Curriculum Learning
Definition
Curriculum learning mimics human education by presenting training data in a structured β¦
3
Right to be Forgotten
Definition
The right to be forgotten enables users to demand the removal of their personal β¦
XLM-RoBERTa
Definition
XLM-RoBERTa (Cross-lingual Language Model RoBERTa) is a large-scale multilingual model β¦
Winner-take-all in action selection
Definition
Winner-take-all (WTA) is a competitive process used in neural networks and reinforcement β¦
WordPiece
Definition
WordPiece is a tokenization method widely used in natural language processing models like β¦
Web intelligence
Definition
Web intelligence involves using data mining, machine learning, and semantic technologies β¦
Webhook
Definition
A webhook is a mechanism for one service to provide real-time information to another β¦
Voice Activity Detection
Definition
VAD algorithms analyze audio streams in real-time to distinguish between active speech β¦
Watermarking
Definition
As generative AI produces increasing amounts of synthetic media, watermarking serves as a β¦
Unsloth
Definition
Unsloth is a specialized tool designed to optimize the fine-tuning and deployment of β¦
Underfitting
Definition
Underfitting occurs when a statistical model or machine learning algorithm cannot β¦
Unified Model
Definition
A unified model refers to an artificial intelligence system capable of performing various β¦
Tracing
Definition
In the context of AI engineering, tracing involves capturing detailed logs of how data β¦
Token maxxing
Definition
Token maxxing involves carefully crafting inputs to utilize the full capacity of a β¦
Toxicity Detection
Definition
Toxicity detection employs natural language processing techniques to analyze text inputs β¦
Throughput
Definition
In AI engineering, throughput is a critical performance metric indicating system β¦
Time series
Definition
Time series data consists of observations recorded sequentially over time intervals. In β¦
TFLite
Definition
TensorFlow Lite is an open-source framework designed to deploy machine learning models on β¦
Text Embeddings Inference
Definition
Text Embeddings Inference refers to the deployment and optimization of models that β¦
TensorFlow Hub
Definition
TensorFlow Hub is a platform for publishing and reusing machine learning components. It β¦
Text Classification
Definition
Text classification is a supervised learning task where algorithms assign predefined β¦
Symbolic artificial intelligence
Definition
Symbolic artificial intelligence, often called GOFAI (Good Old-Fashioned AI), relies on β¦
T2I
Definition
Text-to-Image (T2I) generation involves using deep learning models, such as diffusion β¦
Superintelligence ban
Definition
This concept refers to the debate and potential policy regarding the restriction or β¦
Surrogate model
Definition
In machine learning and optimization, a surrogate model serves as a proxy for a target β¦
Sycophancy
Definition
Sycophancy is a failure mode in large language models where the system prioritizes β¦
Structural risk minimization
Definition
Structural risk minimization (SRM) is a method for minimizing expected risk by β¦
Structured sparsity regularization
Definition
Structured sparsity regularization extends standard L1 regularization by encouraging β¦
Spreading activation
Definition
Spreading activation is a concept originally from cognitive psychology, adapted in neural β¦
Stable Diffusion
Definition
Stable Diffusion is a deep learning model that generates detailed images conditioned on β¦
Stable Diffusion Diffusers
Definition
The Diffusers library is an open-source toolkit from Hugging Face designed to simplify β¦
Speaker Change Detection
Definition
Speaker Change Detection (SCD) is a technique used to pinpoint exact timestamps where one β¦
Socially assistive robot
Definition
Socially Assistive Robots (SARs) are a subset of human-robot interaction focused on β¦
Software agent
Definition
A software agent is an autonomous entity capable of perceiving its environment, β¦
Situated
Definition
In artificial intelligence, ‘situated’ refers to agents that are embedded in β¦
Situated approach
Definition
The situated approach is a methodological framework in AI research that argues β¦
Sequence labeling
Definition
Sequence labeling involves predicting a categorical label for every token in a given β¦
Semi-supervised learning
Definition
Semi-supervised learning is a hybrid training paradigm that utilizes a small amount of β¦
Sentence Transformers
Definition
Sentence Transformers are extensions of traditional Transformer models (like BERT) β¦
Sample complexity
Definition
In computational learning theory, sample complexity quantifies the amount of data needed β¦
Self-management
Definition
This concept encompasses the capacity of AI agents or systems to handle routine β¦
Semantic analysis
Definition
It goes beyond syntactic structure to interpret the actual intent and significance of β¦
