Top International Magazines《IEEE Transactions on Neural Networks and Learning Systems》

AInnovation published a paper "Deep Inception-Residual Laplacian Pyramid Networks for Accurate Single-Image Super-Resolution", which proposes a new image super-resolution algorithm that can more quickly improve the accuracy of image reconstruction. Product identification and other fields have very high industrial practical value.

2019 Design Automation Conference

AInnovation published a paper "Efficient GPU NVRAM Persistence with Helper Warps", and proposed a method to improve GPU performance and break through the bottleneck of computing power in the AI era by using NVRAM storage transaction processing system on GPU.

2019 IEEE International Conference on Computer Vision

AInnovation published the paper "HM-NAS: Efficient Neural Architecture Search via Hierarchical Masking" and was best nominated by the workshop. The paper proposed a search method using hierarchical masks to make model training faster, model parameters less, and model network structure. It is better and requires less computing power. It only takes 1-2 GPUs for one day of training to complete the training of the model.