Nature

Optimization of deep learning architecture based on multi-path convolutional neural network algorithm

Current multi-stream convolutional neural network (MSCNN) exhibits notable limitations in path cooperation, feature fusion, and resource utilization when handling complex tasks. To enhance MSCNN’s ...
Nature

Neural architecture search using attention enhanced precise path evaluation and efficient forward evolution

Predictor-based Neural Architecture Search (NAS) utilizes performance predictors to swiftly estimate architecture accuracy, thereby reducing the cost of architecture evaluation. However, existing ...