Tuesday, April 28, 2026
- Fully Sharded Data Parallel (FSDP)v4Fully Sharded Data Parallel (FSDP) is a distributed training technique implemented in PyTorch that shards a model's parameters, gradients, and optimizer states across data-parallel workers, allowing models…
- ControlNetv4ControlNet is a neural network architecture that adds spatial and structural control to large pretrained text-to-image diffusion models.
- Amazon SageMakerv7Amazon SageMaker is Amazon Web Services' fully managed machine learning platform for building, training, and deploying models at scale, first launched at AWS re:Invent on November 29, 2017 and rebranded in…
- LessWrongv5LessWrong is a community blog and online forum focused on human rationality, cognitive biases, decision theory, the philosophy of science, and AI safety.
- Snorkelv3Snorkel is an open-source software framework and methodology for programmatic data labeling that started at Stanford University in 2015 and is licensed under Apache 2.0.
- Concept driftv5Concept drift is the change over time in the statistical relationship between a model's inputs and its target, formally when the joint distribution P(X, Y) (and in the most damaging case the conditional P(Y |…
- Focal lossv5Focal loss is a loss function that reshapes standard cross-entropy loss by adding a (1 - p_t)^gamma modulating factor, which down-weights well-classified (easy) examples so that training concentrates on hard
- Algorithmic fairnessv4Algorithmic fairness is the study of how automated decision systems can be made to produce decisions that are equitable across protected attributes such as race, gender, age, religion, and disability.
- Edge computingv4Edge computing is a distributed computing paradigm that runs computation and data storage close to where data is generated, at the "edge" of the network
- Information theoryv4Information theory is the mathematical study of the quantification, storage, and communication of information, founded by Claude Shannon in his 1948 paper "A Mathematical Theory of Communication." Shannon…
- ICMLv4ICML, the International Conference on Machine Learning, is one of the three top-tier academic conferences in machine learning, alongside NeurIPS and ICLR, and is organized annually by the International Machine…
- Cloud computingv3Cloud computing is the on-demand availability of computer system resources, especially data storage and computing power, delivered over the internet without active management by the end user.
- Amazon Alexav4Amazon Alexa is a virtual assistant developed by Amazon, first introduced on November 6, 2014, alongside the Amazon Echo smart speaker, and rebuilt in 2025 as a generative AI assistant called Alexa+ that runs…
- Marvin Minskyv5Marvin Lee Minsky (August 9, 1927 to January 24, 2016) was an American cognitive scientist and computer scientist who was one of the founders of artificial intelligence as a field, co-founded the MIT…
- PASCAL VOCv3PASCAL VOC (Pattern Analysis, Statistical Modelling and Computational Learning Visual Object Classes) is a long-running benchmark dataset and annual challenge for object recognition, object detection…
- Bayes' theoremv4Bayes' theorem (also called Bayes' rule or Bayes' law) is a fundamental theorem of probability theory that describes how to update the probability of a hypothesis given new evidence.
- Integrated Gradientsv3Integrated Gradients (IG) is a feature-attribution method for explainable AI that explains a neural network prediction by assigning each input feature an importance score
- fastTextv4fastText is an open-source library for learning word embeddings and performing text classification, developed by Facebook AI Research (FAIR) and released to the public on August 18, 2016.
- Siriv5Siri is the voice assistant developed by Apple Inc. that launched on the iPhone 4S on October 14, 2011, making it the first mainstream voice assistant shipped on a smartphone.
- CART algorithmv3The CART algorithm (Classification And Regression Trees) is a non-parametric supervised learning method that builds a binary decision tree from labelled training data, using Gini impurity to split…
- Microsoft Researchv7Microsoft Research (MSR) is Microsoft's industrial research organization. Established in 1991, it conducts fundamental and applied research in computing and other sciences through regional laboratories and…
- Effective Altruismv3Effective altruism (often abbreviated EA) is a philosophical and social movement that uses evidence and careful reasoning to identify the most effective ways to benefit others
- Sentence-BERT (SBERT)v3Sentence-BERT (SBERT) is a modification of the pretrained BERT transformer network that produces semantically meaningful, fixed-size sentence embeddings comparable with simple cosine similarity.
- Variational Inferencev4Variational inference (VI), also called variational Bayes (VB), is a method in machine learning and statistics that approximates an intractable posterior distribution by turning Bayesian inference into an…
- Allen Institute for AIv5The Allen Institute for AI (branded since the early 2020s as Ai2, and historically abbreviated AI2) is a Seattle-based non-profit artificial intelligence research institute, founded in 2014 by the late…
- Nick Bostromv3Nick Bostrom (born Niklas Boström, 10 March 1973) is a Swedish-born philosopher best known for the 2014 book Superintelligence: Paths, Dangers, Strategies, the 2003 simulation argument, and the…
- Markov Chain Monte Carlov4Markov Chain Monte Carlo (MCMC) is a class of algorithms for drawing samples from a probability distribution by constructing a Markov chain whose stationary distribution equals the target distribution.
- Gaussian Processv4A Gaussian process (GP) is a probabilistic machine learning model defined as a collection of random variables, any finite number of which have a joint Gaussian distribution.
- Model Predictive Controlv4Model Predictive Control (MPC), also called receding horizon control (RHC), is a feedback control method that, at every sampling instant, solves a finite horizon optimal control problem using the current…
- Monte Carlo Tree Searchv6Monte Carlo Tree Search (MCTS) is a heuristic search algorithm for sequential decision-making that finds strong actions by running many simulated playthroughs of a problem and aggregating their outcomes into a…
- John McCarthyv4John McCarthy (September 4, 1927 to October 24, 2011) was an American computer scientist who coined the term "artificial intelligence" in 1955, organized the 1956 Dartmouth Conference that founded the field…
- BART (language model)v4BART (an acronym for Bidirectional and Auto-Regressive Transformers) is a transformer-based encoder-decoder language model introduced by Mike Lewis, Yinhan Liu, Naman Goyal, Marjan Ghazvininejad, Abdelrahman…
- Chinchillav7Chinchilla is a 70-billion-parameter transformer large language model and an accompanying family of compute-optimal scaling laws, both introduced in the March 2022 paper Training Compute-Optimal Large Language…
Monday, April 27, 2026
- Chatbotv5A chatbot is a software application that simulates conversation with human users through text or voice, ranging from simple rule-based programs that match keywords to canned replies, to systems built on a…
- Autonomous Mobile Robotv6An autonomous mobile robot (AMR) is a category of robot that moves through unstructured or partially structured environments without relying on fixed physical guides such as magnetic tape, embedded wires…
- CatBoostv3CatBoost is an open-source gradient boosted decision trees library developed by Yandex and released to the public on July 18, 2017.
- Quadruped Robotv5A quadruped robot is a four-legged robotic system that uses dynamic, articulated legs to walk, trot, run, climb, and traverse uneven terrain.
- Yaskawa Electricv4Yaskawa Electric Corporation (株式会社安川電機, Kabushiki-gaisha Yasukawa Denki) is a Japanese industrial automation company, founded in 1915 and headquartered in Kitakyushu, Fukuoka Prefecture, that is one of the…