Rust
Definition
Rust is a multi-paradigm, general-purpose programming language designed for performance β¦
Sam3
Definition
Sam3 is not a widely recognized standard public AI term like SAM (Segment Anything β¦
Robustness
Definition
In AI safety and ethics, robustness refers to a model’s resilience against β¦
Rule induction
Definition
Rule induction is a symbolic machine learning method that derives if-then rules directly β¦
Representation collapse
Definition
Representation collapse occurs when a neural network, particularly in self-supervised β¦
Resisting AI
Definition
Resisting AI refers to methods used by individuals or entities to avoid being influenced, β¦
Reflection
Definition
In AI, reflection is a paradigm where a model pauses to evaluate its own generation β¦
Relational data mining
Definition
Relational data mining focuses on extracting useful information from databases where data β¦
Random feature
Definition
Random feature maps transform inputs into a new space where linear models can approximate β¦
Reasoning model
Definition
Unlike standard generative models focused on fluency, reasoning models prioritize β¦
Rabbit r1
Definition
The Rabbit r1 is a dedicated hardware device launched by Rabbit Inc., centered around its β¦
ROCm
Definition
ROCm (Radeon Open Compute) is a driver and software stack developed by AMD to enable β¦
Qwen Coder
Definition
Qwen Coder is a dedicated version of the Qwen large language model fine-tuned β¦
Qwen2
Definition
Qwen2 signifies the second significant generation of the Qwen model family, introducing β¦
Prompt Tuning
Definition
Prompt tuning involves adding trainable soft prompts (continuous vectors) to the input β¦
Pruning
Definition
Pruning involves identifying and eliminating neurons, connections, or filters in a neural β¦
Pyannote
Definition
Pyannote is an open-source Python library developed by pyannote.audio, specializing in β¦
Pyannote Audio
Definition
Pyannote Audio is a comprehensive toolkit designed to facilitate the development and β¦
Pythia
Definition
Pythia is a series of open-source large language models (LLMs) created by EleutherAI, β¦
Probability matching
Definition
Probability matching is a behavioral pattern often observed in reinforcement learning and β¦
Programming by example
Definition
Programming by Example (PBE) is a paradigm in program synthesis where developers specify β¦
Principle of rationality
Definition
This principle posits that an agent’s actions should be chosen to maximize its β¦
Prior knowledge for pattern recognition
Definition
Prior knowledge refers to domain-specific insights, constraints, or historical data β¦
Predictive learning
Definition
Predictive learning involves training neural networks to infer unobserved data points β¦
Preference learning
Definition
Preference learning focuses on teaching models to distinguish between good and bad β¦
Phi coefficient
Definition
The Phi coefficient (Ο) is a measure of association for two binary variables, serving as β¦
Physical Intelligence Inc.
Definition
Physical Intelligence Inc. (PI) is a spin-off from Google DeepMind, established to β¦
Personality computing
Definition
Personality computing involves developing algorithms and systems capable of modeling, β¦
Phi
Definition
Phi, short for ‘Foundation models based on Teaching-Learning Paradigm’, is a β¦
Perceiver
Definition
In AI and cognitive science, a perceiver refers to the component of an intelligent system β¦
Percept
Definition
A percept is the internal representation of an external stimulus after it has been β¦
Parallel Web Systems
Definition
Parallel Web Systems refer to infrastructure designs where computational tasks are β¦
Pattern Language
Definition
A Pattern Language is a formalized framework consisting of a set of proven solutions to β¦
POP-11
Definition
POP-11 (Program Oriented Problem Solving) is a multi-paradigm programming language that β¦
Outline of deep learning
Definition
The outline of deep learning encompasses the fundamental structures such as neural β¦
Observability
Definition
In AI engineering, observability refers to the capability to understand the internal β¦
Openvino
Definition
Developed by Intel, OpenVINO (Open Visual Inference and Neural network Optimization) β¦
Novelty detection
Definition
Novelty detection is a machine learning task focused on identifying data points that do β¦
Object Detection
Definition
Object detection extends image classification by not only determining what objects are β¦
Neurocomputing
Definition
This domain focuses on creating hardware and software architectures that mimic the β¦
NASA AI Assisted-Air Quality Monitoring Project
Definition
This project leverages NASA’s Earth observation data combined with advanced AI β¦
Native-language identification
Definition
Native-language identification (NLI) is a subfield of natural language processing that β¦
Neural computation
Definition
Neural computation refers to the mathematical operations performed by artificial neurons β¦
