Case-based reasoning (CBR), broadly construed, is the process of solving new problems based on the solutions of similar past problems. In everyday life, an auto mechanic who fixes an engine by recalling another car that exhibited similar symptoms is using case-based reasoning. A lawyer who advocates a particular outcome in a trial based on legal precedents or a judge who creates case law is using case-based reasoning. So, too, an engineer copying working elements of nature (practicing biomimicry) is treating nature as a database of solutions to problems. Case-based reasoning is a prominent type of analogy solution making. It has been argued that case-based reasoning is not only a powerful method for computer reasoning, but also a pervasive behavior in everyday human problem solving; or, more radically, that all reasoning is based on past cases personally experienced. This view is related to prototype theory, which is most deeply explored in cognitive science. == Process == Case-based reasoning has been formalized for purposes of computer reasoning as a four-step process: Retrieve: Given a target problem, retrieve cases relevant to solving it from memory. A case consists of a problem, its solution, and, typically, annotations about how the solution was derived. For example, suppose Fred wants to prepare blueberry pancakes. Being a novice cook, the most relevant experience he can recall is one in which he successfully made plain pancakes. The procedure he followed for making the plain pancakes, together with justifications for decisions made along the way, constitutes Fred's retrieved case. Reuse: Map the solution from the previous case to the target problem. This may involve adapting the solution as needed to fit the new situation. In the pancake example, Fred must adapt his retrieved solution to include the addition of blueberries. Revise: Having mapped the previous solution to the target situation, test the new solution in the real world (or a simulation) and, if necessary, revise. Suppose Fred adapted his pancake solution by adding blueberries to the batter. After mixing, he discovers that the batter has turned blue – an undesired effect. This suggests the following revision: delay the addition of blueberries until after the batter has been ladled into the pan. Retain: After the solution has been successfully adapted to the target problem, store the resulting experience as a new case in memory. Fred, accordingly, records his new-found procedure for making blueberry pancakes, thereby enriching his set of stored experiences, and better preparing him for future pancake-making demands. == Comparison to other methods == At first glance, CBR may seem similar to the rule induction algorithms of machine learning. Like a rule-induction algorithm, CBR starts with a set of cases or training examples; it forms generalizations of these examples, albeit implicit ones, by identifying commonalities between a retrieved case and the target problem. If for instance a procedure for plain pancakes is mapped to blueberry pancakes, a decision is made to use the same basic batter and frying method, thus implicitly generalizing the set of situations under which the batter and frying method can be used. The key difference, however, between the implicit generalization in CBR and the generalization in rule induction lies in when the generalization is made. A rule-induction algorithm draws its generalizations from a set of training examples before the target problem is even known; that is, it performs eager generalization. For instance, if a rule-induction algorithm were given recipes for plain pancakes, Dutch apple pancakes, and banana pancakes as its training examples, it would have to derive, at training time, a set of general rules for making all types of pancakes. It would not be until testing time that it would be given, say, the task of cooking blueberry pancakes. The difficulty for the rule-induction algorithm is in anticipating the different directions in which it should attempt to generalize its training examples. This is in contrast to CBR, which delays (implicit) generalization of its cases until testing time – a strategy of lazy generalization. In the pancake example, CBR has already been given the target problem of cooking blueberry pancakes; thus it can generalize its cases exactly as needed to cover this situation. CBR therefore tends to be a good approach for rich, complex domains in which there are myriad ways to generalize a case. In law, there is often explicit delegation of CBR to courts, recognizing the limits of rule based reasons: limiting delay, limited knowledge of future context, limit of negotiated agreement, etc. While CBR in law and cognitively inspired CBR have long been associated, the former is more clearly an interpolation of rule based reasoning, and judgment, while the latter is more closely tied to recall and process adaptation. The difference is clear in their attitude toward error and appellate review. Another name for case-based reasoning in problem solving is symptomatic strategies. It does require à priori domain knowledge that is gleaned from past experience which established connections between symptoms and causes. This knowledge is referred to as shallow, compiled, evidential, history-based as well as case-based knowledge. This is the strategy most associated with diagnosis by experts. Diagnosis of a problem transpires as a rapid recognition process in which symptoms evoke appropriate situation categories. An expert knows the cause by virtue of having previously encountered similar cases. Case-based reasoning is the most powerful strategy, and that used most commonly. However, the strategy won't work independently with truly novel problems, or where deeper understanding of whatever is taking place is sought. An alternative approach to problem solving is the topographic strategy which