RepCNN: Micro-Sized, Mighty Models for Wakeword Detection
Always-on machine learning models require a very low memory and compute footprint. Their restricted parameter count limits the model’s capacity to learn, and the effectiveness of the usual training algorithms to find the best parameters. Here we show that a small convolutional model can be better trained by first refactoring its computation into a larger …
Read more “RepCNN: Micro-Sized, Mighty Models for Wakeword Detection”