Neural scaling law
Definition
Neural scaling laws describe the predictable power-law relationship between a β¦
Multimodal sentiment analysis
Definition
Multimodal sentiment analysis extends traditional text-based sentiment detection by β¦
Multiplicative weight update method
Definition
The multiplicative weight update method is a fundamental online learning algorithm used β¦
Multitask optimization
Definition
Multitask optimization involves training a single model to handle several distinct but β¦
Multi Modality
Definition
Multi modality represents the architectural and theoretical framework enabling AI models β¦
Multi-armed bandit
Definition
The multi-armed bandit problem illustrates the dilemma faced by an agent deciding whether β¦
Model Registry
Definition
A Model Registry serves as a critical component in MLOps, providing a unified repository β¦
Moral Outsourcing
Definition
Moral outsourcing refers to the phenomenon where humans cede ethical judgment and β¦
Model Compression
Definition
This category includes methods like pruning, quantization, and knowledge distillation β¦
Model Hub Mixin
Definition
Mixins provide common methods such as saving, loading, and pushing models to the Hugging β¦
Mistral
Definition
Mistral refers to a family of powerful open-weight LLMs created by the French startup β¦
Military applications of artificial intelligence
Definition
Military applications of AI encompass a broad range of technologies designed to enhance β¦
Meansβends analysis
Definition
Means-ends analysis is a cognitive strategy used in artificial intelligence and β¦
Meta
Definition
The prefix ‘meta’ in artificial intelligence denotes a higher level of β¦
Matrix regularization
Definition
Matrix regularization extends scalar regularization concepts to matrices, often used in β¦
Machine learning in video games
Definition
This field involves integrating ML techniques into video game pipelines to automate asset β¦
Machine Learning and Knowledge Extraction
Definition
This field combines machine learning techniques with natural language processing and data β¦
Machine learning in earth sciences
Definition
Machine learning enhances earth sciences by processing satellite imagery, seismic data, β¦
Lyra
Definition
In the context of modern AI terminology, Lyra often denotes specialized AI systems β¦
MLOps
Definition
MLOps enables organizations to deploy and maintain machine learning models in production β¦
LocateAnything
Definition
LocateAnything is a versatile computer vision framework that enables the detection and β¦
Ltx Video
Definition
Ltx Video represents an advancement in generative AI for video, utilizing latent space β¦
Llama3.1
Definition
Released in August 2024, Llama 3.1 expands the Llama family to include a massive 405 β¦
LlamaIndex
Definition
Originally known as GPT Index, LlamaIndex is a powerful data framework that enables LLMs β¦
Linear separability
Definition
Linear separability refers to the geometric condition in which data points belonging to β¦
Leave-one-out cross-validation
Definition
Leave-one-out cross-validation (LOOCV) is a specific case of k-fold cross-validation β¦
Leakage
Definition
Data leakage is a critical error in machine learning where the model gains access to β¦
Learning automaton
Definition
This concept originates from reinforcement learning and involves an agent interacting β¦
Last mile
Definition
The ’last mile’ problem refers to the challenges encountered when deploying β¦
Layer Normalization
Definition
Layer Normalization stabilizes training by reducing internal covariate shift, β¦
Knowledge-based systems
Definition
Knowledge-based systems (KBS) are a branch of artificial intelligence that incorporates β¦
Kubernetes
Definition
Kubernetes (often abbreviated as K8s) is a container orchestration system originally β¦
LLM-as-a-Judge
Definition
LLM-as-a-Judge is an evaluation paradigm where a Large Language Model serves as an β¦
Knowledge integration
Definition
Knowledge integration involves merging data from diverse origins, such as databases, β¦
Knowledge level
Definition
Coined by Allen Newell, the knowledge level analyzes intelligent systems based on their β¦
Knowledge-based configuration
Definition
This approach employs constraint satisfaction techniques within a knowledge base to β¦
Knowledge Compilation
Definition
Knowledge compilation refers to techniques in artificial intelligence that convert a β¦
Intelligent decision support system
Definition
An Intelligent Decision Support System (IDSS) integrates artificial intelligence β¦
Kernel density estimation
Definition
Kernel Density Estimation (KDE) is a fundamental statistical technique that smooths β¦
Intelligent agent
Definition
An intelligent agent is a system capable of perceiving its surroundings through sensors β¦
Intelligent automation
Definition
Intelligent automation integrates traditional Robotic Process Automation (RPA) with β¦
