Model Extraction
Definition
Model extraction involves querying a target machine learning model’s API to infer β¦
4
Backdoor Attack
Definition
A backdoor attack involves poisoning the training data of a machine learning model with β¦
Zeuthen Strategy
Definition
The Zeuthen strategy is a rule-based approach for bargaining in multi-agent negotiations. β¦
Wetware computer
Definition
Wetware computing refers to systems where biological neurons, often cultured in vitro, β¦
WebSocket
Definition
WebSocket is a computer communications protocol that enables persistent, two-way β¦
Wetware
Definition
Wetware originally referred to biological brain tissue but has evolved in cybernetics and β¦
Wadhwani Institute for Artificial Intelligence
Definition
Established with a significant donation from the Wadhwani Foundation, this institute β¦
Video Super Resolution
Definition
Video Super Resolution involves using neural networks to upscale video content from lower β¦
Vllm
Definition
vLLM (Virtual Large Language Model) is an open-source library designed to accelerate LLM β¦
Universal psychometrics
Definition
Universal psychometrics involves developing and applying assessment tools that can β¦
Tree of Thoughts
Definition
Tree of Thoughts (ToT) extends traditional chain-of-thought prompting by allowing the β¦
Timeline of artificial intelligence risks in global finance
Definition
This concept refers to the historical and projected sequence of events where artificial β¦
Three-factor learning
Definition
Three-factor learning is a specific approach within reinforcement learning that β¦
Text To Video
Definition
Text-to-video refers to generative AI models that create dynamic visual content based on β¦
The Master Algorithm
Definition
Coined by Pedro Domingos in his book of the same name, the ‘Master Algorithm’ β¦
Text Generation Inference
Definition
Text Generation Inference (TGI) is a dedicated software framework designed to serve large β¦
Temporal bias
Definition
Temporal bias occurs when machine learning models disproportionately weight recent β¦
Symbolic regression
Definition
Symbolic regression is a type of regression analysis that seeks to find a mathematical β¦
Supermind AI
Definition
Supermind AI refers to systems where multiple AI components, human experts, or hybrid β¦
Statistical learning theory
Definition
Statistical learning theory (SLT) is a branch of statistics and computer science that β¦
Statistical relational learning
Definition
Statistical relational learning (SRL) combines probability theory with relational data β¦
Spike-and-slab regression
Definition
Spike-and-slab regression is a Bayesian statistical technique used for variable selection β¦
Spatial intelligence
Definition
Spatial intelligence refers to the capacity of artificial intelligence models to β¦
Speaker Diarization
Definition
Speaker Diarization is the task of partitioning an audio stream into homogeneous segments β¦
Sovereign AI
Definition
Sovereign AI describes the capability of a country or organization to build, deploy, and β¦
Spatial embedding
Definition
Spatial embedding involves converting physical or abstract spatial relationships into β¦
Singularity studies
Definition
Singularity studies is an emerging academic discipline that investigates the implications β¦
Slopaganda
Definition
Slopaganda describes a strategic form of disinformation that relies on repetition, β¦
Similarity learning
Definition
Similarity learning focuses on training models to map inputs into a vector space where β¦
Semantic folding
Definition
Semantic folding refers to the process of compressing complex, high-dimensional vector β¦
Self-Consistency
Definition
Primarily used with Large Language Models (LLMs), this technique improves accuracy by β¦
Sam3 Video
Definition
Sam3 Video refers to the application of advanced segmentation models, potentially a β¦
SUPS
Definition
SUPS is an acronym that can vary by context but frequently appears in specialized AI β¦
Robot learning
Definition
Robot learning involves training robotic agents to perform tasks autonomously by β¦
Reparameterization trick
Definition
The reparameterization trick is a fundamental method used in variational autoencoders and β¦
Recursive self-improvement
Definition
Recursive self-improvement refers to the theoretical capability of an artificial β¦
Rademacher complexity
Definition
Rademacher complexity evaluates how well a hypothesis class can correlate with random β¦
