Researchers have focused on compressing weights to lower the memory requirements for neural networks. However, activations are far more memory hungry than weights and are the primary contributor to the issue.

In this webinar, our CEO, Steve Teig, will introduce novel strategies for compressing activations, allowing for reduced memory needs and for larger neural networks to be executed on space constrained hardware.

A Q&A session will follow the presentation.

For more information, please visit the Edge AI and Vision Alliance website here.

To access the free webinar, please register here.