Artificial Intelligence & Data Science is coming soon

We're still writing and reviewing the notes for every subject, and we'll open it when every subject is ready. Meanwhile you can practise aptitude, ask Aria about any subject, or see the branches that are ready.

Artificial Intelligence & Data Science

Fundamental Edge AI

Heterogeneous systems, hardware abstraction and power, neural hardware acceleration and vision pipelines, specialised accelerators.

Interview questions
Notes for Fundamental Edge AI are being written and reviewed. Until they're up, Aria teaches every topic — ask for any part of the syllabus, with worked numericals.

Coming next in Fundamental Edge AI

  1. Heterogeneous computing systems· notes coming
  2. System-on-chip architecture· notes coming
  3. Inter-processor communication· notes coming
  4. Shared memory and remote procedure calls· notes coming
  5. Hardware abstraction layers and memory-mapped I/O· notes coming
  6. Power domains and sleep states· notes coming
  7. Power-aware scheduling· notes coming
  8. General-purpose versus task-specific compute· notes coming
  9. SIMD and vectorisation· notes coming
  10. The vision processing chain: MIPI-CSI and ISPs· notes coming
  11. Zero-copy data paths· notes coming
  12. DSPs and NPUs· notes coming
  13. Offloading work from the CPU· notes coming
  14. Real-time image preprocessing on the edge· notes coming
  15. Model compression for the edge· notes coming
  16. Quantisation: FP32 to INT8· notes coming
  17. Scale and zero-point mapping· notes coming
  18. Accuracy loss from quantisation· notes coming
  19. Training versus inference bottlenecks· notes coming
  20. CPUs, GPUs, TPUs and NPUs· notes coming
  21. CUDA, cuDNN and TensorRT· notes coming
  22. Accelerated AI frameworks: TensorFlow, PyTorch and ONNX· notes coming
  23. Knowledge distillation· notes coming
  24. ONNX conversion and optimisation pipelines· notes coming
  25. GPU inference with TensorRT· notes coming
  26. Edge AI devices: Jetson, Coral and RKNN· notes coming
  27. Accelerated AI applications· notes coming
  28. Distributed training with Horovod and PyTorch DDP· notes coming
  29. Real-time video analytics· notes coming
  30. Edge-cloud collaborative AI· notes coming
  31. Power, latency and deployment trade-offs· notes coming