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.
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.
Indo-European languagesThe Indo-European languages are a language family native to the overwhelming majority of Europe, the Iranian plateau, and the northern Indian subcontinent. Some European languages of this family—English, French, Portuguese, Russian, Dutch, and Spanish—have expanded through colonialism in the modern period and are now spoken across several continents. The Indo-European family is divided into several branches or sub-families, of which there are eight groups with languages still alive today: Albanian, Armenian, Balto-Slavic, Celtic, Germanic, Hellenic, Indo-Iranian, and Italic; and another nine subdivisions that are now extinct.
Types of artificial neural networksThere are many types of artificial neural networks (ANN). Artificial neural networks are computational models inspired by biological neural networks, and are used to approximate functions that are generally unknown. Particularly, they are inspired by the behaviour of neurons and the electrical signals they convey between input (such as from the eyes or nerve endings in the hand), processing, and output from the brain (such as reacting to light, touch, or heat). The way neurons semantically communicate is an area of ongoing research.
Recurrent neural networkA recurrent neural network (RNN) is one of the two broad types of artificial neural network, characterized by direction of the flow of information between its layers. In contrast to uni-directional feedforward neural network, it is a bi-directional artificial neural network, meaning that it allows the output from some nodes to affect subsequent input to the same nodes. Their ability to use internal state (memory) to process arbitrary sequences of inputs makes them applicable to tasks such as unsegmented, connected handwriting recognition or speech recognition.
Convolutional neural networkConvolutional neural network (CNN) is a regularized type of feed-forward neural network that learns feature engineering by itself via filters (or kernel) optimization. Vanishing gradients and exploding gradients, seen during backpropagation in earlier neural networks, are prevented by using regularized weights over fewer connections. For example, for each neuron in the fully-connected layer 10,000 weights would be required for processing an image sized 100 × 100 pixels.
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.
Proto-Indo-European languageProto-Indo-European (PIE) is the reconstructed common ancestor of the Indo-European language family. No direct record of Proto-Indo-European exists; its proposed features have been derived by linguistic reconstruction from documented Indo-European languages. Far more work has gone into reconstructing PIE than any other proto-language, and it is the best understood of all proto-languages of its age.
Lexical functional grammarLexical functional grammar (LFG) is a constraint-based grammar framework in theoretical linguistics. It posits two separate levels of syntactic structure, a phrase structure grammar representation of word order and constituency, and a representation of grammatical functions such as subject and object, similar to dependency grammar. The development of the theory was initiated by Joan Bresnan and Ronald Kaplan in the 1970s, in reaction to the theory of transformational grammar which was current in the late 1970s.
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.
Languages of EuropeMost languages of Europe belong to the Indo-European language family. Out of a total European population of 744 million as of 2018, some 94% are native speakers of an Indo-European language. Within Indo-European, the three largest phyla in Europe are Romance, Germanic, and Slavic; they have more than 200 million speakers each and together account for close to 90% of Europeans.
Natural language processingNatural language processing (NLP) is an interdisciplinary subfield of linguistics and computer science. It is primarily concerned with processing natural language datasets, such as text corpora or speech corpora, using either rule-based or probabilistic (i.e. statistical and, most recently, neural network-based) machine learning approaches. The goal is a computer capable of "understanding" the contents of documents, including the contextual nuances of the language within them.
PhonotacticsPhonotactics (from Ancient Greek phōnḗ "voice, sound" and taktikós "having to do with arranging") is a branch of phonology that deals with restrictions in a language on the permissible combinations of phonemes. Phonotactics defines permissible syllable structure, consonant clusters and vowel sequences by means of phonotactic constraints. Phonotactic constraints are highly language-specific. For example, in Japanese, consonant clusters like /st/ do not occur.
Learning classifier systemLearning classifier systems, or LCS, are a paradigm of rule-based machine learning methods that combine a discovery component (e.g. typically a genetic algorithm) with a learning component (performing either supervised learning, reinforcement learning, or unsupervised learning). Learning classifier systems seek to identify a set of context-dependent rules that collectively store and apply knowledge in a piecewise manner in order to make predictions (e.g. behavior modeling, classification, data mining, regression, function approximation, or game strategy).
Generative grammarGenerative grammar, or generativism ˈdʒɛnərətɪvɪzəm, is a linguistic theory that regards linguistics as the study of a hypothesised innate grammatical structure. It is a biological or biologistic modification of earlier structuralist theories of linguistics, deriving ultimately from glossematics. Generative grammar considers grammar as a system of rules that generates exactly those combinations of words that form grammatical sentences in a given language.
Language processing in the brainIn psycholinguistics, language processing refers to the way humans use words to communicate ideas and feelings, and how such communications are processed and understood. Language processing is considered to be a uniquely human ability that is not produced with the same grammatical understanding or systematicity in even human's closest primate relatives. Throughout the 20th century the dominant model for language processing in the brain was the Geschwind-Lichteim-Wernicke model, which is based primarily on the analysis of brain-damaged patients.
Japanese languageis the principal language of the Japonic language family spoken by the Japanese people. It has around 128 million speakers, primarily in Japan, the only country where it is the national language, and within Japanese diaspora worldwide. Japonic family also includes the Ryukyuan languages and the variously classified Hachijō language. There have been many attempts to group the Japonic languages with other families such as the Ainu, Austroasiatic, Koreanic, and the now-discredited Altaic, but none of these proposals has gained widespread acceptance.
BackpropagationAs a machine-learning algorithm, backpropagation performs a backward pass to adjust the model's parameters, aiming to minimize the mean squared error (MSE). In a single-layered network, backpropagation uses the following steps: Traverse through the network from the input to the output by computing the hidden layers' output and the output layer. (the feedforward step) In the output layer, calculate the derivative of the cost function with respect to the input and the hidden layers.
PhoneticsPhonetics is a branch of linguistics that studies how humans produce and perceive sounds, or in the case of sign languages, the equivalent aspects of sign. Linguists who specialize in studying the physical properties of speech are phoneticians. The field of phonetics is traditionally divided into three sub-disciplines based on the research questions involved such as how humans plan and execute movements to produce speech (articulatory phonetics), how various movements affect the properties of the resulting sound (acoustic phonetics), or how humans convert sound waves to linguistic information (auditory phonetics).
InformationInformation is an abstract concept that refers to that which has the power to inform. At the most fundamental level, information pertains to the interpretation (perhaps formally) of that which may be sensed, or their abstractions. Any natural process that is not completely random and any observable pattern in any medium can be said to convey some amount of information. Whereas digital signals and other data use discrete signs to convey information, other phenomena and artefacts such as analogue signals, poems, pictures, music or other sounds, and currents convey information in a more continuous form.
