Deep learningDeep learning is part of a broader family of machine learning methods, which is based on artificial neural networks with representation learning. The adjective "deep" in deep learning refers to the use of multiple layers in the network. Methods used can be either supervised, semi-supervised or unsupervised.
Feature learningIn machine learning, feature learning or representation learning is a set of techniques that allows a system to automatically discover the representations needed for feature detection or classification from raw data. This replaces manual feature engineering and allows a machine to both learn the features and use them to perform a specific task. Feature learning is motivated by the fact that machine learning tasks such as classification often require input that is mathematically and computationally convenient to process.
Mandarin (bureaucrat)A mandarin () was a bureaucrat scholar in the history of China, Korea and Vietnam. The term is generally applied to the officials appointed through the imperial examination system; it sometimes includes the eunuchs also involved in the governance of the above realms. The English term comes from the Portuguese mandarim (spelled in Old Portuguese as mandarin, ˌmɐ̃dɐˈɾĩ). The Portuguese word was used in one of the earliest Portuguese reports about China: letters from the imprisoned survivors of the Tomé Pires' embassy, which were most likely written in 1524, and in Castanheda's História do descobrimento e conquista da Índia pelos portugueses (c.
Artificial neural networkArtificial neural networks (ANNs, also shortened to neural networks (NNs) or neural nets) are a branch of machine learning models that are built using principles of neuronal organization discovered by connectionism in the biological neural networks constituting animal brains. An ANN is based on a collection of connected units or nodes called artificial neurons, which loosely model the neurons in a biological brain. Each connection, like the synapses in a biological brain, can transmit a signal to other neurons.
Extreme learning machineExtreme learning machines are feedforward neural networks for classification, regression, clustering, sparse approximation, compression and feature learning with a single layer or multiple layers of hidden nodes, where the parameters of hidden nodes (not just the weights connecting inputs to hidden nodes) need to be tuned. These hidden nodes can be randomly assigned and never updated (i.e. they are random projection but with nonlinear transforms), or can be inherited from their ancestors without being changed.
CantoneseCantonese () is a language within the Chinese (Sinitic) branch of the Sino-Tibetan languages originating from the city of Guangzhou (historically known as Canton) and its surrounding Pearl River Delta. It is the traditional prestige variety of the Yue Chinese group, which has over 82.4 million native speakers. While the term Cantonese specifically refers to the prestige variety, it is often used to refer to the entire Yue subgroup of Chinese, including related but partially mutually intelligible varieties like Taishanese.
Standard Chinese phonologyThis article summarizes the phonology (the sound system, or in more general terms, the pronunciation) of Standard Chinese (Standard Mandarin). Standard Chinese phonology is based on the Beijing dialect of Mandarin. Actual pronunciation varies widely among speakers, as they introduce elements of their native varieties (although television and radio announcers are chosen for their ability to produce the standard variety). Elements of the sound system include not only the segments – the vowels and consonants – of the language but also the tones that are applied to each syllable.
Radial basis function networkIn the field of mathematical modeling, a radial basis function network is an artificial neural network that uses radial basis functions as activation functions. The output of the network is a linear combination of radial basis functions of the inputs and neuron parameters. Radial basis function networks have many uses, including function approximation, time series prediction, classification, and system control. They were first formulated in a 1988 paper by Broomhead and Lowe, both researchers at the Royal Signals and Radar Establishment.
Evaluation strategyIn a programming language, an evaluation strategy is a set of rules for evaluating expressions. The term is often used to refer to the more specific notion of a parameter-passing strategy that defines the kind of value that is passed to the function for each parameter (the binding strategy) and whether to evaluate the parameters of a function call, and if so in what order (the evaluation order). The notion of reduction strategy is distinct, although some authors conflate the two terms and the definition of each term is not widely agreed upon.
Written CantoneseWritten Cantonese is the most complete written form of Chinese after that for Mandarin Chinese and Classical Chinese. Written Chinese was originally developed for Classical Chinese, and was the main literary language of China until the 19th century. Written vernacular Chinese first appeared in the 17th century, and a written form of Mandarin became standard throughout China in the early 20th century. Cantonese is a common language in places like Hong Kong and Macau.
