Sunday, July 12, 2026
- Termination conditionv6See also: Machine learning terms A termination condition, also called a stopping criterion, convergence criterion, or halting condition, is a rule that decides...
- Supervised Machine Learningv9See also: Machine learning terms Supervised machine learning is a branch of machine learning in which a model learns a mapping from inputs to outputs by...
- Scalarv8See also: vector, matrix, tensor, linear algebra, gradient descent A scalar is a single numerical value, a quantity with magnitude but no direction, and the...
- Tensor Rankv5The rank of a tensor, also referred to as its order or degree, is the number of dimensions (axes or indices) needed to describe the tensor. A scalar has rank...
- Unsupervised learningv5Unsupervised learning is a branch of machine learning in which algorithms identify patterns, structures, and relationships in data without relying on labeled...
- True negativev8A true negative (TN) is a case that a binary classification model correctly predicts as belonging to the negative class: the true label is negative and the...
- Operation (op)v7See also: Machine learning terms In machine learning, an operation (often abbreviated as op) is a basic computational unit that manipulates data, typically...
- Post-trainingv6Post-training is the stage of large language model (LLM) development that comes after pre-training and turns a raw, general-purpose base model into an aligned,...
- Parameter Server (PS)v5See also: Distributed training, Machine learning systems The Parameter Server (PS) is a distributed system architecture for training large machine learning...
- Rectified Linear Unit (ReLU)v9See also: Activation function, Deep learning, Neural network The Rectified Linear Unit (ReLU) is the most widely used activation function in deep learning,...
- Rewardv7See also: Reinforcement Learning, Policy, Q-Learning, Bellman Equation In reinforcement learning (RL), a reward is a scalar feedback signal that an environment...
- Replay Bufferv5A replay buffer (also called an experience replay buffer or replay memory) is a fixed-size memory that stores an off-policy reinforcement learning agent's past...
- One-Hot Encodingv7See also: Machine learning terms One-hot encoding is a data preprocessing technique that converts a categorical variable with distinct categories into ...
- Minority classv5In an imbalanced classification problem, the minority class is the class label with far fewer training examples than the others, and it is almost always the...
- Logistic Regressionv11See also: Machine learning terms Logistic regression is a statistical method that models the probability of a binary (yes/no) outcome as a function of one or...
- Gradient Boostingv9See also: Machine learning terms Gradient boosting is an ensemble machine learning technique that builds a predictive model by combining many weak learners,...
- Incompatibility of Fairness Metricsv4The incompatibility of fairness metrics (also called the impossibility theorem of fairness or fairness trade-offs) is the proven mathematical result that...
- Generative Modelv7See also: Machine learning terms, Discriminative model A generative model is a class of statistical and machine learning model that learns the joint...
- Imbalanced Datasetv5An imbalanced dataset is a dataset used in machine learning where the classification categories are not approximately equally represented, so that one class...
- Hierarchical Clusteringv6Hierarchical clustering is an unsupervised learning method that groups data into a tree of nested clusters, building the hierarchy by repeatedly merging the...
- Convolutionv8See also: Machine learning terms, Convolutional layer, Convolutional filter Convolution is a mathematical operation that combines two functions to produce a...
- Counterfactual Fairnessv7Counterfactual fairness is a formal definition of algorithmic fairness rooted in causal inference: a prediction is counterfactually fair toward an individual...
- Experience Replayv6See also: Reinforcement Learning, Deep Q-Network (DQN), Q-Learning, Replay Buffer Experience replay is a reinforcement learning technique in which an agent...
- Epsilon Greedy Policyv4See also: Machine learning terms, Reinforcement Learning, Q-Learning The epsilon-greedy policy (also written as ε-greedy) is a simple action-selection rule for...
- Demographic Parityv7Demographic parity, also called statistical parity or acceptance rate parity, is a fairness criterion in machine learning that requires a model's predictions...
- Confusion Matrixv6A confusion matrix is a table that summarizes the performance of a classification model by tabulating its predicted class labels against the actual class...
- Coverage Biasv4Coverage bias is a type of selection bias that occurs when the method used to collect data systematically excludes part of the target population, so the sample...
- Bucketingv8Bucketing, also called binning or discretization, is a feature engineering technique in machine learning that converts a continuous feature into a small number...
- Model Capacityv4Model capacity is the size and richness of the family of functions a machine learning model can represent and learn, which determines how complex a pattern the...
- Stabilityv5See also: Machine learning terms and Stability AI Stability in machine learning is the property that a learning algorithm or trained model produces similar...
- AUC (Area Under the ROC Curve)v6AUC (Area Under the ROC Curve) is a classifier evaluation metric equal to the probability that a model ranks a randomly chosen positive instance higher than a...
