Prerequisites & knowledge map
Everything below is a concept Computer Vision leans on that ISN'T taught inside the course itself — not the whole of another course, just the specific skills.
Calculus III — Multivariable Calculus
-
required
-
required
-
required
-
required
-
required
-
required
-
required
-
required
-
required
-
required
-
required
-
required
-
required
-
required
-
required
-
required
-
required
-
required
-
required
-
required
-
required
-
required
-
required
-
required
-
required
-
required
-
required
-
required
-
required
-
required
-
required
-
required
-
required
-
required
-
required
-
required
-
required
Deep Learning / Neural Networks
-
required
-
required
-
required
-
required
-
required
-
required
-
required
-
required
-
required
-
required
-
required
-
required
-
required
-
Matrix multiplication
A layer's forward pass is a matrix-vector product plus a bias.
required -
required
-
required
-
required
-
required
-
required
-
required
-
required
-
required
-
required
-
required
-
required
-
required
-
required
-
required
-
required
-
required
-
required
-
required
-
required
-
required
-
required
-
required
-
required
-
required
-
required
-
required
-
required
-
required
-
required
-
Backpropagation
deep-learning ch.10 derives backpropagation via the chain rule in full; this course's own quizzes only require the working-depth version taught locally.
recommended -
Forward pass of a single neuron
deep-learning ch.02/ch.04 derive the same forward pass in full; this course's own quizzes only require the working-depth version taught locally.
recommended -
Gradient descent: the update rule
deep-learning ch.09-10 derive the update rule and backpropagation this training loop runs; this course's own quizzes only require the working-depth version taught locally.
recommended -
Multiple channels and 1x1 convolution
deep-learning ch.15 derives multi-channel and 1x1 convolution mechanics in full; this course's own quizzes only require the working-depth version taught locally.
recommended -
Self-attention
deep-learning ch.17 derives self-attention in full; this course's own quizzes only require the working-depth version taught locally.
recommended -
The Transformer architecture
deep-learning ch.18 derives the Transformer encoder these image and text towers are typically built from, in full; this course's own quizzes only require the working-depth version taught locally.
recommended -
The Vision Transformer
deep-learning ch.19 derives the Vision Transformer's patch-plus- attention mechanics in full; this course's own quizzes only require the survey-level version taught locally.
recommended
College Algebra
-
required
-
required
-
required
-
required
-
required
-
required
-
required
-
required
-
required
-
required
-
required
-
required
-
required
-
required
-
required
-
required
-
required
-
required
-
required
-
required
-
required
-
required
-
required
-
required
Linear Algebra — Vectors, Matrices, and the Geometry of Data
-
required
-
required
-
required
-
required
-
required
-
required
-
required
-
required
-
required
-
required
-
required
-
required
-
required
-
required
-
required
-
required
-
required
-
required
-
required
-
required
-
required
-
required
-
required
-
required
-
required
-
required
-
required
-
required
-
required
-
required
-
required
-
required
-
required
-
required
-
required
-
required
-
required
-
required
-
required
-
required
-
required
-
required
-
required
-
required
-
required
-
required
-
required
-
required
-
required
-
required
-
required
-
required
-
required
-
required
-
required
-
required
-
required
-
required
-
required
-
required
-
required
-
required
-
required
-
required
-
required
Digital Signal Processing
-
required
-
required
-
required
-
required
Digital Image Processing
-
required
-
required
-
required
-
required
-
required
-
required
-
required
-
required
-
required
-
required
-
required
-
required
-
required
-
required
-
required
-
required
-
required
-
required
-
required
Calculus I — Differential & Integral Calculus
-
required
-
required
-
required
-
required
-
required
-
required
-
required
-
required
-
required
-
required
-
required
-
required
Advanced Linear Algebra
-
required
-
required
-
required
-
required
-
required
-
required
-
required
-
required
Fourier Analysis
-
Eigenvalues and the characteristic equation
Cross-domain (linear-algebra): the DFT matrix's eigenstructure, needed later for circulant diagonalization, presumes eigenvalues/characteristic-equation machinery.
required -
required
-
required
-
required
-
required
-
required
-
required
-
required
-
required
-
required
-
required
-
required
-
The complex form of the Fourier series
Cross-domain (sequences-and-series): the Fourier transform is derived by letting a Fourier series' period grow without bound, starting from its complex-exponential form.
required
Calculus II — Integral Calculus & Infinite Series
-
required
Advanced Multivariable Calculus
-
required
-
required
-
required
-
required