Intelligent database
Definition
An intelligent database leverages machine learning and AI to enhance standard database β¦
Inception Score
Definition
The Inception Score (IS) is a statistical measure introduced to assess the performance of β¦
Information space analysis
Definition
This concept involves analyzing the structure of the representation space in machine β¦
Instance selection
Definition
Instance selection aims to improve computational efficiency and model performance by β¦
Image Text To Text
Definition
Image Text To Text refers to models that process visual inputs alongside textual queries β¦
Image To Image
Definition
Image To Image (I2I) involves using deep learning models, such as GANs or diffusion β¦
I2I
Definition
Image-to-Image (I2I) translation involves mapping pixels from a source domain to a target β¦
Image Generation
Definition
This paradigm utilizes models like Stable Diffusion or DALL-E to produce high-quality β¦
Hybrid Search
Definition
Hybrid Search integrates two distinct retrieval methods: dense vector search, which β¦
Hyperparameter Tuning
Definition
Hyperparameter tuning involves evaluating different sets of hyperparameters to find the β¦
Human Oversight
Definition
Human oversight refers to the mechanisms and processes where humans monitor, evaluate, β¦
Human-centered AI
Definition
Human-centered AI is a design philosophy that places humans at the core of artificial β¦
HumanβAI interaction
Definition
HumanβAI interaction (HAI) is an interdisciplinary field examining the dynamics between β¦
Hierarchical control system
Definition
A hierarchical control system organizes control logic into multiple layers, typically β¦
Hello World: How to be Human in the Age of the Machine
Definition
This phrase refers to a specific literary work that examines how humans can maintain β¦
Hidden Layer
Definition
A hidden layer consists of neurons that receive inputs from previous layers, apply β¦
H2O
Definition
H2O is a widely used open-source in-memory platform for distributed, scalable machine β¦
Grok 1
Definition
Grok-1 is the inaugural release from xAI, launched in November 2023. It is a decoder-only β¦
Grounding
Definition
In AI, grounding refers to linking symbolic representations or generated text to concrete β¦
GraphQL
Definition
Developed by Facebook, GraphQL provides a complete and understandable description of the β¦
Governance
Definition
AI Governance refers to the set of rules, guidelines, and institutional structures that β¦
Gpt Bigcode
Definition
GPT Bigcode, often associated with models like StarCoder, represents a significant β¦
GLM
Definition
In statistical modeling, GLM stands for Generalized Linear Models, which extend linear β¦
Generative artificial intelligence dependency
Definition
This concept refers to the strategic and operational reliance businesses place on β¦
Genie
Definition
Genie refers to a family of generative models designed specifically for video synthesis. β¦
Gemma
Definition
Gemma models are designed to be efficient and accessible for researchers and developers. β¦
Game theory
Definition
Game theory is a branch of applied mathematics that models strategic interactions between β¦
Gated Recurrent Unit
Definition
A Gated Recurrent Unit (GRU) is a specialized recurrent neural network (RNN) cell β¦
FrontierMath
Definition
FrontierMath is a specialized evaluation suite created to test the limits of large β¦
GGUF
Definition
GGUF (GPT-Generated Unified Format) is a binary file format designed specifically for β¦
Forethought Technologies
Definition
This concept involves designing AI systems with forward-looking capabilities that can β¦
Fp8
Definition
Floating-point 8 (FP8) is a numerical data type that offers a balance between β¦
Feedback neural network
Definition
Feedback neural networks, also known as recurrent neural networks (RNNs), contain loops β¦
Feature hashing
Definition
Feature hashing, also known as the hashing trick, allows machine learning models to β¦
Feature Store
Definition
A Feature Store acts as a bridge between data engineering and machine learning teams, β¦
Feature Engineering
Definition
Feature engineering is the art of leveraging domain expertise to transform raw data into β¦
Feature Extraction
Definition
Feature extraction involves transforming raw data into a set of features that better β¦
Explainable artificial intelligence
Definition
As machine learning models become more complex, particularly deep neural networks, their β¦
Explorationβexploitation dilemma
Definition
In decision-making processes, agents face a trade-off: they can exploit current knowledge β¦
Evolvability
Definition
In computational contexts, evolvability refers to how easily an algorithm or neural β¦
Enterprise cognitive system
Definition
An enterprise cognitive system combines artificial intelligence, natural language β¦
Emergent algorithm
Definition
Emergent algorithms refer to complex global behaviors or patterns that arise from the β¦