Reciprocal human machine learning
Definition
This approach moves beyond simple human-in-the-loop labeling. It involves bidirectional β¦
Qwen3 5 Moe
Definition
This term refers to a specialized architecture within the Qwen family, likely leveraging β¦
Qwen3 5
Definition
Qwen3 5 appears to denote a specific checkpoint, size variant, or specialized release β¦
Quantized
Definition
Quantization is a model optimization technique that reduces the numerical precision of a β¦
Proximal gradient methods for learning
Definition
Proximal gradient methods are iterative optimization techniques used when the loss β¦
Psychology of reasoning
Definition
This field examines the mental processes underlying human deduction, induction, and β¦
Pyannote Audio Pipeline
Definition
In the context of Pyannote Audio, a pipeline refers to a configurable workflow that β¦
Pytorch Model Hub Mixin
Definition
The PyTorch Model Hub Mixin is a component provided by the Hugging Face Transformers β¦
Product of experts
Definition
The Product of Experts (PoE) is a method for constructing complex probability β¦
Proactive learning
Definition
In proactive learning, the AI system determines which samples would most reduce β¦
Probabilistic numerics
Definition
Probabilistic numerics applies Bayesian methods to traditional numerical problems like β¦
Predictive state representation
Definition
Predictive State Representations (PSRs) extend traditional partially observable Markov β¦
Prefix Tuning
Definition
Prefix Tuning is a parameter-efficient adaptation technique for pre-trained transformers. β¦
Polysemanticity
Definition
Polysemanticity is a characteristic observed in deep neural networks, particularly in β¦
Personaplex
Definition
Personaplex refers to the ecosystem or infrastructure supporting the creation, β¦
Pattern theory
Definition
Pattern theory provides a rigorous mathematical foundation for understanding how complex β¦
Perception error model
Definition
A perception error model describes the discrepancies between observed sensory data and β¦
Parity Learning
Definition
Parity Learning is a benchmark problem in machine learning theory where the goal is to β¦
P-Tuning
Definition
P-Tuning (Prompt Tuning) is a technique designed to adapt large pre-trained language β¦
PagedAttention
Definition
PagedAttention is a technique introduced by the vLLM project to improve the efficiency of β¦
Overlapped Speech Detection
Definition
Overlapped Speech Detection (OSD) is a specialized task in speech processing that β¦
Nouvelle AI
Definition
Nouvelle AI refers to a class of artificial intelligence systems that utilize symbolic β¦
Neurorobotics
Definition
This field bridges neuroscience and robotics by implementing neural network models into β¦
Muse Spark
Definition
Muse Spark is an open-source deep learning framework designed to run efficiently on top β¦
Mxfp4
Definition
MXFP4 (Mixed eXtended Floating Point 4-bit) is a specialized data type format introduced β¦
Neural modeling fields
Definition
Neural modeling fields involve the study of how neural populations organize themselves in β¦
Neuro-symbolic AI
Definition
Neuro-symbolic AI integrates sub-symbolic neural learning methods with symbolic β¦
Multimodal representation learning
Definition
Multimodal representation learning involves training models to process and integrate β¦
Multivariate adaptive regression spline
Definition
Multivariate Adaptive Regression Splines (MARS) is a flexible regression method that β¦
Multi-task Learning
Definition
This technique leverages the inductive bias shared among related tasks to enhance β¦
Mixture of Experts
Definition
Mixture of Experts (MoE) is a machine learning architecture designed to improve β¦
Moshi
Definition
Moshi is an advanced AI model created by Kyutai that integrates speech and text β¦
Mode Collapse
Definition
In GANs, mode collapse occurs when the generator learns to exploit weaknesses in the β¦
Mistral Common
Definition
Mistral Common is a Python package maintained by Mistral AI that offers standardized β¦
Mixed Precision Training
Definition
Mixed Precision Training (MPT) combines half-precision (FP16) and full-precision (FP32) β¦
Mixtral
Definition
Mixtral is a pioneering open-weight LLM that utilizes a Sparse Mixture of Experts (MoE) β¦
Meta-learning
Definition
Meta-learning focuses on designing algorithms that can learn from previous tasks to β¦
Mindpixel
Definition
While not a standard academic term, ‘Mindpixel’ typically denotes a discrete β¦