- Dimension Reductionv9See also: Machine learning terms Dimensionality reduction, also known as dimension reduction, is the process of transforming data from a high-dimensional space...
- Squared Hinge Lossv7Squared hinge loss (also called L2 hinge loss or L2-loss) is a loss function used in machine learning for classification tasks, most commonly in support vector...
- L1 Lossv5L1 loss is a regression loss function equal to the average of the absolute differences between predicted values and target values, written as . It is also...
- BERTv11BERT (Bidirectional Encoder Representations from Transformers) is a transformer-based encoder-only language model developed by researchers at Google AI...
- Average Precisionv6See also: precision, recall, F1 score, confusion matrix, AUC, precision-recall curve Average precision (AP) is an evaluation metric that summarizes the...
- Visual Autoregressive modeling (VAR)v2Visual Autoregressive modeling (VAR) is an image generation paradigm, introduced in 2024, that reframes autoregressive image synthesis as coarse-to-fine...
- VQ-VAE (Vector Quantized Variational Autoencoder)v3VQ-VAE (Vector Quantized Variational Autoencoder) is a generative neural network that compresses data into a grid or sequence of discrete tokens drawn from a...
- PEER (Parameter Efficient Expert Retrieval / Mixture of a Million Experts)v2PEER, short for Parameter Efficient Expert Retrieval, is a neural network layer for Transformer models that replaces the dense feed-forward block with a sparse...
- Lightning Attentionv3Lightning Attention is an IO-aware (input/output aware) implementation of linear attention that lets the method reach its theoretical linear-time complexity in...
- SoundStreamv5SoundStream is an end-to-end neural audio codec introduced by Google Research in July 2021 that compresses speech, music, and general audio at low-to-medium...
- Retentive Network (RetNet)v3See also: Transformer, Mamba, RWKV, Linear Attention, Microsoft Research RetNet (Retentive Network) is a sequence-modeling architecture proposed by Microsoft...
- KL Divergence (Kullback-Leibler Divergence)v3Kullback-Leibler divergence, often abbreviated KL divergence and written , is a measure of how one probability distribution P differs from a second reference...
- ReLUv9See also: Machine learning terms ReLU (Rectified Linear Unit) is an activation function used in neural networks, defined by the formula : it passes positive...
- Voiceboxv3Voicebox is a non-autoregressive, text-conditioned generative model for speech developed by Meta AI Research and announced on June 16, 2023. It is trained with...
- Surge AIv4Surge AI (legal entity Surge Labs Inc., often stylized SurgeHQ) is an American data annotation and human evaluation company headquartered in San Francisco,...
- Sulu.be Stevev5--- General information Sulu.be (Slightly Overdone Robots) Designer Humanoid robot (social/character) Country of origin 2014 Height 100 kg (220...
- Loss Curvev6See also: Machine learning terms, Loss function A loss curve is a plot that shows the value of a loss function over the course of training a machine learning...
- Lepton AIv2Subsidiary of NVIDIA (since 2025); formerly private company Industry 2023 Founders Cupertino / San Francisco Bay Area, California, United States Key...
- Wisdom of the Crowdv4Wisdom of the crowd is the observation that the aggregate judgment of a large group of individuals often produces more accurate estimates or decisions than any...
- Westwood Roboticsv5--- Industry January 2018 Founder Los Angeles, California, United States Key people BEAR actuators, BRUCE robot, THEMIS humanoid robot Parent lab ...
- Kernel Support Vector Machines (KSVMs)v5See also: Machine learning terms A kernel support vector machine (kernel SVM, or KSVM) is a supervised learning algorithm that finds the maximum-margin...
- SkyWalker 2v5--- General information EIR Technology Full company name China Unveiled Deployed (factories, industrial parks) Price eir.com.cn Specification ...
- Double Descentv3Double descent is a phenomenon in machine learning and statistical learning theory in which a model's test error, plotted against increasing model complexity,...
Saturday, July 11, 2026
- Batch Sizev11In machine learning, batch size is the hyperparameter that sets how many training examples a model processes together before it updates its parameters with one...
- Accuracyv11See also: machine learning terms, confusion matrix, precision, recall, F1 score Accuracy is a classification metric that measures the fraction of predictions a...
- TIES-Mergingv3TIES-Merging is a training-free model merging method that combines several models fine-tuned from a shared pre-trained checkpoint into one multitask model...
- Hyenav4Hyena is a sub-quadratic, attention-free neural sequence operator that replaces the self-attention operator of the Transformer with a recurrence of long,...
- Normal distributionv3The normal distribution, also called the Gaussian distribution, is a continuous probability distribution defined by two parameters, a mean and a variance ,...