Empirical risk minimization
Definition
Empirical Risk Minimization (ERM) is the standard objective function for training β¦
Edge inference
Definition
This practice involves deploying trained AI models directly onto hardware such as β¦
Embodied agent
Definition
Unlike disembodied AI that processes abstract data, embodied agents learn and act within β¦
Eagle
Definition
Eagle represents a specific architectural and engineering framework within the domain of β¦
Edge Computing
Definition
Edge computing addresses the latency and bandwidth limitations of cloud-centric β¦
ELMo
Definition
ELMo generates context-sensitive word embeddings by processing input text through a β¦
Diffusers: Zimagepipeline
Definition
In the context of the Hugging Face Diffusers ecosystem, this term generally refers to a β¦
Discovery System
Definition
A discovery system is a computational framework aimed at accelerating scientific or β¦
Diffusers:Stablediffusion3Pipeline
Definition
This pipeline utilizes the Stable Diffusion 3 model, which introduces a Multimodal β¦
Diffusers:Stablediffusionxlpipeline
Definition
This pipeline implements the Stable Diffusion XL architecture, which uses a refined base β¦
Diffusers:Ltxpipeline
Definition
The LTX pipeline is tailored for models that prioritize speed and efficiency in β¦
Decision tree pruning
Definition
Pruning is a method used to prevent overfitting in decision tree models by removing β¦
DeepSeek V3
Definition
DeepSeek V3 is an advanced iteration in the DeepSeek model family, characterized by its β¦
DeepSeek V4
Definition
As a successor to previous versions, DeepSeek V4 implies continued evolution in the β¦
DeepSeek VL V2
Definition
DeepSeek VL V2 extends the capabilities of the standard language model into the β¦
Diella
Definition
Diella refers to specific neural network models optimized for enhancing image quality by β¦
Dataset:Nvidia/Helpsteer2
Definition
Helpsteer2 is a curated dataset released by NVIDIA that contains pairwise comparisons of β¦
Dataset:S2Orc
Definition
S2ORC is a comprehensive corpus of scholarly articles derived from Semantic Scholar. It β¦
Dataset:Tiiuae/Falcon Refinedweb
Definition
RefinedWeb is a large-scale dataset of filtered web pages designed for pretraining β¦
Dataset:Natural Questions
Definition
Natural Questions (NQ) is a benchmark dataset introduced by Google to advance research in β¦
Dataset:Nerfgun3/Bad Prompt
Definition
This term refers to a specific dataset hosted on Hugging Face under the user β¦
Dataset:Embedding Data/Simple Wiki
Definition
This dataset consists of sentences and paragraphs extracted from Simple English β¦
Dataset:Embedding Data/Wikianswers
Definition
This dataset contains millions of question-answer pairs scraped from the now-defunct β¦
Dataset:Embedding Data/Altlex
Definition
The Altlex dataset consists of pairs of sentences that share the same underlying meaning β¦
Dataset:Embedding Data/Flickr30K Captions
Definition
Flickr30K Captions is a widely used benchmark dataset comprising 31,783 images, each β¦
Dataset:Embedding Data/Sentence Compression
Definition
Sentence compression datasets consist of pairs where the target sentence is a shortened β¦
Dataset shift
Definition
Dataset shift occurs when the distribution of data used to train a machine learning model β¦
Dataset:Code Search Net
Definition
Code Search Net is a comprehensive dataset created to advance research in code retrieval. β¦
Data-centric AI
Definition
Data-centric AI represents a paradigm shift in artificial intelligence development, β¦
Data Science and Predictive Analytics
Definition
Data science involves the interdisciplinary process of extracting knowledge from β¦
Curse of dimensionality
Definition
The curse of dimensionality refers to various phenomena that arise when analyzing data in β¦
CrewAI
Definition
CrewAI provides a structured environment for building multi-agent systems where each β¦
Croissant
Definition
Developed as part of the MLCommons initiative, Croissant uses JSON-LD to provide a β¦
Content Provenance
Definition
Content provenance refers to the documentation and verification of where digital content β¦
Compliance
Definition
In artificial intelligence, compliance refers to the process of ensuring that AI models β¦
Computational heuristic intelligence
Definition
Computational heuristic intelligence involves algorithms that employ rules of thumb, β¦
Computational intelligence
Definition
Computational intelligence (CI) encompasses a set of nature-inspired computational β¦
Computer Audition
Definition
Computer audition involves developing algorithms that allow computers to extract β¦
ComfyUI
Definition
ComfyUI is a powerful, modular, and node-based GUI for Stable Diffusion models. Unlike β¦
Commonsense knowledge
Definition
Commonsense knowledge refers to the vast amount of implicit information about everyday β¦
Codeqwen
Definition
CodeQwen is a variant of the Qwen series developed by Alibaba Cloud, specifically β¦
