• Diagram

Machine learning

• Supervised Learning
  • Classification
    • Medical Diagnosis
    • Image Classification
    • Fraud Detection
    • Optical Character Recognition (OCR)
  • Regression
    • Market Forecasting
    • Population Growth Prediction
    • Weather Prediction
• Unsupervised Learning
  • Clustering
    • Customer Segmentation
    • Recommendation Systems
    • Targeted Marketing
    • Data Mining
    • Anomaly Detection
    • Novelty Detection
  • Dimension Reduction
    • PCA (Principal Component Analysis)
    • SVD (Singular Value Decomposition)
    • Factor Analysis
    • NMF (Non-negative Matrix Factorization)
    • LDA (Linear Discriminant Analysis)
    • t-SNE
    • UMAP
    • LLE (Locally-Linear Embedding)
    • Isomap
    • Kernel PCA
    • Autoencoder
    • SOM (Self -Organizing Map)
    • GDA (Generalized Discriminant Analysis)
• Reinforcement Learning
  • Policy Optimization
  • Value-Based Methods
  • Actor-Critic Methods
  • Exploration-Exploitation Balancing

Deep learning

• Computer Vision (CV)
  • Image Classification
    • Object Recognition
    • Scene Understanding
  • Object Detection
    • Face Detection
    • Pedestrian Detection
  • Segmentation
    • Semantic Segmentation
    • Instance Segmentation
  • Image Captioning
    • Automatic Image Description
  • 3D Vision
    • Novel View Synthesis (NVS)
  • Video Processing
    • Action Recognition
    • Video Object Tracking
• Natural Language Processing (NLP)
  • KnowledgeIntensive Task
    • Open-Domain Question Answering (ODQA)
    • Fact Verification
    • Knowledge Graph Completion
  • Retrieval-Augmented Generation (RAG)
    • Cross-Modality Feature Alignment
    • Document Retrieval for QA
  • Prompt-Based Learning
    • In-Context Learning (ICL)
    • Chain of Thought (CoT) Reasoning
    • Instruction Tuning
    • Few-Shot Prompting
    • Prompt Engineering
    • Reinforcement Learning from Human Feedback (RLHF)
• Multimodal Learning
  • Vision-Language Learning
    • Visual Commonsense Reasoning (VCR)
    • Visual Question Answering (VQA)
    • Image-Text Matching
  • Cross-Modality Feature Alignment
    • Image-Text Embedding Alignment
    • Audio-Text Embedding
    • Multimodal RAG
    • Retrieval for Image and Text QA
    • Multimodal Search and Generation
• Audio Processing
  • Speech Recognition (STT)
    • Automatic Speech Recognition (ASR)
  • Speech Synthesis (TTS)
    • Text-to-Speech
    • Voice Cloning
  • Music Generation
    • AI Music Composition
  • Audio Separation
    • Speech Enhancement
    • Source Separation
  • Accompaniment Generation
  • Voice Conversion
    • Voice Imitation
    • Style Transfer in Speech
  • Talking Portrait Generation
    • Speech-Driven Facial Animation
• Graph Neural Networks (GNNs)
  • Node Classification
  • Link Prediction
  • Graph Embedding
  • Knowledge Graphs
  • Social Network Analysis
• Information Retrieval (IR)
  • Document Ranking
  • Semantic Search
  • Query Expansion
  • Vector-Based Search (e.g., Dense Retrieval)
  • Graph-Based Retrieval
  • Personalized Search
• Recommender Systems
  • Collaborative Filtering
  • Content-Based Filtering
  • Hybrid Methods
  • Context-Aware Recommendations
  • Personalized Recommendations
  • User Behavior Modeling
• Personalization
• Multitask Learning (MTL)
• Few Shot Learning
• Distributed Learning
• MLOps