Notes
  • AI
    • Bayesian
      • Complexity Theory
        • Constraint Satisfaction Problem
          • Cryptography
            • Data Science
              • Data
                • Data Visualization
                  • Database
                    • Dimensionality Reduction
                      • Machine Learning
                        • Classification
                          • Clustering
                            • Decision Tree
                              • Deep Learning
                                • Ensemble
                                  • Evaluation
                                    • Explainable AI
                                      • Feature Engineering
                                        • Natural Language Processing
                                          • LLM
                                            • Chain of Thought
                                            • Few-Shot Learning
                                            • In-Context Learning
                                            • Infilling
                                            • Input-Output Prompting
                                            • Knowledge Base LLM
                                            • Knowledge Distillation in Large Language Models
                                            • Large Language Model
                                            • Low-Rank Adaptation
                                            • Multi-Head Attention
                                            • One-Shot Learning
                                            • RAG Evaluation
                                            • Reinforcement Learning from Human Feedback
                                            • Self Consistency with CoT
                                            • Self-Attention
                                            • Self-Instruct
                                            • The Scaled Dot-Product Attention
                                            • Thoughts on RAG
                                            • Transformer Architecture
                                            • Transformer Decoder
                                            • Transformer Encoder
                                            • Tree of Thoughts
                                            • Zero-Shot Learning
                                          • Bag Of Words
                                          • Bidirectional Recurrent Neural Network
                                          • Branching Factor
                                          • Common Bag Of Words
                                          • Embedding
                                          • Information Retrieval
                                          • Integer Encoding
                                          • Inverse Document Frequency
                                          • Language Identification
                                          • Masked Language Model
                                          • N Gram Model
                                          • Named Entity Recognition
                                          • Natural Language
                                          • Natural Language Generation
                                          • Natural Language Processing
                                          • Natural Language Semantics
                                          • Natural Language Understanding
                                          • NLP Abstraction
                                          • NLP Ambiguity
                                          • NLP Composition
                                          • NLP Reading
                                          • NLP Truth Conditions
                                          • Out Of Vocabulary
                                          • POS Tagging
                                          • Pragmatic Analysis
                                          • Spam Detection
                                          • Statistical Language Model
                                          • Terminology
                                          • Text Classification
                                          • TF-IDF
                                          • TF-IDF Word Embedding
                                          • Tokenization
                                          • Vector Database
                                          • Vocabulary
                                          • Word Embedding
                                          • Word Frequency Vector
                                        • Neural Networks
                                          • Outlier
                                            • Random Forest
                                              • SVM
                                                • Time Series
                                                  • Attribute Selection Method
                                                  • Automatic Concept-Hierarchy Generation
                                                  • Basis Function Expansion
                                                  • Classification
                                                  • Complexity vs. Generalization Error
                                                  • Custom Loss Function for Linear Regression in Python
                                                  • Decision Boundary
                                                  • Decision List
                                                  • Double Descent
                                                  • Empirical Loss
                                                  • Forest-RC
                                                  • Generalization Loss
                                                  • Grid Search
                                                  • Heuristic Search
                                                  • Kernel Trick
                                                  • Learning Curve
                                                  • Lineare Regression per Hand ausrechnen
                                                  • Loss Function
                                                  • Machine Learning
                                                  • Majority Voting
                                                  • Maximum Margin Separator
                                                  • ML Pipeline
                                                  • Model Deployment
                                                  • Model Selection
                                                  • Model Training
                                                  • Nearest Neighbors Algorithm
                                                  • Nested Cross Validation
                                                  • Norm Loss
                                                  • Normalization
                                                  • Normalization by decimal scaling
                                                  • Numerosity Reduction
                                                  • One-Hot-Encoding
                                                  • Online Learning
                                                  • Optimization of a Linear Model
                                                  • Overfitting
                                                  • Overfitting and Underfitting
                                                  • Performance Monitoring
                                                  • Presidio
                                                  • Quantile Regression
                                                  • Randomized Search
                                                  • Reconstruction Loss
                                                  • Regression
                                                  • Reinforcement Learning
                                                  • Semi-Supervised Learning
                                                  • Sequence To Sequence Model
                                                  • Singular Value Decomposition
                                                  • Sparsity
                                                  • Stratified K-Fold Corss Validation
                                                  • Stratified Sampling
                                                  • Supervised Learning
                                                  • Support Vector Machine
                                                  • Train Validation Split
                                                  • U-shaped Learning
                                                  • Underfitting
                                                  • Unsupervised Learning
                                                • Bias
                                                • Binning
                                                • Contingency table for binary data
                                                • Correlation Analysis
                                                • Cross-Industry Standard Process for Data Mining
                                                • Data Cleaning
                                                • Data Compression
                                                • Data Discretization
                                                • Data Ingestion
                                                • Data Integration
                                                • Data Mining in the ML and Statistics Community
                                                • Data Preparation
                                                • Data Profiling
                                                • Data Quality
                                                • Data Reduction
                                                • Data Segregation
                                                • Data Transformation
                                                • Gaussian Mixture Expectation Maximization
                                                • Gewichteter Mittelwert
                                                • Histogram Analysis
                                                • Log-Likelihood
                                                • Metriken
                                                • Min-Max Normalization
                                                • Sample
                                                • Sampling
                                                • Simple Matching Coefficient
                                              • Decision Theory
                                                • Distances
                                                  • Fourier Transform
                                                    • Frequent Item
                                                      • Graph
                                                        • Information Theory
                                                          • Knowledge Representation
                                                            • Logic
                                                              • Markov
                                                                • Mathematics
                                                                  • media
                                                                    • Optimization
                                                                      • Other
                                                                        • Pattern Recognition
                                                                          • Search
                                                                            • Sort
                                                                              • Statistics
                                                                                • INDEX
                                                                                • MOC - Introduction to Statistics and Statistical Programming
                                                                                • MOC - Stochastische Modellbildung
                                                                                Navigation

                                                                                • All tags
                                                                                • #Algorithmus(48)
                                                                                • #Algorithmus, codesnippet, code, js, Python(1)
                                                                                • #E(1)
                                                                                • #Gemischt-ganzzahlige(1)
                                                                                • #MOC(8)
                                                                                • #P-hard(1)
                                                                                • #bachelor(1)
                                                                                • #code(1)
                                                                                • #codesnippet, code, js, programmingassignment(5)
                                                                                • #codesnippet, code, programmingassignment, js(1)
                                                                                • #confirm(1)
                                                                                • #data(1)
                                                                                • #datascience(1)
                                                                                • #excalidraw(11)
                                                                                • #infovislearn(2)
                                                                                • #keep(2)
                                                                                • #lnsexam(1)
                                                                                • #note(2)
                                                                                • #note, datascience, keep(1)
                                                                                • #paper(1)
                                                                                • #programmingassignment(4)
                                                                                • #question(4)
                                                                                • #todo(21)
                                                                                • #uebung(1)

                                                                                • Transformer Encoder
                                                                                • Attention Is All You Need
                                                                                • Attention

                                                                                • The Scaled Dot-Product Attention

                                                                                Local graph
                                                                                1. Data Science /
                                                                                2. Machine Learning /
                                                                                3. Natural Language Processing /
                                                                                4. LLM /
                                                                                5. Multi-Head Attention

                                                                                Multi-Head Attention

                                                                                Uses The Scaled Dot-Product Attention in multiple layers.

                                                                                Multi-Head Attention.canvas