We optimize GPU tensor library in CUDA environment, providing efficient memory access, batch mode computations and shards mode computations.
Details
We study tensor decompositions (CPU, Tucker, Tensor-train/Tensor-ring,tensor networks, etc) and propose a transform-based tensor decomposition.
Details
We propose secure protocols to support tensor computations on the cloud. Homomophic encrytion differential privacy in Cloud Computing and SN.
Details
We apply deep learning and deep reinforcement learning to IoT tasks. Also, tensor structures are exploited and tensor operations are accelerated.
Details
We design efficient algorithms for big data and deep learning. Our algorithms are anomaly entries and effective algorithms for tensor time series prediction.
Details
Tensor for Intelligent IoT & ITS, Sensory big data analysis; Smartphone applications ;RF tomography (VR/AR); Intelligent transportation systems.
Details

Reach the top ending AI science!

A young team, professional in GPU tensor and Deep Learning technology, commits to creating top AI algorithms and solutions for corprates, labs, schools and communities.