<ul><li>RBFleX-NAS is a training-free Neural Architecture Search (NAS) framework that utilizes the Radial Basis Function (RBF) kernel and a detection algorithm.</li><li>Conventional NAS techniques require extensive training for evaluating candidate networks.</li><li>RBFleX-NAS outperforms other training-free NAS methods in terms of top-1 accuracy and search time.</li><li>RBFleX-NAS introduces NAFBee, an extended activation design space, for improved activation function exploration.</li></ul>

RBFleX-NAS: Training-Free Neural Architecture Search Using Radial Basis Function Kernel and Hyperparameter Detection

Discover more