falls into the category of deep reasoning. With deep reasoning, in-depth knowledge of a system is used. Topography in this context means a description or an analysis of a structured entity, showing the relations among its elements. Also known as reasoning from first principles, deep reasoning is applied to novel faults when experience-based approaches aren't viable. The topographic strategy is therefore linked to à priori domain knowledge that is developed from a more a fundamental understanding of a system, possibly using first-principles knowledge. Such knowledge is referred to as deep, causal or model-based knowledge. Hoc and Carlier noted that symptomatic approaches may need to be supported by topographic approaches because symptoms can be defined in diverse terms. The converse is also true – shallow reasoning can be used abductively to generate causal hypotheses, and deductively to evaluate those hypotheses, in a topographical search. == Criticism == Critics of CBR argue that it is an approach that accepts anecdotal evidence as its main operating principle. Without statistically relevant data for backing and implicit generalization, there is no guarantee that the generalization is correct. However, all inductive reasoning where data is too scarce for statistical relevance is inherently based on anecdotal evidence. == History == CBR traces its roots to the work of Roger Schank and his students at Yale University in the early 1980s. Schank's model of dynamic memory was the basis for the earliest CBR systems: Janet Kolodner's CYRUS and Michael Lebowitz's IPP. Other schools of CBR and closely allied fields emerged in the 1980s, which directed at topics such as legal reasoning, memory-based reasoning (a way of reasoning from examples on massively parallel machines), and combinations of CBR with other reasoning methods. In the 1990s, interest in CBR grew internationally, as evidenced by the establishment of an International Conference on Case-Based Reasoning in 1995, as well as European, German, British, Italian, and other CBR workshops. CBR technology has resulted in the deployment of a number of successful systems, the earliest being Lockheed's CLAVIER, a system for laying out composite parts to be baked in an industrial convection oven. CBR has been used extensively in applications such as the Compaq SMART system and has found a major application area in the health sciences, as well as in structural safety management. There is recent work that develops CBR within a statistical framework and formalizes case-based inference as a specific type of probabilistic inference. Thus, it becomes possible to produce case-based predictions equipped with a certain level of confidence. One description of the difference between CBR and induction from instances is that statistical inference aims to find what tends to make cases similar while CBR aims to encode what suffices to claim similarly.
Quantum machine learning
Quantum machine learning (QML) is the study of quantum algorithms for machine learning. It often refers to quantum algorithms for machine learning tasks which analyze classical data, sometimes called quantum-enhanced machine learning. QML algorithms use qubits and quantum operations to try to improve the space and time complexity of classical machine learning algorithms. Hybrid QML methods involve both classical and quantum processing, where computationally difficult subroutines are outsourced to a quantum device. These routines can be more complex in nature and executed faster on a quantum computer. Furthermore, quantum algorithms can be used to analyze quantum states instead of classical data. The term "quantum machine learning" is sometimes used to refer classical machine learning methods applied to data generated from quantum experiments (i.e. machine learning of quantum systems), such as learning the phase transitions of a quantum system or creating new quantum experiments. QML also extends to a branch of research that explores methodological and structural similarities between certain physical systems and learning systems, in particular neural networks. For example, some mathematical and numerical techniques from quantum physics are applicable to classical deep learning and vice versa. Furthermore, researchers investigate more abstract notions of learning theory with respect to quantum information, sometimes referred to as "quantum learning theory". == Machine learning with quantum computers == Quantum-enhanced machine learning refers to quantum algorithms that solve tasks in machine learning, thereby improving and often expediting classical machine learning techniques. Such algorithms typically require one to encode the given classical data set into a quantum computer to make it accessible for quantum information processing. Subsequently, quantum information processing routines are applied and the result of the quantum computation is read out by measuring the quantum system. For example, the outcome of the measurement of a qubit reveals the result of a binary classification task. While many proposals of QML algorithms are still purely theoretical and require a full-scale universal quantum computer to be tested, others have been implemented on small-scale or special purpose quantum devices. === Quantum associative memories and quantum pattern recognition === Early work on quantum associative memories has been done by Dan Ventura and Tony Martinez and by Carlo A. Trugenberger in the late 1990s and early 2000s. Associative (or content-addressable) memories are able to recognize stored content on the basis of a similarity measure, while random access memories are accessed by the address of stored information and not its content. As such they must be able to retrieve both incomplete and corrupted patterns, the essential machine learning task of pattern recognition. Typical classical associative memories