Brief

Researchers have developed PrototypeNAS, a novel zero-shot neural architecture search method designed to rapidly create efficient deep neural networks (DNNs) for microcontroller units (MCUs). This method automates the selection, compression, and specialization of DNNs, addressing the resource-intensive nature of existing NAS techniques. PrototypeNAS decouples DNN design from training and utilizes an ensemble of zero-shot proxies with Hypervolume subset selection to optimize for accuracy and FLOPs, enabling deployment on off-the-shelf MCUs with comparable performance to larger models. AI

A new framework called Modality vs. Morphology has been proposed for classifying time series data from biological signals. This framework connects the waveform structure (morphology) of physiological processes to the design of machine learning models. By analyzing various biological signals like EEG and ECG, the research indicates that morphology, rather than the specific model class used, is the primary determinant of performance and interpretability in time series classification. AI