Citation
Definition
As generative AI models produce content, the need for citation mechanisms has emerged to β¦
Clip
Definition
In deep learning engineering, clipping is commonly applied to gradients to mitigate the β¦
Chain
Definition
In AI application development, a Chain refers to a linear or directed graph structure β¦
Chatglm
Definition
ChatGLM represents a family of transformer-based language models specifically designed to β¦
Chunking
Definition
Chunking is a critical preprocessing step in Retrieval-Augmented Generation (RAG) and β¦
Case-based reasoning
Definition
CBR operates on the principle that similar problems have similar solutions. The process β¦
Bloom
Definition
While historically referring to Benjamin Bloom’s educational taxonomy, in modern AI β¦
Bert
Definition
BERT is a transformer-based machine learning technique for NLP pre-training developed by β¦
Biomedical
Definition
Biomedical refers to the intersection of biology, medicine, and technology, particularly β¦
Behavior informatics
Definition
Behavior informatics combines computer science, psychology, and statistics to analyze β¦
Beliefβdesireβintention model
Definition
The Belief-Desire-Intention (BDI) model is a cognitive architecture for designing β¦
Bayesian optimization
Definition
Bayesian optimization uses a probabilistic surrogate model, typically a Gaussian Process, β¦
Autonomous Agent
Definition
In artificial intelligence, an autonomous agent is an entity that operates independently β¦
Batch Normalization
Definition
This method adjusts and scales activations to have zero mean and unit variance within β¦
Automated medical scribe
Definition
Automated medical scribes utilize natural language processing and speech recognition β¦
Automatic Speech Recognition
Definition
Automatic Speech Recognition (ASR), also known as speech-to-text, is a subfield of speech β¦
Automation in construction
Definition
Automation in construction refers to the integration of robotic systems, drones, and β¦
Audit
Definition
An AI audit involves a rigorous, structured review of machine learning models and their β¦
Automated machine learning
Definition
AutoML (Automated Machine Learning) streamlines the development of ML models by β¦
Async Processing
Definition
Asynchronous processing allows software to perform long-running tasks, such as I/O β¦
Audio To Audio
Definition
Audio-to-audio refers to neural network architectures designed to map one audio signal to β¦
Artificial intelligence arms race
Definition
The AI arms race refers to the intense competition among countries, corporations, and β¦
Artificial intelligence of things
Definition
Artificial Intelligence of Things (AIoT) represents the synergistic integration of β¦
Artificial intelligence and elections
Definition
This term encompasses the dual role of AI in democratic processes: enhancing efficiency β¦
Artificial Inventor Project
Definition
The Artificial Inventor Project is an interdisciplinary research effort aimed at β¦
Anonymization
Definition
Anonymization involves modifying data so that it can no longer be associated with a β¦
Argumentation framework
Definition
Argumentation frameworks provide a mathematical basis for representing arguments, β¦
AlphaChip
Definition
AlphaChip is a specialized AI system designed to automate and enhance the placement and β¦
Andβor tree
Definition
An Andβor tree is a representation used in problem-solving and planning, particularly in β¦
Algorithm selection
Definition
Algorithm selection involves evaluating different computational approaches to determine β¦
Algorithmic bias
Definition
Bias in algorithms typically originates from non-representative training data, subjective β¦
Algorithmic inference
Definition
Also known as prediction or scoring, inference occurs after the model training phase. The β¦
Agent harness
Definition
It acts as the backbone for multi-agent systems, providing tools for orchestration, β¦
Active learning
Definition
Active learning reduces the amount of labeled data required by allowing the model to β¦
Admissible heuristic
Definition
In pathfinding and search problems, an admissible heuristic provides a lower bound on the β¦
Accelerated Linear Algebra
Definition
This field focuses on speeding up fundamental linear algebra computations, which are core β¦
AIOps
Definition
Artificial Intelligence for IT Operations (AIOps) combines big data analytics and machine β¦
AI warfare
Definition
AI warfare refers to the integration of artificial intelligence into military strategies, β¦
AI infrastructure
Definition
AI infrastructure encompasses the foundational technology stack necessary for artificial β¦
A/B Testing
Definition
A/B testing is a randomized controlled experiment where two variants, A and B, are β¦
AI agent
Definition
An AI agent is a software entity that operates autonomously within a defined environment β¦
AI Security Institute
Definition
