🎓How I Study AIHISA
📖Read
📄Papers📰Blogs🎬Courses
💡Learn
🛤️Paths📚Topics💡Concepts🎴Shorts
🎯Practice
📝Daily Log🎯Prompts🧠Review
SearchSettings
How I Study AI - Learn AI Papers & Lectures the Easy Way

Concepts16

Groups

📐Linear Algebra15📈Calculus & Differentiation10🎯Optimization14🎲Probability Theory12📊Statistics for ML9📡Information Theory10🔺Convex Optimization7🔢Numerical Methods6🕸Graph Theory for Deep Learning6🔵Topology for ML5🌐Differential Geometry6∞Measure Theory & Functional Analysis6🎰Random Matrix Theory5🌊Fourier Analysis & Signal Processing9🎰Sampling & Monte Carlo Methods10🧠Deep Learning Theory12🛡️Regularization Theory11👁️Attention & Transformer Theory10🎨Generative Model Theory11🔮Representation Learning10🎮Reinforcement Learning Mathematics9🔄Variational Methods8📉Loss Functions & Objectives10⏱️Sequence & Temporal Models8💎Geometric Deep Learning8

Category

🔷All∑Math⚙️Algo🗂️DS📚Theory

Level

AllBeginnerIntermediate
∑MathIntermediate

Pseudoinverse (Moore-Penrose)

The Moore–Penrose pseudoinverse generalizes matrix inversion to rectangular or singular matrices and is denoted A⁺.

#pseudoinverse#moore-penrose#least squares+12
📚TheoryIntermediate

Spectral Regularization

Spectral regularization controls how much a weight matrix can stretch inputs by constraining its largest singular value (spectral norm).

#spectral regularization
12
Advanced
Filtering by:
#condition number
#spectral norm
#power iteration
+11
📚TheoryIntermediate

Double Descent Phenomenon

Double descent describes how test error first follows the classic U-shape with increasing model complexity, spikes near the interpolation threshold, and then drops again in the highly overparameterized regime.

#double descent#interpolation threshold#overparameterization+12
⚙️AlgorithmIntermediate

Matrix Factorizations (Numerical)

Matrix factorizations rewrite a matrix into simpler building blocks (triangular or orthogonal) that make solving and analyzing linear systems much easier.

#lu decomposition#qr factorization#householder reflections+12
⚙️AlgorithmIntermediate

Iterative Methods for Linear Systems

The Conjugate Gradient (CG) method solves large, sparse, symmetric positive definite (SPD) linear systems Ax = b using only matrix–vector products and dot products.

#conjugate gradient#iterative solver#krylov subspace+12
∑MathIntermediate

Numerical Stability

Numerical stability measures how much rounding and tiny input changes can distort an algorithm’s output on real computers using floating-point arithmetic.

#numerical stability#forward error#backward error+12
⚙️AlgorithmIntermediate

Gradient Descent

Gradient descent is a simple, repeatable way to move downhill on a loss surface by stepping in the opposite direction of the gradient.

#gradient descent#batch gradient descent#learning rate+12
∑MathIntermediate

Implicit Differentiation & Implicit Function Theorem

Implicit differentiation lets you find slopes and higher derivatives even when y is given indirectly by an equation F(x,y)=0.

#implicit differentiation#implicit function theorem#jacobian+12
∑MathIntermediate

Jacobian Matrix

The Jacobian matrix collects all first-order partial derivatives of a vector-valued function, describing how small input changes linearly affect each output component.

#jacobian matrix#partial derivatives#multivariable calculus+11
∑MathIntermediate

Matrix Norms & Condition Numbers

Matrix norms measure the size of a matrix in different but related ways, with Frobenius treating entries like a big vector, spectral measuring the strongest stretch, and nuclear summing all singular values.

#matrix norm#spectral norm#frobenius norm+12
∑MathIntermediate

Positive Definite Matrices

A real symmetric matrix A is positive definite if and only if x^T A x > 0 for every nonzero vector x, and positive semidefinite if x^T A x ≥ 0.

#positive definite#positive semidefinite#cholesky decomposition+11
∑MathIntermediate

Systems of Linear Equations

A system of linear equations asks for numbers that make several linear relationships true at the same time, which we compactly write as Ax = b.

#systems of linear equations#gaussian elimination#row echelon form+12