“Remember back in the old days, when nano-scale motors were a clunky 500 nanometers across? That record was subsequently broken with a 200-nanometer model, but has now been broken again, by a motor that’s just one nanometer wide. By comparison, the width of a human hair is about 60,000 nanometers. The new motor, created by scientists at Tufts University in Massachusetts, is reportedly the first one ever to consist of a single molecule.” via Gizmag
 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. |
