Accelerate your machine learning networks using TVM and the Adreno OpenCL ML APIs on Adreno GPUs - Qualcomm Developer Network
APIs for Accelerating Vision and Inferencing: An Overview of Options and Trade-offs
What is ONNX? - AI@Edge Community
SoyNet, a Fast and Affordable Solution for Inference Optimization - Edge AI and Vision Alliance
GitHub - chriskinzel/OpenCL-NeuralNetwork: Simple MLP Neural Network example using OpenCL kernels that can run on the CPU or GPU, supports Elman and Jordan recurrent networks