Saturday, July 11, 2026
- Generalizationv6See also: Machine learning terms, Bias-variance tradeoff Generalization in machine learning is the ability of a trained model to perform accurately on new,...
- L0 Regularizationv5L0 regularization is a regularization technique in machine learning and statistics that penalizes the number of nonzero parameters in a model, a quantity...
- Action (Reinforcement Learning)v9In reinforcement learning (RL), an action is a decision or move made by an agent that affects the state of the environment. At each discrete time step, the...
- RLOO (REINFORCE Leave-One-Out)v3RLOO (REINFORCE Leave-One-Out) is an online reinforcement learning algorithm for aligning large language models with reward signals such as those derived from...
- Muon (optimizer)v4Muon (short for MomentUm Orthogonalized by Newton-Schulz) is a neural-network optimizer that updates the two-dimensional weight matrices of hidden layers by...
- DiLoCov4DiLoCo (Distributed Low-Communication training) is a distributed optimization algorithm for neural networks introduced by Google DeepMind in November 2023 to...
- Zero Moment Point (ZMP)v4The Zero Moment Point (ZMP) is the point on the ground where the horizontal component of the moment generated by the contact reaction force vanishes, leaving...
- RMSPropv4RMSProp (Root Mean Square Propagation) is an adaptive learning-rate optimizer that divides each parameter's gradient by a running root-mean-square of that...
- Monte Carlo Tree Searchv5Monte Carlo Tree Search (MCTS) is a heuristic search algorithm for sequential decision-making that finds strong actions by running many simulated playthroughs...
- TF-IDF (Term Frequency-Inverse Document Frequency)v4TF-IDF (term frequency-inverse document frequency) is a numerical statistic that measures how important a word is to a single document within a larger...
- Causal inferencev3Causal inference is the field of study concerned with drawing conclusions about cause-and-effect relationships from data, answering questions of the form "what...
- Swin Transformerv10The Swin Transformer (Shifted Window Transformer) is a hierarchical vision transformer architecture that computes self-attention within local, non-overlapping...
- Residual connectionv5A residual connection (also called a skip connection or shortcut connection) is a structural element in neural networks that adds the input of a layer or block...
- DPOv9DPO (Direct Preference Optimization) is an alignment technique for large language models that directly optimizes a language model policy from human preference...
- Z-Score Normalizationv8See also: Machine learning terms Z-score normalization, also called standardization, standard score normalization, or z-score scaling, is a data preprocessing...
- Perplexityv9Perplexity has two distinct meanings in the field of artificial intelligence. In natural language processing and information theory, perplexity (often...
- OCR Modelsv6OCR Models are artificial intelligence (AI) systems that convert images of typed, handwritten, or printed text into machine-readable digital text through...
- Out-of-bag evaluation (OOB evaluation)v6See also: Machine learning terms, Bagging, Random forest, Cross-validation Out-of-bag (OOB) evaluation, sometimes called out-of-bag estimation or OOB error, is...
- RNNv8See also: Machine learning terms RNN is the standard abbreviation for recurrent neural network, a class of artificial neural network in which connections...
- Partial derivativev6See also: Machine learning terms A partial derivative measures how a multivariable function changes when one of its inputs is varied while every other input is...
- LoRA (Low-Rank Adaptation)v9LoRA (Low-Rank Adaptation) is a parameter-efficient fine-tuning technique that freezes a pre-trained model's weights and trains small, injected low-rank...
- Item matrixv7See also: Machine learning terms In collaborative filtering and matrix factorization recommender systems, the item matrix (commonly written V, sometimes Q or...
- Hidden Layerv9See also: neural network, input layer, output layer, activation function A hidden layer is a layer of artificial neurons in a neural network that sits between...
- IoUv5See also: Machine learning terms Intersection over Union (IoU), also known as the Jaccard index or Jaccard similarity coefficient, is the standard overlap...
