Speaker
Register until April15:
✓Save up to 310 €
✓ 2-in-1 conference special
✓10 % Team Discount
Register Now
Register until April15:
✓Save up to 310 €
✓ 2-in-1 conference special
✓10 % Team Discount
Register Now
Register until December 12:
✓ML Intro Day for free
✓Raspberry Pi or C64 Mini for free
✓Save up to $580
Register Now
Register until December 12:
✓ML Intro Day for free
✓Raspberry Pi or C64 Mini for free
✓Save up to $580
Register Now
Register until November 7th:
✓Save up to € 210
✓10% Team Discount
Register Now
Register until November 7th:
✓Save up to € 210
✓10% Team Discount
Register Now
Infos
Description
There are different cases when you want to reduce your model size and hardware utilization.
Our case revolves around optimizing the cloud by identifying a sensible trade-off between
computation costs and model quality when dealing with a large amount of simultaneously
working neural networks. We want to better understand the comparisons and combinations with
tested approaches like distillation, pruning, and quantization.