Skip to content

Latest commit

 

History

History
30 lines (21 loc) · 1.21 KB

File metadata and controls

30 lines (21 loc) · 1.21 KB

Tutorial

This is the recommended learning path for VTL. It starts with tensors, then builds toward autograd, neural networks, optimizers, and GPU-backed examples.

Tensor fundamentals

  1. First Steps — creation, indexing, shapes.
  2. Slicing — views and sub-tensors.
  3. Broadcasting — shape-compatible operations.
  4. Map and Reduce — element-wise transforms and reductions.
  5. Reductions — argmax, argmin, cumulative operations.

Linear algebra

  1. Matrix and Vector operations — VSL-backed LA.
  2. Advanced Linear Algebra — QR, LU, Cholesky, pinv.

Machine learning

  1. Automatic DifferentiationVariable, gates, backprop.
  2. Neural Networks — layers, losses, Sequential.
  3. Optimizers — SGD, Adam, AdamW, schedulers.

Next