- Leafv4See also: Machine learning terms A leaf (also called a terminal node) is a node in a decision tree that has no children and holds the model's prediction. Every...
- Feedforward Neural Network (FFN)v11A feedforward neural network (FFN), also called a multilayer perceptron (MLP) when it has multiple layers, is a type of artificial neural network in which...
- Clusteringv6See also: Machine learning terms Clustering is an unsupervised learning technique that groups a set of data points into clusters so that points in the same...
- Fairness Metricv6A fairness metric is a quantitative, mathematical measure used to evaluate whether a machine learning model's predictions or decisions treat different...
- Deep Q-Network (DQN)v5Deep Q-Network (DQN) is a reinforcement learning algorithm that uses a deep neural network to approximate the optimal action-value function (Q-function),...
- Trigramv6See also: N-gram, Bigram, Language model A trigram is a contiguous sequence of three items (most often three words) drawn from a sample of text or speech, and...
- Gated DeltaNetv2Gated DeltaNet is a linear attention sequence model that augments the delta rule, a key-value error-correction update used in the earlier DeltaNet...
- muP (Maximal Update Parametrization)v3muP, short for Maximal Update Parametrization (often written muP, μP, or mu-P), is a parametrization scheme for deep neural networks in which a small set of...
- Schedule-Free optimizerv3Schedule-Free is a family of optimization algorithms for deep learning and convex stochastic optimization that matches or exceeds the performance of tuned...
- Control theoryv4Control theory is the mathematical and engineering discipline concerned with designing and analysing systems that achieve desired behaviour through measurement...
- Frechet Inception Distancev4The Frechet Inception Distance (FID) is the standard metric for measuring the quality of images produced by generative models: it computes the Frechet distance...
- t-SNEv7t-distributed stochastic neighbor embedding (t-SNE) is a nonlinear dimensionality reduction technique used primarily for visualizing high-dimensional data in...
- UMAP (Uniform Manifold Approximation and Projection)v4UMAP (Uniform Manifold Approximation and Projection) is a nonlinear dimensionality reduction technique that compresses high-dimensional data into a...
- T5 (language model)v10T5 (Text-to-Text Transfer Transformer) is a family of transformer-based language models released by Google in 2019-2020 that reframes every natural language...
- KV Cachev8A KV cache (key-value cache) is a memory optimization technique used during transformer inference that stores previously computed key and value tensors from...
- Beam searchv6Beam search is a heuristic search algorithm for sequence generation that, at each decoding step, keeps only the top-K highest-scoring partial sequences (where...
- Speculative Decodingv8See also: transformer, large language model, inference, KV cache, autoregressive model, knowledge distillation Speculative decoding is a lossless inference...
- Deep Learningv9Deep learning is a subset of machine learning that uses artificial neural networks with multiple layers to automatically learn representations of data at...
- Training-Serving Skewv8Training-serving skew is a difference between a machine learning model's performance during training and its performance during serving (production inference)....
- Sketchingv6See also: Machine learning terms Sketching is a family of techniques in computer science, machine learning, and database systems that use small probabilistic...
- Subsamplingv6Subsampling is the practice of drawing a smaller subset from a larger collection of data points, training examples, features, or signal values, in order to cut...
- Sequence-to-Sequence Taskv9See also: Machine learning terms, Natural language processing, Recurrent neural network A sequence-to-sequence (seq2seq) task is any machine learning problem...
- Regularization Ratev8The regularization rate (commonly denoted as or alpha) is a hyperparameter that controls the strength of the penalty applied to a model's parameters during...
- Batch Normalizationv9See also: Machine learning terms Batch normalization (often abbreviated BatchNorm or BN) is a technique for improving the speed, stability, and performance of...
- Calibration (machine learning)v5Calibration in machine learning is the property that the probability scores produced by a probabilistic classifier match the empirical frequency of the...
- Semi-Supervised Learningv8See also: Machine learning terms Semi-supervised learning is a machine learning approach that trains a model on a small amount of labeled data together with a...
