The advancements in machine learning (ML) opened a new opportunity to bring intelligence
to the low-end Internet-of-Things (IoT) nodes, such as microcontrollers. Conventional ML …

Despite the impressive progress in neural network architecture design, improving the
performance of the existing state-of-the-art models has become increasingly challenging …

In this paper, we explore a novel knowledge-transfer task, termed as Deep Model
Reassembly (DeRy), for general-purpose model reuse. Given a collection of heterogeneous …

Neural Architecture Search (NAS) is quickly becoming the standard methodology to design
neural network models. However, NAS is typically compute-intensive because multiple …

Neural Architecture Search (NAS) has been explosively studied to automate the discovery of
top-performer neural networks. Current works require heavy training of supernet or intensive …

Neural architecture search (NAS) enables researchers to automatically explore broad
design spaces in order to improve efficiency of neural networks. This efficiency is especially …

Over the past half-decade, many methods have been considered for neural architecture
search (NAS). Bayesian optimization (BO), which has long had success in hyperparameter …

ABSTRACT Neural Architecture Search (NAS) is a logical next step in the automatic learning
of representations, but the development of NAS methods is slowed by high computational …

Accuracy predictor is a key component in Neural Architecture Search (NAS) for ranking
architectures. Building a high-quality accuracy predictor usually costs enormous …

Early methods in the rapidly developing field of neural architecture search (NAS) required
fully training thousands of neural networks. To reduce this extreme computational cost …