Maximum inner-product search
Definition
Maximum Inner-Product Search (MIPS) is a fundamental problem in information retrieval and β¦
Manifold regularization
Definition
Manifold regularization extends traditional regularization methods by incorporating the β¦
Machine unlearning
Definition
This technique addresses privacy regulations like GDPR’s ‘right to be β¦
Manifold hypothesis
Definition
This hypothesis explains why deep learning works effectively despite the curse of β¦
Machine learning control
Definition
Machine learning control integrates adaptive algorithms with traditional control systems β¦
Machine learning in bioinformatics
Definition
This interdisciplinary field uses machine learning to process vast amounts of biological β¦
MAUVE
Definition
MAUVE is a statistical measure designed to assess how closely the output of a generative β¦
Local case-control sampling
Definition
Local case-control sampling is a strategy used primarily in training contrastive learning β¦
Lottery ticket hypothesis
Definition
The Lottery Ticket Hypothesis suggests that within a large, randomly initialized neural β¦
Local Llm
Definition
Running a Local LLM involves deploying open-weight models directly on consumer-grade β¦
Life-time of correlation
Definition
In dynamic systems and time-series analysis, the life-time of correlation measures the β¦
Lifelong Planning A*
Definition
Lifelong Planning A* (LPA*) is an extension of the A* search algorithm designed for β¦
Learnable function class
Definition
In statistical learning theory, a learnable function class represents the hypothesis β¦
Learning to rank
Definition
Unlike standard classification or regression, learning to rank focuses on predicting a β¦
Language/action perspective
Definition
Rooted in speech act theory and pragmatics, this perspective emphasizes how utterances β¦
KolmogorovβArnold Networks
Definition
KolmogorovβArnold Networks (KANs) are a recent class of neural networks inspired by the β¦
Knowledge graph embedding
Definition
Knowledge graph embedding methods, such as TransE or DistMult, transform discrete graph β¦
Knowledge-based recommender system
Definition
Unlike collaborative filtering, which relies on past user behavior, KBRS uses explicit β¦
Knowledge Distillation
Definition
Knowledge distillation is a machine learning method used to compress a large, complex β¦
Intrinsic motivation
Definition
In reinforcement learning, intrinsic motivation drives an agent to explore its β¦
KAoS
Definition
KAoS is an intelligent agent framework developed to handle the complexity of large-scale, β¦
Intelligent control
Definition
Intelligent control employs artificial intelligence methods such as fuzzy logic, neural β¦
Incremental Heuristic Search
Definition
Incremental Heuristic Search refers to algorithms that refine a candidate solution β¦
Inductive Bias
Definition
Inductive bias represents the inherent preferences or constraints built into a machine β¦
Inductive Programming
Definition
Inductive Programming, often referred to as Program Synthesis, involves creating software β¦
Inferential theory of learning
Definition
This theory posits that learning is essentially a process of probabilistic inference. β¦
Image To Video
Definition
Image To Video technology takes a single static frame and predicts subsequent frames to β¦
Ideonomy
Definition
This field studies the processes behind how ideas are formed, combined, and evolved. It β¦
Hybrid intelligent system
Definition
A Hybrid Intelligent System (HIS) merges different AI paradigms, typically combining β¦
Hyperparameter optimization
Definition
Hyperparameter Optimization (HPO) refers to the broader field of automating the selection β¦
Hierarchical navigable small world
Definition
The Hierarchical Navigable Small World (HNSW) algorithm constructs a multi-layered graph β¦
Hierarchical Risk Parity
Definition
Hierarchical Risk Parity (HRP) is a portfolio construction method that addresses the β¦
Highway network
Definition
Highway Networks are designed to address the vanishing gradient problem in deep learning β¦
Histogram of oriented displacements
Definition
Histogram of Oriented Displacements (HOD) is a feature extraction method for video β¦
Halite AI Programming Competition
Definition
Halite was an annual AI programming competition hosted by Two Sigma, where developers β¦
Grokking
Definition
Grokking refers to a counter-intuitive behavior observed in deep learning where a model β¦
