Reviews: SpArSe: Sparse Architecture Search for CNNs on Resource-Constrained Microcontrollers
–Neural Information Processing Systems
Specifically, the way the authors encode the objectives in (1)-(3), and the desire for a Pareto optimal configuration is reasonable and seems extendable in future works. However, there are some non-trivial topics in this section that could use some more explanation, including the SpVD and BC pruning methods (S3.3), Thompson sampling (S3.4) to get the next configurations, and the coarse-to-fine search (S3.5).
Neural Information Processing Systems
Jan-21-2025, 07:16:20 GMT
- Technology: