๐ŸŽ“How I Study AIHISA
๐Ÿ“–Read
๐Ÿ“„Papers๐Ÿ“ฐBlogs๐ŸŽฌCourses
๐Ÿ’กLearn
๐Ÿ›ค๏ธPaths๐Ÿ“šTopics๐Ÿ’กConcepts๐ŸŽดShorts
๐ŸŽฏPractice
๐Ÿ“Daily Log๐ŸŽฏPrompts๐Ÿง Review
SearchSettings
How I Study AI - Learn AI Papers & Lectures the Easy Way

Concepts140

Groups

๐Ÿ“Linear Algebra15๐Ÿ“ˆCalculus & Differentiation10๐ŸŽฏOptimization14๐ŸŽฒProbability Theory12๐Ÿ“ŠStatistics for ML9๐Ÿ“กInformation Theory10๐Ÿ”บConvex Optimization7๐Ÿ”ขNumerical Methods6๐Ÿ•ธGraph Theory for Deep Learning6๐Ÿ”ตTopology for ML5๐ŸŒDifferential Geometry6โˆžMeasure Theory & Functional Analysis6๐ŸŽฐRandom Matrix Theory5๐ŸŒŠFourier Analysis & Signal Processing9๐ŸŽฐSampling & Monte Carlo Methods10๐Ÿง Deep Learning Theory12๐Ÿ›ก๏ธRegularization Theory11๐Ÿ‘๏ธAttention & Transformer Theory10๐ŸŽจGenerative Model Theory11๐Ÿ”ฎRepresentation Learning10๐ŸŽฎReinforcement Learning Mathematics9๐Ÿ”„Variational Methods8๐Ÿ“‰Loss Functions & Objectives10โฑ๏ธSequence & Temporal Models8๐Ÿ’ŽGeometric Deep Learning8

Category

๐Ÿ”ทAllโˆ‘Mathโš™๏ธAlgo๐Ÿ—‚๏ธDS๐Ÿ“šTheory

Level

AllBeginnerIntermediateAdvanced
โˆ‘MathIntermediate

Numerical Stability

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

#numerical stability#forward error#backward error+12
โˆ‘MathIntermediate

Floating Point Arithmetic

Floating-point numbers approximate real numbers using a fixed number of bits following the IEEE 754 standard.

#ieee 754
34567
#floating point
#machine epsilon
+10
โˆ‘MathAdvanced

KKT Conditions

KKT conditions generalize Lagrange multipliers to handle inequality constraints in constrained optimization problems.

#kkt conditions#lagrangian#complementary slackness+12
โˆ‘MathIntermediate

Convex Optimization Problems

A convex optimization problem minimizes a convex function over a convex set, guaranteeing that every local minimum is a global minimum.

#convex optimization#gradient descent#projected gradient+12
โˆ‘MathIntermediate

Convex Sets & Functions

A set is convex if every line segment between any two of its points lies entirely inside the set.

#convex set#convex function#convex hull+11
โˆ‘MathIntermediate

Confidence Intervals & Prediction Intervals

A confidence interval estimates a fixed but unknown parameter (like a population mean) with a range that would capture the true value in a long run of repeated samples.

#confidence interval#prediction interval#t distribution+12
โˆ‘MathIntermediate

Sufficient Statistics

A sufficient statistic compresses all information in the sample about a parameter into a lower-dimensional summary without losing inferential power.

#sufficient statistic#fisher neyman factorization#exponential family+12
โˆ‘MathIntermediate

Hypothesis Testing

Hypothesis testing is a decision-making process to evaluate claims about a population using sample data.

#hypothesis testing#null hypothesis#alternative hypothesis+12
โˆ‘MathIntermediate

Maximum A Posteriori (MAP) Estimation

Maximum A Posteriori (MAP) estimation chooses the parameter value with the highest posterior probability after seeing data.

#map estimation#posterior mode#bayesian inference+12
โˆ‘MathIntermediate

Maximum Likelihood Estimation (MLE)

Maximum Likelihood Estimation (MLE) chooses parameters that make the observed data most probable under a chosen model.

#maximum likelihood#log-likelihood#bernoulli mle+12
โˆ‘MathIntermediate

Exponential Family Distributions

Exponential family distributions express many common probability models in a single template p(x|ฮท) = h(x) exp(ฮท^T T(x) โˆ’ A(ฮท)).

#exponential family#natural parameter#sufficient statistics+12
โˆ‘MathIntermediate

Markov Chains

A Markov chain models a system that moves between states where the next step depends only on the current state, not the past.

#markov chain#transition matrix#stationary distribution+11