pytorch tensors and autograd

Tensor code is easier to read when shapes, broadcasting, and gradients are visible. This chapter uses plain Python stand-ins for PyTorch ideas so learners can inspect the grammar before meeting the library surface.

The exercises use small Python dictionaries and lists so every check can run in the browser. Real-world tools may be larger, but the review shape stays the same: input, decision, evidence, blocker, and next step.

By the end of the chapter, learners should be able to turn this topic into a concrete handoff instead of a vague model claim.