Gradient Accumulation
Definition
This optimization strategy allows deep learning models to be trained with effective batch β¦
Granular computing
Definition
This approach mimics human cognitive processes by grouping data into higher-level β¦
Gpt Oss
Definition
GPT OSS typically denotes open-source alternatives or derivatives of proprietary β¦
GLM MoE DSA
Definition
There is no single standard term ‘GLM MoE DSA’. However, it likely combines β¦
Genesis Mission
Definition
The Genesis Mission typically refers to a strategic phase or project within an β¦
Geometric feature learning
Definition
Geometric feature learning focuses on processing data that possesses non-Euclidean β¦
Gemma4
Definition
As of current knowledge, there is no officially released model specifically named β¦
Fuzzy agent
Definition
A fuzzy agent operates within environments where data is often ambiguous or incomplete, β¦
Force control
Definition
Force control enables robots to perform delicate operations such as assembly, polishing, β¦
Formal concept analysis
Definition
FCA provides a rigorous framework for analyzing relationships between objects and their β¦
Fitness approximation
Definition
Fitness approximation is used in evolutionary computation when evaluating the true β¦
Flow-based generative model
Definition
Flow-based generative models construct complex probability distributions by applying a β¦
Feature learning
Definition
Feature learning, often associated with deep learning, enables models to learn β¦
Explanation-based learning
Definition
EBL combines symbolic reasoning with machine learning to accelerate the learning process. β¦
Extremal optimization
Definition
Unlike genetic algorithms that maintain a population, EO works on a single solution. It β¦
Evolutionary developmental robotics
Definition
Inspired by biological ontogeny, ED-Robotics explores how complex behaviors and physical β¦
ExBERT
Definition
ExBERT provides interpretability for the BERT transformer model by analyzing the β¦
Equalized odds
Definition
Equalized odds is a statistical parity constraint used in algorithmic fairness to ensure β¦
Empirical dynamic modeling
Definition
Empirical Dynamic Modeling (EDM) is a framework for analyzing nonlinear dynamical systems β¦
Empowerment
Definition
In reinforcement learning and artificial intelligence, empowerment is a intrinsic β¦
Energy-based model
Definition
Energy-Based Models (EBMs) define a probability distribution over input data using an β¦
EfficientNet
Definition
Developed by Google, EfficientNet uses a compound scaling method to balance network β¦
Embodied cognitive science
Definition
This field challenges traditional views that treat the mind as a computer processing β¦
EM algorithm and GMM model
Definition
This term refers to the synergistic relationship between the Expectation-Maximization β¦
Domain Adaptation
Definition
Domain adaptation addresses the challenge when training and testing data come from β¦
Diffusers: Stable Video Diffusion Pipeline
Definition
This term refers to a specific implementation within the Hugging Face Diffusers library β¦
Discrimination against robots
Definition
Discrimination against robots is an emerging ethical and sociological concept that β¦
Diffusers:Qwenimageeditpipeline
Definition
This pipeline integrates the Qwen-Vision-Language model capabilities into the Diffusers β¦
Diffusers:Qwenimagepipeline
Definition
This pipeline adapts the generative capabilities of Qwen-VL models for image synthesis. β¦
Differential Privacy
Definition
Differential privacy provides strong privacy guarantees by adding calibrated statistical β¦
Diffusers:Fluxkontextpipeline
Definition
This pipeline leverages the Flux architecture, known for its high-quality image β¦
Deep Learning Anti-Aliasing
Definition
Deep Learning Anti-Aliasing refers to methods that employ neural networks to mitigate β¦
Deep Learning Super Sampling
Definition
Deep Learning Super Sampling (DLSS) is a technology that leverages neural networks to β¦
Deep Tomographic Reconstruction
Definition
Deep Tomographic Reconstruction represents a significant advancement over traditional β¦
Deploy:Azure
Definition
Deploying to Azure involves utilizing cloud-native tools like Azure Machine Learning, β¦
Description Logic
Definition
Description Logics (DL) are decidable fragments of first-order logic that form the β¦
Dataset:Search Qa
Definition
Search QA datasets typically consist of pairs of search queries and relevant answer β¦