An AI Security Institute is a specialized entity focused on mitigating risks associated β¦
Tool Use
Definition
Tool Use enables language models to interact with external software environments by β¦
Unsupervised Learning
Definition
Unsupervised learning identifies hidden structures, clusters, or distributions within raw β¦
Positional Encoding
Definition
Since transformers process all tokens in parallel rather than sequentially like RNNs, β¦
Quantization
Definition
Quantization converts high-precision floating-point numbers (like FP32) into β¦
Reasoning
Definition
In AI, reasoning involves algorithms that simulate logical deduction, induction, or β¦
ReLU
Definition
ReLU is widely used in deep learning neural networks due to its computational efficiency β¦
Residual Connection
Definition
Residual connections, also known as skip connections, allow gradients to flow through a β¦
Semantic Search
Definition
Semantic search interprets the intent and contextual meaning behind a query, going beyond β¦
Summarization
Definition
Text summarization reduces large volumes of text into shorter versions without losing β¦
Planning
Definition
Planning in AI involves determining a sequence of actions that will lead from an initial β¦
Memory
Definition
In artificial intelligence, memory refers to mechanisms that allow models to retain β¦
Model Serving
Definition
Model serving involves taking a static trained model and wrapping it in a scalable β¦
Multimodal
Definition
Multimodal AI systems integrate information from different sensory inputs to form a more β¦
Learning Rate
Definition
The learning rate determines how much the model’s weights are updated relative to β¦
Loss Function
Definition
Also known as the cost or error function, the loss function provides a scalar value β¦
Function Calling
Definition
Function calling enables large language models to interact with external tools and APIs β¦
Interpretability
Definition
Interpretability, or explainability, involves making the internal workings and β¦
Dropout
Definition
In neural networks, dropout prevents overfitting by temporarily removing a random subset β¦
Encoder
Definition
Encoders process raw input sequences or data structures and convert them into latent β¦
Fairness
Definition
In artificial intelligence, fairness is a critical ethical metric ensuring that β¦
Data Protection
Definition
Data Protection encompasses legal, technical, and organizational measures designed to β¦
Deepfake
Definition
Deepfakes are hyper-realistic audio or video manipulations created using generative β¦
BPE
Definition
Byte Pair Encoding (BPE) is a data compression technique adapted for natural language β¦
Activation Function
Definition
An activation function introduces non-linearity into a neural network, allowing it to β¦
Agentic
Definition
The term ‘agentic’ describes AI agents that operate with a high degree of β¦
training-free
Definition
Training-free approaches refer to techniques that modify model behavior or output without β¦
two-stage
Definition
Two-stage architectures divide a complex task into two separate steps, typically β¦
post-training
Definition
Post-training is a critical stage in the machine learning lifecycle that occurs after the β¦
one-shot
Definition
One-shot learning is a specific type of few-shot learning where the algorithm must β¦
out-of-distribution
Definition
Out-of-distribution (OOD) detection identifies inputs that fall outside the scope of the β¦
multi-step
Definition
Multi-step methods involve breaking down a complex query or task into smaller, executable β¦
learning-based
Definition
Learning-based approaches rely on statistical algorithms to identify patterns and make β¦
high-dimensional
Definition
High-dimensional refers to datasets or vector spaces containing a vast number of β¦
high-fidelity
Definition
High-fidelity describes outputs from generative models that are indistinguishable from or β¦
few-shot
Definition
Few-shot learning enables machine learning models to generalize from very limited data, β¦
fine-grained
Definition
Fine-grained analysis involves identifying and categorizing objects or concepts at a β¦
closed-loop
Definition
Closed-loop systems in AI utilize real-time feedback from the environment to dynamically β¦
cross-modal
Definition
Cross-modal AI involves processing and correlating data from distinct modalities, such as β¦
Tokenization
Definition
Tokenization is a critical preprocessing step in Natural Language Processing (NLP) that β¦
Transfer Learning
Definition
Transfer learning leverages pre-trained models to improve performance and reduce training β¦
Understanding
Definition
AI understanding goes beyond statistical correlation to interpret the underlying meaning β¦
Synthetic
Definition
In AI, synthetic data is artificially generated information that mimics real-world data β¦
Temporal
Definition
Temporal concepts in AI involve analyzing data points ordered in time, such as stock β¦
Stochastic
