3,135 articles
Mythic (company)
Mythic, also known as Mythic AI, is an American semiconductor company in Austin, Texas, founded in 2012, that makes energy-efficient analog compute-in-memory processors for AI inference.
N-BEATS
N-BEATS is a deep neural architecture for univariate time series forecasting, introduced in 2019 by researchers at Element AI and Mila including Yoshua Bengio, and published at ICLR 2020.
N-gram
An n-gram is a contiguous sequence of n items from a text or speech stream, and n-gram models were the dominant form of statistical language modeling for decades.
N-gram language model
An n-gram language model is a statistical model that estimates the probability of a word sequence by counting how often word sequences appear in training data.
Nadam
Nadam, short for Nesterov-accelerated Adaptive Moment Estimation, is an optimization algorithm for training neural networks that combines Adam with Nesterov momentum, introduced by Timothy Dozat in 2016.
Naive Bayes classifier
The naive Bayes classifier is a fast machine learning algorithm that applies Bayes' theorem assuming features are independent, famously used for spam filtering and document classification.
Named-entity recognition
Named-entity recognition (NER), also known as entity extraction, is a natural language processing task that finds proper names in text and classifies each entity's type.
NARX model
The NARX model (Nonlinear AutoRegressive with eXogenous inputs) predicts a time series from its own past values and past external input signals, using a nonlinear function fitted to data.
NASA Planetary Data System
The NASA Planetary Data System (PDS) is a long-term archive of digital data from NASA's planetary missions, providing access to more than 50 years of planetary science.
NATGRID
NATGRID (National Intelligence Grid) is an Indian intelligence-sharing platform under the Ministry of Home Affairs, conceived after the 2008 Mumbai attacks and operational since 2020 for counter-terrorism investigations.
National AI Research Institutes
The National AI Research Institutes are a US program led by the National Science Foundation, launched in 2020, funding 29 distributed artificial intelligence research institutes.
National Data Protection Authority of Brazil
The National Data Protection Authority of Brazil (ANPD) is the federal agency that enforces the General Personal Data Protection Law (LGPD), created in 2018 and operating since 2020.
National Database and Registration Authority
The National Database and Registration Authority (NADRA) is Pakistan's federal agency for citizen registration, established on 10 March 2000, which maintains the national database behind identity cards and biometric verification.
National identification number
A national identification number, also called a national ID or national identity number, is a unique number a government issues to identify a person, typically assigned once for life.
National identity card (Bangladesh)
The National identity card of Bangladesh (জাতীয় পরিচয়পত্র, NID) is the identity document issued to citizens by the Election Commission, serving as standard proof of identity.
National Instant Criminal Background Check System
The National Instant Criminal Background Check System, or NICS, is the FBI-run federal system, launched in 1998 under the Brady Act, that screens firearm and explosive buyers.
National Insurance number
A National Insurance number (NINO) is a unique personal account number used throughout life in the United Kingdom to record National Insurance contributions and tax, with format QQ123456B.
National Register of Citizens
The National Register of Citizens (NRC) is the register of Indian citizens for Assam, first compiled in 1951 and updated in 2019 under Supreme Court supervision.
National Registration Identity Card
The National Registration Identity Card, or NRIC, is the compulsory identity card issued to Singapore citizens and permanent residents, who register at 15 and re-register at 30 and 55.
Natural gradient
The natural gradient is the steepest ascent direction of a function under the Fisher information metric, computed as the ordinary gradient multiplied by the inverse Fisher matrix.
Natural gradient descent
Natural gradient descent is an optimization method introduced by Shun-ichi Amari in 1998 that rescales the gradient by the inverse Fisher information matrix, following steepest descent on probability distributions.
Natural language generation
Natural language generation (NLG), also called language generation, is the area of natural language processing that produces readable text or speech from non-linguistic input like structured records.
Natural language inference
Natural language inference (NLI) is a natural language processing task in which a model decides whether a premise entails, contradicts, or neither implies a hypothesis.
Natural language processing
Natural language processing (NLP) is the field of computing that enables machines to recognize, understand, and generate human text and speech by combining computational linguistics with machine learning.
Natural Questions
Natural Questions, or NQ, is a question answering dataset built by Google AI from real Google search queries paired with human-annotated answers on Wikipedia pages, released in 2019.
NCCL
NCCL (NVIDIA Collective Communications Library) is a NVIDIA library of multi-GPU and multi-node communication primitives, such as all-reduce and broadcast, optimized for NVIDIA GPUs and networking.
Nearest neighbor algorithm
A nearest neighbor algorithm answers a query by finding the stored data points closest to it under a distance metric, voting in classification or averaging in regression.
Nearest neighbor search
Nearest neighbor search, also called the post-office problem, is an algorithmic problem in computational geometry: preprocessing points so a query finds the closest one without computing every distance.
Negative sampling (machine learning)
Negative sampling is a machine learning training technique that replaces expensive softmax normalization with binary classification, distinguishing a positive example from a few random negatives.
Nelder–Mead method
The Nelder–Mead method, or downhill simplex method, is a derivative-free optimization algorithm published in 1965 that minimizes a function of n variables using a simplex.