Tag
BeFit is an end-to-end framework that shifts model capacity from weights to learnable Bernstein polynomial activations, enabling multiplication-free CNNs on resource-constrained microcontrollers while achieving 2.75pp higher accuracy than ReLU CNNs and up to 5.9× faster execution than the MLPerf Tiny DS-CNN reference.
The paper introduces BernBRS, a scalable framework for certified backward reachability analysis of DeepBernNets, computing certified inner and outer approximations of the Backward Reachable Set via activation-pattern-based refinement of the input space cover, demonstrated on Half-Cheetah and TinyBERT-derived models.
Bern2Edge is a neurosymbolic compiler that converts pre-trained neural networks into Bernstein polynomial representations for efficient and interpretable edge deployment on FPGAs, achieving significant reductions in latency and resource usage while maintaining accuracy.