Learning Resources

On this page and subsequent sub-pages you will find a number of engineering sourced resources to help you with your artificial intelligence development using the Qualcomm® Neural Processing SDK. The topics included are as follows:

Artificial Intelligence, Machine Learning, Android and the Qualcomm Neural Processing SDK for AI

  • Types of machine learning
  • Data collection and pre-processing techniques
  • Introduction to the Qualcomm Neural Processing SDK for AI and its components
  • Benchmarking the Qualcomm Neural Processing SDK for AI vs. TensorFlow on Android
  • Bringing up Caffe and TensorFlow frameworks on the Qualcomm Neural Processing SDK for AI
  • Setting up the project using the Android Studio IDE and required SDKs

Developing Apps with the Qualcomm Neural Processing SDK for AI

  • Working with Machine Learning Models in the Qualcomm Neural Processing SDK for AI
  • Tuning and Optimizing Machine Learning Models
  • Developing an Android App with a Snapdragon® HDK
  • Streaming Live Frames to a Machine Learning Model with the Qualcomm Neural Processing SDK for AI

Training and testing ML models

  • Functional testing of Machine Learning Models
  • Training, Testing and Evaluating Machine Learning Models

Image Segmentation using DeepLab-v3 and Qualcomm Neural Processing SDK for AI

  • Classification, Object Detection and Image Segmentation
  • DeepLab-v3 using Qualcomm Neural Processing SDK for AI on Ubuntu
  • DeepLab-v3 using Qualcomm Neural Processing SDK for AI on Android

CNN Architectures

  • Deep Learning and Convolutional Neural Networks for Computer Vision
  • Computer Vision CNN Architectures
  • Advanced Computer Vision CNN Architectures

Vision-based AI Use Cases

  • Real-time Facial Detection and Validation
  • Functional Testing of Vision-based ML Applications
  • Facial Keypoint Detection
  • Facial Expression Recognition — Part 1: Solution Pipeline on Ubuntu
  • Facial Expression Recognition — Part 2: Solution Pipeline on Android