I recently did a blog post on sensor fusion, and I included some input I received from Dave Rothenberg of Movea. He had some follow-on comments clarifying some points against my interpretation of our conversation. Unfortunately, I discovered that we have had some issues with our blog comments being visible. That has been fixed, so I wanted to post a new note here with a link to his comments since they’re moved off the front page now.
I thank Dave for his patience as we sorted this.
 Quantized Neural Networks for FPGA InferenceSponsored by Intel Implementing a low precision network in FPGA hardware for efficient inferencing provides numerous advantages when it comes to meeting demanding specifications. The increased flexibility allows optimization of throughput, overall power consumption, resource usage, device size, TOPs/watt, and deterministic latency. These are important benefits where scaling and efficiency are inherent requirements of the application. |