Dataset:Jackrong/Qwen3.5 Reasoning 700X
Definition
This entry refers to a specific dataset repository identified by the identifier β¦
Dataset:Embedding Data/Specter
Definition
The Specter dataset is constructed from a vast collection of Computer Science papers, β¦
Dataset:Flax Sentence Embeddings/Stackexchange Xml
Definition
This dataset extracts sentence-level data from Stack Exchange XML files, providing a rich β¦
Dataset:Embedding Data/Paq Pairs
Definition
The PAQ (Pseudo-Answer Quality) dataset contains millions of automatically generated β¦
Data-driven astronomy
Definition
Data-driven astronomy leverages advanced computational methods, including machine β¦
DABUS
Definition
DABUS is a specific artificial neural network designed to generate novel inventions β¦
Data Poisoning
Definition
This adversarial technique aims to compromise the integrity of machine learning models by β¦
Cross-entropy method
Definition
The Cross-Entropy Method (CEM) is a powerful general-purpose optimization algorithm used β¦
Cost-sensitive machine learning
Definition
Cost-sensitive machine learning extends traditional supervised learning by assigning β¦
Coupled pattern learner
Definition
Coupled pattern learners are designed to handle data where instances from two different β¦
Continual Learning
Definition
Continual learning, also known as lifelong learning, enables neural networks to acquire β¦
Contrastive LanguageβImage Pre-training
Definition
Contrastive LanguageβImage Pre-training (CLIP) is a neural network architecture trained β¦
Contrastive Learning
Definition
Contrastive learning is a representation learning method that does not require labeled β¦
Connectionist expert system
Definition
A connectionist expert system integrates the pattern recognition and learning strengths β¦
Constitutional AI
Definition
Constitutional AI is a framework for aligning large language models with human values β¦
Compressed Tensors
Definition
Compressed tensors are multi-dimensional arrays used in deep learning where the numerical β¦
Concept Drift
Definition
Concept drift is a phenomenon in machine learning where the relationship between input β¦
Conditional Random Field
Definition
Conditional Random Fields (CRFs) are a class of discriminative models commonly used in β¦
Coherent extrapolated volition
Definition
Coherent Extrapolated Volition (CEV) is a concept introduced by Eliezer Yudkowsky in the β¦
Cognitive computing
Definition
Cognitive computing is a branch of artificial intelligence that seeks to interact with β¦
Cognitive robotics
Definition
Cognitive robotics integrates cognitive science with robotics to build machines that can β¦
Class activation mapping
Definition
CAM generates heatmaps overlaid on input images to show which pixels contributed most to β¦
Co-training
Definition
This method leverages multiple distinct feature sets (views) of the same data points. β¦
Category utility
Definition
This metric quantifies how well a set of categories allows one to predict the values of β¦
CHAOS
Definition
Chaos theory explores how small variations in starting parameters can lead to vastly β¦
Bioserenity
Definition
Bioserenity refers to the conceptual ideal where human biology and artificial β¦
BradleyβTerry model
Definition
The Bradley-Terry model is a probabilistic model widely used in psychometrics and machine β¦
Biasβvariance tradeoff
Definition
The bias-variance tradeoff describes the tension between underfitting (high bias) and β¦
Biohybrid system
Definition
Biohybrid systems merge living tissues, cells, or organisms with synthetic materials and β¦
Bayesian programming
Definition
Bayesian programming is a mathematical framework that generalizes Bayes’ theorem to β¦
Bayesian regret
Definition
Bayesian regret quantifies the difference between the optimal reward achievable with β¦
Bayesian structural time series
Definition
Bayesian structural time series (BSTS) models represent time series data as a sum of β¦
Bayesian interpretation of kernel regularization
Definition
This concept establishes that minimizing a regularized risk functional with a specific β¦
Bayesian learning mechanisms
Definition
Bayesian learning mechanisms update beliefs about model parameters using Bayes’ β¦
Ball tree
Definition
A Ball tree partitions data points into nested hyperspheres (balls) rather than β¦
Automated negotiation
Definition
Automated negotiation involves software agents that represent human interests in β¦
