api: YAML JSON TOON Database
version: 1.0.0
format: toon
category:
  id: 391
  slug: ai-ml-terms
  name: AI & ML Terms
  description: Key terminology in artificial intelligence and machine learning.
  icon: cpu
  created_at: 1783090350
  dataset_count: 12
  topic:
    overview: "AI and machine-learning reference data covers the vocabulary around large language models and the methods under them: how models are structured (architectures, attention), how they are trained (optimizers, training algorithms, regularization, transfer learning), how they are evaluated (metrics) and the concepts that shape their use (tokens, context windows, sampling, retrieval, fine-tuning) and their risks (ethics, interpretability, hallucination). The field moves quickly, so definitions of broad terms are stable while specific model names, sizes and benchmarks age within months. An entry should be read as the concept, not as a snapshot of the state of the art."
    key_ideas[7]{term,meaning}:
      Token,"The unit of text a language model reads and writes, often a word fragment. Costs and context limits are measured in tokens, not characters."
      Context window,"The maximum number of tokens a model can consider at once, covering the prompt and the response together."
      Training vs inference,Training adjusts model parameters from data; inference uses the trained model to produce outputs. Their costs and tools differ.
      Overfitting and regularization,Overfitting is memorizing training data at the expense of generalization; regularization techniques reduce it.
      Embedding,"A vector representation of text, images or other data in which similar items are close together."
      Retrieval-augmented generation,Supplying a model with retrieved documents at query time so answers can use current or private information.
      Evaluation metric,"A number that summarizes performance on a task. Different metrics reward different behavior, so the choice shapes what gets optimized."
    pitfalls[4]: "Treating model output as verified fact. Language models can produce fluent, wrong statements (hallucination).",Choosing a metric that does not match the cost of errors; accuracy is misleading on imbalanced data.,"Quoting model sizes, context lengths or benchmark scores as current without a date.","Confusing correlation in training data with understanding, or assuming interpretability methods explain a model exactly."
    agent_tips[3]: "Distinguish a concept (attention) from a named product or model, and date any claim about a specific model.",Ground factual answers in retrieved sources and cite them; verify numbers against reference data before stating them.,"When explaining a metric, state its formula and what kind of error it ignores."
    start_with[2]: llm-glossary,ml-evaluation-metrics
datasets[12]{id,slug,title,description,tags,view_count,created_at,entry_count,summary}:
  2728,ai-ethics-interpretability,AI Ethics & Interpretability,"Key concepts in responsible AI: fairness, bias detection, explainability (XAI), model cards, and regulatory compliance (EU AI Act).","ai ethics,interpretability,xai,fairness,explainability,regulation,ai-act",46,1777673262,13,"Principles and tools for responsible AI: fairness, transparency, accountability, privacy and safety, with metrics, sources of bias and mitigations for each, key concepts such as Shapley values and counterfactuals, major regulations, and a practical checklist."
  2733,attention-mechanisms,Attention Mechanisms in Deep Learning,"Attention architectures: self-attention, multi-head attention, cross-attention, scaled dot-product, sparse attention, and efficient attention variants (Linformer, Performer, FlashAttention).","attention,self-attention,transformer,multi-head,cross-attention,sparse-attention,flash-attention",60,1778695229,8,"Attention mechanisms in deep learning with formula, complexity, description, uses and notes: scaled dot-product, multi-head, cross-attention, causal masking, sparse attention, FlashAttention and linear attention variants."
  2779,deep-learning-optimizers,Deep Learning Optimizers,"Optimization algorithms for training neural networks: SGD, Momentum, NAG, Adam, AdamW, RMSprop, AdaGrad, and learning rate scheduling strategies.","deep-learning,optimizers,sgd,adam,adamw,rmsprop,learning-rate,momentum",55,1778695229,8,"Optimization algorithms for training neural networks with year, update rule, pros, cons and best uses: SGD, momentum, Nesterov, AdaGrad, RMSprop, Adam, AdamW and LAMB/LARS."
  2837,llm-evaluation-failure-modes,LLM Evaluation Failure Modes,"Evaluation mistakes that inflate confidence in language-model and agent changes, with corrective checks.","ai-ml-terms,llm evaluation failure modes,reference,engineering",61,1791798640,10,"Evaluation mistakes that inflate confidence in language-model and agent changes, with corrective checks. Each row includes a practical application and a failure to check before using it."
