[sytelus]

This is super confusing. Questions:

1. What is your unique strength here?

2. Does user need to call in web API to use this? Can this whole thing work offline? If not, is web API part open sourced?

3. What are the techniques you are using to bring down power usage?

4. You keep mentioning AutoML but AutoML is only useful for training and generating model, not inference. For embedded software, the bottleneck is not training but inference. Also, you need to clearly mention what exact AutoML techniques are you referring to.

5. On one table you mention NVidia and CPU hardware having same GFLOPS. Very confusing.

Overall, I'd recommend more rigore and being crystal clear when you are using technical terminology.

[simbaz]

1. No production implemented the feature we open sourced. This is unique. 2. Whole thing(AI Inference/Classifier training) are offline. 3. ARM did it. 4. We have classifier training on the embedded system. 5. I calc the theory/real, arm is better than Nvidia GPU.