Autonomic networking
Definition
Autonomic networking applies principles of autonomic computing to telecommunications β¦
Autognostics
Definition
Autognostics refers to the self-monitoring and self-repair mechanisms embedded within β¦
Astrostatistics
Definition
Astrostatistics is a specialized field that bridges statistics and astronomy. It involves β¦
Audio inpainting
Definition
Audio inpainting is a technique used to fill gaps in audio recordings caused by dropouts, β¦
Artificial intelligence in spirituality
Definition
AI in spirituality refers to the application of artificial intelligence in religious or β¦
Artificial intimacy
Definition
Artificial intimacy refers to the psychological phenomenon where humans develop genuine β¦
Artificial reproduction
Definition
Artificial reproduction encompasses techniques that facilitate or replicate biological β¦
Artificial brain
Definition
An artificial brain refers to hardware or software architectures that emulate the neural β¦
Any To Any
Definition
Any-to-any refers to unified multimodal architectures that can handle various β¦
Apprenticeship learning
Definition
Apprenticeship learning, also known as inverse reinforcement learning from β¦
Algorithmic probability
Definition
Algorithmic probability, rooted in Kolmogorov complexity and Solomonoff induction, β¦
Algorithmic Discrimination
Definition
This phenomenon arises when AI models inadvertently or systematically treat individuals β¦
Adversarial Attack
Definition
Adversarial attacks exploit the vulnerabilities of neural networks by introducing subtle β¦
Adversarial machine learning
Definition
This field encompasses both offensive techniques to break models and defensive strategies β¦
Agentive logic
Definition
It extends traditional logic to account for agency, allowing systems to represent β¦
Action model learning
Definition
Action model learning involves an agent constructing an internal representation of how β¦
Actor-critic algorithm
Definition
The actor-critic algorithm employs two components: the actor, which updates the policy to β¦
AZFinText
Definition
AZFinText is a large-scale annotated corpus specifically curated for Chinese financial β¦
AI veganism
Definition
AI veganism is a speculative and metaphorical term referring to the idea of creating β¦
AI-complete
Definition
AI-complete problems are tasks that, if solved, would imply the existence of Artificial β¦
AI nationalism
Definition
AI nationalism describes the trend where governments treat artificial intelligence as a β¦
AI observability
Definition
AI observability extends traditional software monitoring to address the unique challenges β¦
AI alignment
Definition
AI alignment addresses the challenge of making artificial intelligence systems robustly β¦
Vision Language
Definition
Vision-Language models, often referred to as Multimodal Large Language Models (MLLMs), β¦
Zero-shot Learning
Definition
Zero-shot learning enables a machine learning model to classify instances of classes that β¦
Prompt Injection
Definition
Prompt injection exploits the way large language models interpret user instructions by β¦
QLoRA
Definition
QLoRA combines Low-Rank Adaptation (LoRA) with 4-bit quantization to significantly reduce β¦
ReAct
Definition
The ReAct framework enables LLMs to generate both reasoning traces and task-specific β¦
Recurrent Neural Network
Definition
RNNs are designed to recognize patterns in sequences of data, such as text, genomes, β¦
Self-supervised Learning
Definition
Self-supervised learning is a technique where the algorithm creates supervisory signals β¦
Supervised Fine-tuning
Definition
Supervised Fine-tuning (SFT) involves taking a large pre-trained model, such as a β¦
Multiple instance learning
Definition
Multiple Instance Learning (MIL) addresses scenarios where data is grouped into β¦
Model Context Protocol
Definition
The Model Context Protocol (MCP) is an open standard that enables AI applications to β¦
Multi-Agent System
Definition
Multi-agent systems consist of several independent agents, each potentially specializing β¦
Long Short-Term Memory
Definition
LSTM networks address the vanishing gradient problem common in standard RNNs by using a β¦
Jailbreak
Definition
Jailbreaking involves crafting specific inputs or prompts that trick an AI model into β¦
Embedding Model
Definition
These models map high-dimensional data into a lower-dimensional continuous vector space β¦
Explainability
Definition