Definition
Stochastic elements introduce variability into AI systems, such as noise in data or β¦
Privacy
Definition
In artificial intelligence, privacy refers to the protection of sensitive user β¦
Rate
Definition
In AI, ‘rate’ most frequently refers to the learning rate, a hyperparameter β¦
Reinforcement
Definition
Reinforcement is a fundamental psychological and computational mechanism where an β¦
Robust
Definition
In artificial intelligence, robustness refers to the resilience of a model against β¦
Safe
Definition
Safety in AI involves implementing constraints and safeguards to ensure that automated β¦
Scaling
Definition
Scaling is the active methodology of expanding AI systems by adding more layers, neurons, β¦
Search
Definition
Search is a fundamental paradigm in AI used to navigate complex problem spaces, such as β¦
Self
Definition
While current AI lacks consciousness, the term ‘self’ often describes β¦
Semantic
Definition
Semantic analysis in AI focuses on understanding the underlying meaning of inputs rather β¦
Policy
Definition
The term ‘policy’ has dual meanings depending on the context. In general β¦
Optimal
Definition
In AI and optimization theory, an optimal solution is one that achieves the highest β¦
Perception
Definition
AI perception involves converting raw sensor data into meaningful information that can be β¦
Natural Language Processing
Definition
Natural Language Processing (NLP) is a subfield of artificial intelligence that combines β¦
Online
Definition
Online learning is a machine learning paradigm where the model is updated incrementally β¦
Nash
Definition
In AI, particularly in Multi-Agent Systems and Reinforcement Learning, Nash Equilibrium β¦
Markov
Definition
In artificial intelligence and probability theory, Markov processes are fundamental β¦
Monte
Definition
Monte Carlo techniques are a class of computational algorithms that rely on repeated β¦
Long
Definition
In the context of AI, ’long’ often describes the capability to process β¦
Loss
Definition
Loss functions, also known as cost functions, measure how well a machine learning β¦
Large Language Models
Definition
This term refers to the broader application paradigm where models with billions of β¦
Instruction Tuning
Definition
This process bridges the gap between general pre-training and specific task performance. β¦
Grounded
Definition
In artificial intelligence, ‘grounded’ describes the process of linking β¦
Guided
Definition
The term ‘guided’ in AI typically refers to techniques where the β¦
Hierarchical
Definition
Hierarchical AI systems organize information or control into a tree-like structure of β¦
Generation
Definition
In artificial intelligence, generation refers to the capability of models, particularly β¦
Gaussian
Definition
Gaussian refers to the normal distribution, a continuous probability distribution β¦
Fine
Definition
Fine-tuning involves taking a general-purpose model trained on large datasets and further β¦
Evolving
Definition
The term ’evolving’ characterizes dynamic AI models that undergo continuous β¦
Embodied
Definition
Embodied AI posits that intelligence emerges from the interaction between an β¦
Energy
Definition
Energy has two primary meanings in AI. First, it denotes the electrical power required to β¦
Distillation
Definition
This process involves transferring knowledge from a complex, high-performance β¦
Detection
Definition
Detection is a core computer vision and signal processing task where an AI model β¦
Contrastive
Definition
This method encourages the model to pull embeddings of positive pairs (similar items) β¦
Benchmarking
Definition
Benchmarking is the active practice of conducting experiments to measure how well an AI β¦
Autonomous
Definition
Autonomy in AI refers to the ability of a system to perceive its environment, make β¦
Adam
Definition
Adam (Adaptive Moment Estimation) is a popular first-order gradient-based optimization β¦
Agents
Definition
AI agents are software programs or systems capable of perceiving their surroundings β¦
Fine-tuning
Definition
Fine-tuning involves taking a model already trained on a large, general dataset and β¦
In-Context Learning
Definition
In-context learning (ICL) allows large language models to adapt to new tasks without β¦
Code Generation
Definition
Code generation leverages large language models trained on vast repositories of β¦
Context Window
Definition
The context window defines the operational limit of an AI model’s memory for a β¦
Deep Learning
Definition
Deep learning algorithms attempt to mimic the human brain’s analytical and learning β¦
Attention Mechanism
Definition
An attention mechanism enables a model to weigh the importance of different elements β¦
Chain-of-Thought
Definition
Chain-of-Thought (CoT) prompting is a strategy where large language models are guided to β¦
Agent
Definition
In AI, an agent is an entity that acts on behalf of a user or system to complete tasks. β¦