store p patterns in the O ( n 2 ) {\displaystyle O(n^{2})} interactions (synapses) of a real, symmetric energy matrix over a network of n artificial neurons. The encoding is such that the desired patterns are local minima of the energy functional and retrieval is done by minimizing the total energy, starting from an initial configuration. Unfortunately, classical associative memories are severely limited by the phenomenon of cross-talk. When too many patterns are stored, spurious memories appear which quickly proliferate, so that the energy landscape becomes disordered and no retrieval is anymore possible. The number of storable patterns is typically limited by a linear function of the number of neurons, p ≤ O ( n ) {\displaystyle p\leq O(n)} . Quantum associative memories (in their simplest realization) store patterns in a unitary matrix U acting on the Hilbert space of n qubits. Retrieval is realized by the unitary evolution of a fixed initial state to a quantum superposition of the desired patterns with probability distribution peaked on the most similar pattern to an input. By its very quantum nature, the retrieval process is thus probabilistic. Because quantum associative memories are free from cross-talk, however, spurious memories are never generated. Correspondingly, they have a superior capacity than classical ones. The number of parameters in the unitary matrix U is O ( p n ) {\displaystyle O(pn)} . One can thus have efficient, spurious-memory-free quantum associative memories for any polynomial number of patterns. If the matrix U is encoded as a unique operator (as opposed as to a sequence of gates as in the circuit model), e.g. by an optical interferometer, the retrieval becomes efficient even for an exponential number of patterns. === Linear algebra simulation with quantum amplitudes === A number of quantum algorithms for machine learning are based on the idea of amplitude encoding, that is, to associate the amplitudes of a quantum state with the inputs and outputs of computations. Since a state of n {\displaystyle n} qubits is described by 2 n {\displaystyle 2^{n}} complex amplitudes, this information encoding can allow for an exponentially compact representation. Intuitively, this corresponds to associating a discrete probability distribution over binary random variables with a classical vector. The goal of algorithms based on amplitude encoding is to formulate quantum algorithms whose resources grow polynomially in the number of qubits n {\displaystyle n} , which amounts to a logarithmic time complexity in the number of amplitudes and thereby the dimension of the input. Many QML algorithms in this category are based on variations of the quantum algorithm for linear systems of equations (colloquially called HHL, after the paper's authors) which, under specific conditions, performs a matrix inversion using an amount of physical resources growing only logarithmically in the dimensions of the matrix. One of these conditions is that a Hamiltonian which entry-wise corresponds to the matrix can be simulated efficiently, which is known to be possible if the matrix is sparse or low rank. For reference, any known classical algorithm for matrix inversion requires a number of operations that grows more than quadratically in the dimension of the matrix (e.g. O ( n 2.373 ) {\displaystyle O{\mathord {\left(n^{2.373}\right)}}} ), but they are not restricted to sparse matrices. Quantum matrix inversion can be applied to machine learning methods in which the training reduces to solving a linear system of equations, for example in least-squares linear regression, the least-squares version of support vector machines, and Gaussian processes. A crucial bottleneck of methods that simulate linear algebra computations with the amplitudes of quantum states is state preparation, which often requires one to initialise a quantum system in a state whose amplitudes reflect the features of the entire dataset. Although efficient methods for state preparation are known for specific cases, this step easily hides the complexity of the task. === Variational quantum algorithms (VQAs) === In a variational quantum algorithm, a classical computer optimizes the parameters used to prepare a quantum state, while a quantum computer is used to do the actual state preparation and measurement. VQAs are considered promising candidates for noisy intermediate-scale quantum computers. Variational quantum circuits (or parameterized quantum circuits) are a popular class of VQAs where the parameters are those used in a fixed quantum circuit. Researchers have studied VQCs to solve optimization problems and find the ground state energy of complex quantum systems, which were difficult to solve using a classical computer. === Quantum binary classifier === Pattern reorganization is one of the important tasks of machine learning, binary classification is one of the tools or algorithms to find patterns. Binary classification is used in supervised learning and in unsupervised learning. In QML, classical bits are converted to qubits and they are mapped to Hilbert space; complex value data are used in a quantum binary classifier to use the advantage of Hilbert space. By exploiting the quantum mechanic properties such as superposition, entanglement, interference the quantum binary classifier produces the accurate result in short period of time. === Quantum machine learning algorithms based on Grover search === Another approach to improving classical machine learning with quantum information processing uses amplitude amplification methods based on Grover's search algorithm, which has been shown to solve unstructured search problems with a quadratic speedup compared to classical algorithms. These quantum routines can be employed for learning algorithms that translate into an unstructured search task, as can be done, for instance, in the case of the k-medians and the k-nearest neighbors algorithms. Other applications include quadratic speedups in the training of perceptrons. An e
