclusion
24
Object detection
25
Embedded vs cloud
26
AI and Embedded Systems
27
Challenges
28
Risk 5 and AI modeling
29
TinyML vs microcontrollers
30
Distributed AI
Description:
Explore the state of TinyML in this 53-minute panel discussion featuring experts Frédéric Pétrot, Etienne Balit, and Loic Lietar. Delve into the landscape and potential of ultra-low-power applications, recent advances, and challenges in TinyML. Learn about AI needs, current neural network architectures, hardware acceleration, and power efficiency. Discover commercial applications, disruptive potential, and use case evaluation for TinyML. Examine tradeoffs, IoT applications, voice commands, face ID, and object detection. Compare embedded vs. cloud solutions, and understand the challenges of AI in embedded systems. Investigate RISC-V architecture for AI modeling, and contrast TinyML with microcontrollers. Gain insights into distributed AI and participate in an interactive Q&A session with the audience.

TinyML Talks France - State of the TinyML Today

tinyML
Add to list
0:00 / 0:00