This concept addresses the ‘black box’ problem in complex AI systems by β¦
Federated Learning
Definition
Federated learning enables organizations to collaboratively train AI models without β¦
Few-shot Learning
Definition
Few-shot learning aims to enable models to generalize from just a handful of examples, β¦
Decoder
Definition
In sequence-to-sequence models, the decoder takes the context vector produced by the β¦
Distributed Training
Definition
Distributed Training accelerates model convergence by parallelizing computation over β¦
Chain-of-Thought Prompting
Definition
Chain-of-Thought (CoT) prompting improves the performance of large language models on β¦
Adapter
Definition
Adapters are a parameter-efficient fine-tuning technique used primarily in large language β¦
Attention
Definition
Attention mechanisms enable models to focus on relevant information when processing β¦
zero-shot
Definition
Zero-shot learning enables models to generalize to new categories or tasks for which no β¦
self-supervised
Definition
Self-supervised learning is a subset of machine learning where the supervision signal is β¦
multi-agent
Definition
Multi-agent systems consist of several independent, intelligent entities that perceive β¦
on-policy
Definition
On-policy algorithms require that the agent learns directly from the actions taken by its β¦
long-horizon
Definition
Long-horizon problems involve sequences of actions where the impact of early decisions β¦
diffusion-based
Definition
Diffusion-based models are a class of generative AI that create new data samples by β¦
continuous-time
Definition
Continuous-time models describe system dynamics using differential equations, allowing β¦
Wasserstein
Definition
The Wasserstein distance, also known as Earth Mover’s Distance, quantifies the β¦
Vector Database
Definition
Vector databases optimize the storage and retrieval of unstructured data by converting it β¦
Transformer
Definition
Introduced in the ‘Attention Is All You Need’ paper, the Transformer β¦
Reinforcement Learning
Definition
Reinforcement Learning (RL) is a branch of machine learning focused on how intelligent β¦
Retrieval-Augmented Generation
Definition
Retrieval-Augmented Generation (RAG) combines the strengths of retrieval-based and β¦
Safety
Definition
AI Safety is a multidisciplinary field focused on preventing adverse outcomes from β¦
Self-Attention
Definition
Self-attention enables models to capture dependencies between all positions in a sequence β¦
Pre-training
Definition
Pre-training is a foundational technique in deep learning where a model learns broad β¦
Prior
Definition
A ‘prior’ represents existing beliefs or historical data regarding a variable β¦
Neural Network
Definition
A neural network is a series of algorithms that endeavors to recognize underlying β¦
Multi-Head Attention
Definition
Multi-Head Attention extends the standard attention mechanism by running it multiple β¦
Mamba
Definition
Mamba represents a significant advancement in sequence modeling by introducing a β¦
Latent
Definition
In machine learning, latent variables are unobserved factors that influence observed β¦
LoRA
Definition
LoRA freezes pre-trained model weights and inserts trainable decomposition matrices into β¦
Langevin
Definition
Langevin dynamics incorporates random noise and damping forces to explore energy β¦
Group
Definition
In mathematics and theoretical computer science, a group is a set G together with a β¦
Diffusion
Definition
Diffusion models are a class of generative AI that learn to reverse a stochastic process β¦
Causal
Definition
In artificial intelligence, causal modeling seeks to understand how interventions on one β¦
Beyond
Definition
In the context of AI terminology, ‘beyond’ often describes emerging paradigms β¦
Carlo
Definition
Monte Carlo methods are essential techniques in AI and statistics for approximating β¦
Bayesian
Definition
Bayesian approaches in AI use probability theory to update the likelihood of hypotheses β¦
Convolutional Neural Network
Definition
Convolutional Neural Networks (CNNs) are designed to automatically and adaptively learn β¦
Backpropagation
Definition
Backpropagation, short for backward propagation of errors, is a method used in artificial β¦
AI Safety
Definition
AI safety encompasses research and practices aimed at ensuring that autonomous systems β¦
Alignment
Definition
Alignment focuses on making sure AI systems do what humans actually want, rather than β¦