Results for “nas-bench-201”

2 skills

Evaluates the correlation between a zero-cost NAS metric (epsilon) and actual training accuracy across different neural architecture search spaces, testing the metric's ability to rank architectures without training. It probes whether output dispersion from constant weight initializations can serve as a reliable.

More results

Measures inference latency of binarized, 8-bit, and 32-bit convolutional layers on edge devices to evaluate the efficiency and speedup of the Larq Compute Engine framework compared to standard implementations.