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

Concepts10

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

AllBeginnerIntermediate
๐Ÿ“šTheoryAdvanced

CTC Loss (Connectionist Temporal Classification)

CTC loss trains sequence models when you do not know the alignment between inputs (frames) and outputs (labels).

#ctc loss#connectionist temporal classification#forward backward+12
๐Ÿ“šTheoryAdvanced

Reinforcement Learning Theory

Reinforcement Learning (RL) studies how an agent learns to act in an environment to maximize long-term cumulative reward.

#reinforcement learning
Advanced
Filtering by:
#dynamic programming
#mdp
#bellman equation
+12
โš™๏ธAlgorithmAdvanced

DP on Broken Profile - Plug DP

Plug DP (DP on broken profile with plugs) sweeps a grid cell by cell while remembering how partial path segments cross the frontier as labeled โ€œplugs.โ€

#plug dp#broken profile#hamiltonian path+12
โˆ‘MathAdvanced

Partition Function

The partition function p(n) counts the number of ways to write n as a sum of positive integers where order does not matter.

#partition function#integer partitions#euler pentagonal theorem+11
โš™๏ธAlgorithmAdvanced

Broken Profile DP

Broken Profile DP is a dynamic programming technique that sweeps a grid one cell or one column at a time while encoding the boundary between processed and unprocessed cells as a compact state.

#broken profile dp#profile dp#plug dp+11
โš™๏ธAlgorithmAdvanced

Knuth Optimization

Knuth Optimization speeds up a class of interval dynamic programming (DP) from O(n^3) to O(n^2) by exploiting the monotonicity of optimal split points.

#knuth optimization#interval dp#quadrangle inequality+12
โš™๏ธAlgorithmAdvanced

Digit DP - Advanced States

Digit DP counts integers in a range by scanning digits from most significant to least while maintaining compact state information.

#digit dp#tight flag#leading zeros+12
โš™๏ธAlgorithmAdvanced

DP with Probability

DP with probability models how chance flows between states over time by repeatedly redistributing mass according to transition probabilities.

#markov chain#probability dp#absorbing state+12
๐Ÿ—‚๏ธData StructureAdvanced

Aho-Corasick - DP Applications

Ahoโ€“Corasick (AC) turns a set of forbidden patterns into a finite automaton that lets you process or generate strings while tracking whether any pattern appears.

#aho-corasick#automaton dp#forbidden substrings+12
๐Ÿ—‚๏ธData StructureAdvanced

Palindromic Tree (Eertree)

A Palindromic Tree (Eertree) stores every distinct palindromic substring of a string as a node and can be built online in linear time.

#palindromic tree#eertree#palindromic substrings+12