🎓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

Concepts356

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
📚TheoryIntermediate

Autoregressive Models

Autoregressive (AR) models represent a joint distribution by multiplying conditional probabilities in a fixed order, using the chain rule of probability.

#autoregressive#ar model#n-gram+11
∑MathIntermediate

Wasserstein Distance & Optimal Transport

Wasserstein distance (Earth Mover’s Distance) measures how much “work” is needed to transform one probability distribution into another by moving mass with minimal total cost.

#wasserstein distance
34567
Advanced
#earth mover's distance
#optimal transport
+12
📚TheoryIntermediate

Maximum Likelihood & Generative Models

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

#maximum likelihood#generative models#naive bayes+12
📚TheoryIntermediate

Mixture of Experts (MoE)

A Mixture of Experts (MoE) routes each input to a small subset of specialized models called experts, enabling conditional computation.

#mixture of experts#moe#gating network+12
📚TheoryIntermediate

Key-Value Memory Systems

Key-Value memory systems store information as pairs where keys are used to look up values by similarity rather than exact match.

#key-value memory#attention#scaled dot-product+12
∑MathIntermediate

Softmax & Temperature Scaling

Softmax turns arbitrary real-valued scores (logits) into probabilities that sum to one.

#softmax#temperature scaling#logits+12
∑MathIntermediate

Positional Encoding Mathematics

Sinusoidal positional encoding represents each token’s position using pairs of sine and cosine waves at exponentially spaced frequencies.

#positional encoding#sinusoidal#transformer+11
⚙️AlgorithmIntermediate

Efficient Attention Mechanisms

Standard softmax attention costs O(n²) in sequence length because every token compares with every other token.

#linear attention#efficient attention#kernel trick+12
📚TheoryIntermediate

Self-Attention as Graph Neural Network

Self-attention can be viewed as message passing on a fully connected graph where each token (node) sends a weighted message to every other token.

#self-attention#graph neural network#message passing+11
📚TheoryIntermediate

Multi-Head Attention

Multi-Head Attention runs several attention mechanisms in parallel so each head can focus on different relationships in the data.

#multi-head attention#scaled dot-product attention#transformer+12
📚TheoryIntermediate

Scaled Dot-Product Attention

Scaled dot-product attention scores how much each value V should contribute to a query by taking dot products with keys K, scaling by \(\sqrt{d_k}\), applying softmax, and forming a weighted sum.

#scaled dot-product attention#softmax#transformer+10
📚TheoryIntermediate

Stochastic Depth

Stochastic Depth randomly drops whole residual layers during training while keeping the full network at inference time.

#stochastic depth#resnet#residual block+12