- Markov Decision Process (MDP)v8See also: Machine learning terms A Markov Decision Process (MDP) is a mathematical framework for modeling sequential decision-making in stochastic...
- Objective functionv5See also: Machine learning terms An objective function is the single scalar-valued quantity that an optimization algorithm tries to minimize or maximize during...
- K-Meansv9See also: Machine learning terms K-means is an unsupervised machine learning clustering algorithm that partitions a dataset into k distinct, non-overlapping...
- Discriminatorv6A discriminator is the neural network in a generative adversarial network (GAN) that is trained to tell real data apart from data produced by the generator,...
- Infini-Attentionv4Infini-attention is an attention mechanism introduced by Google researchers Tsendsuren Munkhdalai, Manaal Faruqui, and Siddharth Gopal in the April 2024 paper...
- Stochastic Gradient Descent (SGD)v8See also: Machine learning terms Stochastic gradient descent (SGD) is an iterative optimization algorithm that updates model parameters using the gradient of...
- Parameterv5In machine learning and statistics, a parameter is an internal variable of a model whose value is learned from data during the training process.[1] Parameters...
- Knowledge Distillationv7Knowledge distillation (also known as model distillation) is a model compression technique in machine learning in which a smaller model, called the student, is...
- Fairness Constraintv5A fairness constraint is an explicit mathematical condition imposed on a machine learning model during training, evaluation, or post-processing that forces its...
- Node (TensorFlow graph)v4See also: Machine learning terms, TensorFlow, Computational graph, Tensor A node in a TensorFlow graph is a single unit of computation, such as a matrix...
- GPT Public Directoryv5--- Information GPT Public Directory Platform GPT Store Model Productivity Description Geoffrey Robichaux OpenAI URL 10 November 2023 Free ...
- Circuit discoveryv3Circuit discovery is a research program in mechanistic interpretability that aims to identify sparse computational subgraphs inside trained neural networks,...
- Training runv3A training run is a single, deliberate instance of training a neural network from scratch (or from a prior checkpoint) on a specified dataset, with a fixed...
- SimPOv3SimPO (Simple Preference Optimization) is a reference-free offline preference learning algorithm for aligning large language models with human preferences. It...
- Mirsee MH3v6--- Manufacturer Industrial teleoperated humanoid robot Country of origin 2025 (third generation) Founders Pre-production (eight prototypes built as...
- Getty Images v. Stability AIv3Getty Images v. Stability AI is a pair of parallel intellectual property lawsuits brought by the visual content licensing company Getty Images against...
- Robert Bosch GmbHv2Robert Bosch GmbH, known as Bosch, is a German engineering and technology company that is the world's largest automotive supplier and one of Europe's largest...
- Size invariancev5See also: Machine learning terms Size invariance, also called scale invariance, is the property of a model, feature, or algorithm that produces the same output...
- Model Specv4The Model Spec is a public document published by openai that defines the intended behavior of the company's language models: how they should follow...
- Lumos LUS 2v5--- General information Lumos Robotics Country of origin 2025 Status $99,000 USD (estimated) Availability lumosbot.tech Round Lead Investors ...
- Chai-1v3Chai-1 is an open multimodal foundation model for biomolecular structure prediction released by the San Francisco startup Chai Discovery on 9 September 2024....
- Random Policyv6See also: Reinforcement Learning, Policy, Epsilon Greedy Policy, Q-Learning A random policy is a reinforcement learning policy that chooses actions from a...
- Linear Regressionv9Linear regression is a statistical method that models the relationship between one or more independent variables (the predictors or features) and a continuous...
- Information Gainv6Information Gain (IG) is a measure from information theory that quantifies the reduction in entropy (uncertainty) achieved by partitioning a dataset on a...
- Decoderv6See also: Encoder, Transformer, Machine learning terms A decoder is the component of a neural network that turns an internal, compressed, or abstract...
- Costv5See also: Machine learning terms In machine learning, cost is the scalar number that summarizes how badly a model is performing on a chunk of data. The...
