Introduction to Deep Learning · HIT

Week 2   Part I · Foundations

Tensors & Data Representation

Tensor operations, shapes, broadcasting, devices; representing images, text, and tabular data as tensors.

Curated, free, canonical references for this week: a course or lecture, a book chapter, a video, and an authoritative blog post or official tutorial. Each opens in a new tab.

Course
Stanford CS231n: Python, NumPy and Array/Tensor Tutorial cs231n.github.io

Canonical Stanford notes on arrays, shapes, array math, and broadcasting.

Book
Dive into Deep Learning, 2.1 Data Manipulation d2l.ai

Hands-on PyTorch tensor creation, reshaping, indexing, broadcasting, and in-place ops.

Video
Andrej Karpathy: Neural Networks, Zero to Hero karpathy.ai

From-scratch lectures that build tensor and autograd objects in code with a PyTorch-like API.

Blog / Docs
PyTorch Official Tutorial: Tensors docs.pytorch.org

The official reference on tensor initialization, attributes (shape, dtype, device), and operations.

← Back to the Week 2 lab

PreviousWeek 1: Deep Learning Overview & ML-to-Network FramingNextWeek 3: MLPs & Backpropagation