  2838,llm-glossary,Large Language Model Glossary,"Key terms and concepts in LLM technology: tokens, context windows, temperature, RAG, fine-tuning, quantization, KV cache, and emergence.","llm,ai,glossary,nlp",56,1777673262,41,"A glossary of large-language-model terms with precise definitions: tokens, context windows, temperature, retrieval-augmented generation, fine-tuning, quantization, KV cache and emergence, extended with embeddings, prompts, hallucination, sampling methods, RLHF, tool use, agents, mixture of experts, distillation, LoRA, perplexity and prompt injection."
  2849,ml-evaluation-metrics,Machine Learning Evaluation Metrics,"Common ML evaluation metrics: Accuracy, Precision, Recall, F1 Score, ROC-AUC, MAE, MSE, and R-squared with formulas and best-use scenarios.","ml,evaluation,metrics,data science",48,1777673262,21,"Evaluation metrics for machine-learning models with type, formula, best use and range: accuracy, precision, recall, F1, ROC-AUC, MAE, MSE and R-squared, extended with specificity, log loss, RMSE, Matthews correlation, IoU, perplexity, BLEU, nDCG and Cohen's kappa."
  2850,ml-model-architectures,Machine Learning Model Architectures,"Overview of major ML model families: feedforward neural networks, CNNs, RNNs/LSTMs, Transformers, GANs, and when to use each.","machine-learning,neural-networks,architectures,cnn,rnn,transformer,gan",54,1777673262,7,"Machine-learning model architectures with type, structure, layers, uses, pros, cons and notes: feedforward networks, CNNs, RNNs, LSTMs, transformers, GANs and autoencoders, with a selection guide by data type."
  2851,ml-training-algorithms,Machine Learning Training Algorithms,"Core ML training algorithms: gradient descent variants, backpropagation, optimization methods (SGD, Adam, RMSprop), and when to use each.","machine-learning,training,optimization,gradient-descent,backpropagation",56,1777673262,13,"Training algorithms for machine learning, including gradient descent in its batch, stochastic and mini-batch forms, momentum, RMSprop, Adam, backpropagation and learning-rate schedules, each with type, mechanism, update rule, pros, cons and when to use it, plus practical tips."
  2860,neural-network-types,Neural Network Architectures,"Common neural network architectures: CNN, RNN, LSTM, Transformer, GAN, and Diffusion models with their primary use cases and key features.","neural networks,deep learning,ai,architecture",49,1777673262,12,"The main neural-network architectures with name, full name, primary use and key feature: CNN, RNN, LSTM, transformer, GAN and diffusion models, extended with the multilayer perceptron, autoencoder, graph neural network, state-space model, mixture of experts and U-Net."
  2882,regularization-techniques,Regularization Techniques in Machine Learning,"Techniques to prevent overfitting: L1/L2 regularization, dropout, batch normalization, early stopping, data augmentation, label smoothing, and mixup.","regularization,overfitting,dropout,batch-norm,l1,l2,early-stopping,data-augmentation,label-smoothing",59,1778695229,8,"Regularization techniques that reduce overfitting, with formula, effect, uses and notes: L1 and L2 penalties, dropout, batch normalization, early stopping, data augmentation, label smoothing and mixup or CutMix."
  2881,rag-retrieval-metrics,Retrieval Evaluation Metrics for RAG,Retrieval metrics and diagnostic slices for evaluating the evidence selected before language-model generation.,"ai-ml-terms,rag retrieval metrics,reference,engineering",56,1791798640,10,Retrieval metrics and diagnostic slices for evaluating the evidence selected before language-model generation. Each row includes a practical application and a failure to check before using it.
  2915,transfer-learning,Transfer Learning and Fine-Tuning,"Transfer learning strategies: feature extraction, fine-tuning, domain adaptation, multi-task learning, prompt tuning, LoRA, and pretraining paradigms.","transfer-learning,fine-tuning,feature-extraction,domain-adaptation,lora,prompt-tuning,pretraining",46,1778695229,8,"Strategies for adapting pretrained models: feature extraction, full fine-tuning, layer-wise learning-rate decay, progressive unfreezing, domain adaptation, LoRA, prompt and prefix tuning and multi-task learning, with approach, when to use, pros, cons and examples."