- Discriminative Modelv6See also: Machine learning, Generative model, Classification A discriminative model is a class of machine learning model that learns the conditional...
- Group Sequence Policy Optimization (GSPO)v2Group Sequence Policy Optimization (GSPO) is a reinforcement learning algorithm for training large language models, introduced by the Qwen team at Alibaba in...
- Gradient checkpointingv4Gradient checkpointing, also called activation checkpointing, activation recomputation, or rematerialization, is a memory-saving technique for training deep...
- LongRoPEv3LongRoPE is a context-window extension technique for large language models (LLMs) that use rotary position embeddings (RoPE). Introduced by researchers at...
- Score matchingv4Score matching is a method for fitting a probabilistic model by matching the gradient of its log-density, the so-called score function , to the same gradient...
- xLSTMv3xLSTM (Extended Long Short-Term Memory) is a recurrent neural network architecture introduced in May 2024 by Maximilian Beck, Korbinian Pöppel, Sepp...
- DoRA (Weight-Decomposed Low-Rank Adaptation)v5DoRA (Weight-Decomposed Low-Rank Adaptation) is a parameter-efficient fine-tuning (PEFT) method for large neural networks introduced in February 2024 by...
- Tanh (hyperbolic tangent)v3The hyperbolic tangent, written tanh, is a smooth, S-shaped activation function that maps any real number into the open interval , passing through the origin...
- Dynamic Programmingv4Dynamic programming (DP) is an algorithmic technique that solves a complex problem by breaking it into simpler overlapping subproblems, solving each subproblem...
- Weighted Alternating Least Squares (WALS)v6Weighted Alternating Least Squares (WALS), also called implicit Alternating Least Squares (iALS) or weighted regularized matrix factorization (WRMF), is a...
- Wasserstein Lossv5Wasserstein loss is a loss function for training generative models that measures the distance between two probability distributions as the Wasserstein-1...
- Output Layerv10See also: neural network, activation function, loss function, hidden layer, softmax, backpropagation The output layer is the final layer of a neural network:...
- Mean Squared Error (MSE)v7See also: Machine learning terms Mean Squared Error (MSE), also called mean squared deviation (MSD), is the average of the squared differences between...
- Feature Vectorv8A feature vector is an n-dimensional, ordered list of numerical values that represents the measurable properties of an object, data point, or observation in a...
- Centroidv5See also: Machine learning terms A centroid is the geometric center of a set of points, computed as the arithmetic mean of their coordinates: each component of...
- Embedding Layerv8An embedding layer is a neural network component that acts as a trainable lookup table, mapping discrete integer indices (such as word IDs, user IDs, or...
- Baggingv6See also: Machine learning terms, Ensemble methods, Random forest, Boosting Bagging, short for bootstrap aggregating, is an ensemble learning technique in...
- Diffusion modelv11A diffusion model is a type of generative model that produces data by learning to reverse a gradual noising process: it is trained so that if Gaussian noise is...
- Task arithmeticv3Task arithmetic is a model-editing technique that steers the behavior of a neural network by adding or subtracting vectors in its weight space. The central...
- LongNetv3LongNet is a transformer variant introduced by Microsoft Research in July 2023 that is designed to scale attention to sequences exceeding one billion tokens...
- Medusav4Medusa is a large language model inference acceleration framework that speeds up text generation by adding multiple lightweight decoding heads on top of an...
- Latent Dirichlet allocationv4Latent Dirichlet allocation (LDA) is a generative probabilistic model that discovers the hidden thematic structure in a collection of documents by treating...
- Policy gradient methodsv3Policy gradient methods are a family of reinforcement learning algorithms that directly parameterise the agent's policy and optimise it by stochastic gradient...
- Hidden Markov Modelv4A Hidden Markov Model (HMM) is a statistical model of sequential data in which an unobserved (hidden) sequence of discrete states follows a Markov process, and...
