AI tools

Planted 02025-07-05

AI Classical Machine Learning Linear Regression Predicting continuous values with linear relationships Logistic Regression Binary and...

AI

Classical Machine Learning

• Linear Regression - Predicting continuous values with linear relationships
• Logistic Regression - Binary and multiclass classification
• Decision Trees - Interpretable models for classification and regression
• Random Forest - Ensemble method combining multiple decision trees
• Support Vector Machines (SVM) - Classification and regression with kernel methods
• K-Means Clustering - Unsupervised grouping of data points
• K-Nearest Neighbors (KNN) - Instance-based learning for classification/regression
• Naive Bayes - Probabilistic classifier based on Bayes’ theorem
• Gradient Boosting (XGBoost, LightGBM, CatBoost) - Ensemble methods for structured data

Deep Learning Architectures

• Convolutional Neural Networks (CNNs) - Image recognition and computer vision
• Recurrent Neural Networks (RNNs/LSTMs/GRUs) - Sequential data processing
• Transformers - Attention-based models for NLP and beyond
• Autoencoders - Unsupervised learning for dimensionality reduction
• Generative Adversarial Networks (GANs) - Generating synthetic data
• Variational Autoencoders (VAEs) - Probabilistic generative models

Natural Language Processing

• Text Classification - Categorizing documents, sentiment analysis, spam detection
• Named Entity Recognition (NER) - Identifying people, places, organizations in text
• Part-of-Speech Tagging - Grammatical role identification
• Text Summarization - Extractive and abstractive summarization
• Machine Translation - Converting text between languages
• Question Answering - Systems that answer questions based on context
• Text Generation - Creating human-like text from prompts
• Sentiment Analysis - Determining emotional tone in text
• Topic Modeling (LDA, NMF) - Discovering themes in document collections

Computer Vision

• Image Classification - Categorizing images into predefined classes
• Object Detection (YOLO, R-CNN) - Locating and identifying objects in images
• Semantic Segmentation - Pixel-level classification in images
• Face Recognition - Identifying individuals from facial features
• Optical Character Recognition (OCR) - Converting images to text
• Image Generation (Stable Diffusion, DALL-E) - Creating images from text prompts
• Style Transfer - Applying artistic styles to images

Time Series Analysis

• ARIMA - Autoregressive integrated moving average for forecasting
• Prophet - Facebook’s time series forecasting tool
• LSTM Networks - Deep learning for sequential prediction
• Exponential Smoothing - Simple forecasting methods
• Seasonal Decomposition - Breaking down time series components

Recommendation Systems

• Collaborative Filtering - User-item interaction based recommendations
• Content-Based Filtering - Item feature based recommendations
• Matrix Factorization - Dimensionality reduction for recommendations
• Deep Learning Recommenders - Neural approaches to recommendation

Large Language Model Applications

• Few-Shot Learning - Learning from minimal examples
• In-Context Learning - Learning within the prompt context
• Chain-of-Thought Prompting - Step-by-step reasoning
• Retrieval-Augmented Generation (RAG) - Combining retrieval with generation
• Fine-tuning - Adapting pre-trained models to specific tasks
• Parameter-Efficient Fine-tuning (LoRA, Adapters) - Efficient model adaptation
• Prompt Engineering - Crafting effective prompts for LLMs
• Instruction Following - Training models to follow human instructions

Clustering and Dimensionality Reduction

• Principal Component Analysis (PCA) - Linear dimensionality reduction
• t-SNE - Nonlinear dimensionality reduction for visualization
• UMAP - Uniform manifold approximation and projection
• DBSCAN - Density-based clustering
• Hierarchical Clustering - Tree-based clustering approaches

Reinforcement Learning

• Q-Learning - Model-free reinforcement learning
• Policy Gradient Methods - Direct policy optimization
• Actor-Critic Methods - Combining value and policy methods
• Deep Q-Networks (DQN) - Deep learning for Q-learning
• Proximal Policy Optimization (PPO) - Stable policy gradient method

Reference

• Series:Machine Learning
• Series: Artificial Intelligence
• Category:Machine learning algorithms
• MLU-EXPLAIN
• scikit-learn
• Google Developers: Machine Learning
• Andrew Ng: Courses
• CS229: Machine Learning
• Fast.ai: Practical Deep Learning
• CS224N: Natural Language Processing with Deep Learning
• CS231n: Deep Learning for Computer Vision
• Rob J Hyndman and George Athanasopoulos, Forecasting: Principles and Practice
• Learn Machine Learning Resources
• LLM Embeddings Explained: A Visual and Intuitive Guide
• BERT Neural Network explained
• How to Scale Your Model