Efficient evaluation methods for neural architecture search: A survey
Neural Architecture Search (NAS) has received increasing attention because of its
exceptional merits in automating the design of Deep Neural Network (DNN) architectures …
exceptional merits in automating the design of Deep Neural Network (DNN) architectures …
Automated machine learning: past, present and future
Automated machine learning (AutoML) is a young research area aiming at making high-
performance machine learning techniques accessible to a broad set of users. This is …
performance machine learning techniques accessible to a broad set of users. This is …
Self-adaptive weight based on dual-attention for differentiable neural architecture search
Differentiable architecture search is a popular gradient-based method for neural architecture
search, and has achieved great success in automating design of neural network …
search, and has achieved great success in automating design of neural network …
On k-regular edge connectivity of chemical graphs
Quantitative structure property research works, which are the essential part in chemical
information and modelling, give basic underlying topological properties for chemical …
information and modelling, give basic underlying topological properties for chemical …
MGAS: Multi-Granularity Architecture Search for Effective and Efficient Neural Networks
Differentiable architecture search (DAS) has become the prominent approach in the field of
neural architecture search (NAS) due to its time-efficient automation of neural network …
neural architecture search (NAS) due to its time-efficient automation of neural network …
Scalable NAS with factorizable architectural parameters
Abstract Neural Architecture Search (NAS) replaces manually designed networks with
automatically searched networks and has become a hot topic in machine learning and …
automatically searched networks and has become a hot topic in machine learning and …