Artificial neural networks

computational model used in machine learning, based on connected, hierarchical functions

artificial intelligence model capable of generating content in response to a prompt

type of large language model

In machine learning, the perceptron is an algorithm for supervised learning of binary classifiers. A binary classifier is a function that can decide whether or not an input, represented by a vector of numbers, belongs to some specific class. It is a type of linear classifier, i.e. a classification algorithm that makes its predictions based on a linear predictor function combining a set of weights with the feature vector.

mathematical function having a characteristic "S"-shaped curve or sigmoid curve

In machine learning, backpropagation is a gradient computation method commonly used for training a neural network in computing parameter updates.

technique in natural language processing that represents words as vectors in a continuous vector space

a function associated to a node in a computational network that defines the output of that node given an input or set of inputs

machine learning technique useful for dimensionality reduction

Word2vec is a technique in natural language processing for obtaining vector representations of words. These vectors capture information about the meaning of the word based on the surrounding words. The word2vec algorithm estimates these representations by modeling text in a large corpus. Once trained, such a model can detect synonymous words or suggest additional words for a partial sentence. Word2vec was developed by Tomáš Mikolov, Kai Chen, Greg Corrado, Ilya Sutskever and Jeff Dean at Google, and published in 2013.

function that maps a k-element real-valued vector to a k-element categorical probability distribution

mathematical function conceived as a crude model

activation function defined as the identity function for positive arguments and zero for negative arguments

machine learning model training problem of greatly diverging gradient magnitudes between earlier and later layers encountered when training neural networks with backpropagation

real-valued function whose value depends only on the distance between the input and some fixed point, which forms a basis for some function space

system developed by Google to increase fluency and accuracy in Google Translate

machine learning combining different information resources, such as images and text

theorem that a feed-forward network with a single hidden layer can approximate continuous functions

machine learning algorithm for vision processing

artificial neural network that mimics real neurons

mechanisms in recurrent neural networks

type of artificial neural network

theory developed by Stephen Grossberg and Gail Carpenter on aspects of how the brain processes information

specialized artificial neural networks that are designed for tasks whose inputs are graphs

computational neural network model based on the principles of quantum mechanics

Strategy within machine learning to avoid overfitting by stopping model training when the error flattens. Alternatively when the difference between the training and validation set increases.

thumb|Animation of seq2seq with Recurrent neural network|RNN and attention mechanism Seq2seq is a family of machine learning approaches used for natural language processing. Originally developed by Lê Viết Quốc, a Vietnamese computer scientist and a machine learning pioneer at Google Brain, this framework has become foundational in many modern AI systems. Applications include language translation, image captioning, conversational models, speech recognition, and text summarization. Seq2seq uses sequence transformation: it turns one sequence into another sequence.

right|thumb|241x241px|Learning inside a single-layer ADALINE thumb|286x286px|Photo of an ADALINE machine, with hand-adjustable weights implemented by rheostats thumb|346x346px|Schematic of a single ADALINE unit ADALINE (Adaptive Linear Neuron or later Adaptive Linear Element) is an early single-layer artificial neural network and the name of the physical device that implemented it. It was developed by professor Bernard Widrow and his doctoral student Marcian Hoff at Stanford University in 1960. It is based on the perceptron and consists of weights, a bias, and a summation function. The weights

recurrent neural network with a sparsely connected hidden layer

thumb|321x321px|LeNet-5 architecture (overview)

artificial neural network

WaveNet is a deep neural network for generating raw audio. It was created by researchers at London-based AI firm DeepMind. The technique, outlined in a paper in September 2016, is able to generate relatively realistic-sounding human-like voices by directly modelling waveforms using a neural network method trained with recordings of real speech. Tests with US English and Mandarin reportedly showed that the system outperforms Google's best existing text-to-speech (TTS) systems, although as of 2016 its text-to-speech synthesis still was less convincing than actual human speech. WaveNet's ability

framework for computation derived from recurrent neural network theory

type of artificial neural network

artificial neural network with connections forming a hierarchical structure, processing data recursively

gradient descent learning rule in machine learning

biological theory of intelligence

type of artificial neural network

Analysis used for machine learning systems

__NOTOC__

Deep learning model structure

type of artificial neural network

approach to artificial intelligence that represents information as vectors of up to thousands of components

Law in machine learning

parallel computing paradigm similar to neural networks, with the difference that communication is allowed between neighbouring units only

model forgetting previously learned information because of new training

family of inductive algorithms

function for machine learning algorithms

artificial neural network architecture

thumb|300px|Sketch of a neuro-fuzzy system implementing a simple Sugeno-Takagi controller In the field of artificial intelligence, the designation neuro-fuzzy refers to combinations of artificial neural networks and fuzzy logic.

2023 text-generating language model

neural network-based evaluation function

type of artificial neural network

computational principle applied in computational models of neural networks

neural-net machine

artificial neural network algorithm

physical implementation of an artificial neural network with optical components

Neutral network

modeling tool for assigning probabilities to events