Chinchilla (language model)
Chinchilla is a family of large language models (LLMs) developed by the research team at Google DeepMind, presented in March 2022. == Models == It is named "chinchilla" because it is a further development over a previous model family named Gopher. Both model families were trained in order to investigate the scaling laws of large language models. It claimed to outperform GPT-3. It considerably simplifies downstream utilization because it requires much less computer power for inference and fine-tuning. Based on the training of previously employed language models, it has been determined that if one doubles the model size, one must also have twice the number of training tokens. This hypothesis has been used to train Chinchilla by DeepMind. Similar to Gopher in terms of cost, Chinchilla has 70B parameters and four times as much data. Chinchilla has an average accuracy of 67.5% on the Measuring Massive Multitask Language Understanding (MMLU) benchmark, which is 7% higher than Gopher's performance. Chinchilla was still in the testing phase as of January 12, 2023. Chinchilla contributes to developing an effective training paradigm for large autoregressive language models with limited compute resources. The Chinchilla team recommends that the number of training tokens is twice for every model size doubling, meaning that using larger, higher-quality training datasets can lead to better results on downstream tasks. It has been used for the Flamingo vision-language model. == Architecture == Both the Gopher family and Chinchilla family are families of transformer models. In particular, they are essentially the same as GPT-2, with different sizes and minor modifications. Gopher family uses RMSNorm instead of LayerNorm; relative positional encoding rather than absolute positional encoding. The Chinchilla family is the same as the Gopher family, but trained with AdamW instead of Adam optimizer. The Gopher family contains six models of increasing size, from 44 million parameters to 280 billion parameters. They refer to the largest one as "Gopher" by default. Similar naming conventions apply for the Chinchilla family. Table 1 of shows the entire Gopher family: Table 4 of compares the 70-billion-parameter Chinchilla with Gopher 280B.
OrCam device
OrCam devices such as OrCam MyEye are portable, artificial vision devices that allow visually impaired people to understand text and identify objects through audio feedback, describing what they are unable to see. Reuters described an important part of how it works as "a wireless smartcamera" which, when attached outside eyeglass frames, can read and verbalize text, and also supermarket barcodes. This information is converted to spoken words and entered "into the user’s ear." Face-recognition is also part of OrCam's feature set. == Devices == OrCam Technologies Ltd has created three devices; OrCam MyEye 2.0, OrCam MyEye 1, and OrCam MyReader. OrCam My Eye 2.0: OrCam debuted the second-generation model, the OrCam MyEye 2.0 in December 2017. About the size of a finger, the MyEye 2.0 is battery-powered, and has been compressed into a self-contained device. The device snaps onto any eyeglass frame magnetically. Orcam 2.0 is small and light (22.5 grams/0.8 ounces) with functionality to restore independence to the visually impaired. It comes in two versions. The basic model can read text, and a more advanced one adds features such as face recognition and barcode reading. As of July 2023, the retail cost is between $4000 and $6000 (USD). == Clinical Studies == JAMA Ophthalmology: In 2016 JAMA Ophthalmology conducted a study involving 12 legally blind participants to evaluate the usefulness of a portable artificial vision device (OrCam) for patients with low vision. The results showed that the OrCam device improved the patient's ability to perform tasks simulating those of daily living, such as reading a message on an electronic device, a newspaper article or a menu. Wills Eye: Wills Eye was a clinical study designed to measure the impact of the OrCam device on the quality of life of patients with End-stage Glaucoma. The conclusion was that OrCam, a novel artificial vision device using a mini-camera mounted on eyeglasses, allowed legally blind patients with end-stage glaucoma to read independently, subsequently improving their quality of life. == Employee testing == The New York Times described how a pre-release OrCam device was used by a Coloboma-impaired employee of the device's developer in 2013 for grocery shopping. It was the small size of the prototype rather than the functionality that gave her added mobility in an Israeli store's aisles. Added life-enhancement was described: "to both recognize and speak .. bus numbers .. traffic lights." == Social aspects == In contrast to an early version of Google Glass, which "failed ... because .. Glass wearers were ..mocked", early OrCam devices used designs that "clip unobtrusively on your shirt or perhaps your belt." In addition, it does not record sounds or images, what was called "the privacy puzzle that stumped Google. One 2018 technology reviewer wrote that he wished it had a headphone jack "so it would be less disruptive in places where others are working." An attempt was made to use bone conduction. == USA introduction == In 2018 a team headed by New York Assemblyman Dov Hikind introduced use of OrCam devices to ten individuals screened for what he termed "new Israeli technology that really makes a difference to the blind." Although not the first USA success, it was more focused than a publicly funded project that was authorized in 2016 by a California government agency. Also in 2016 the Chicago Lighthouse for the Blind demonstrated its use. == Technology == In the area of hardware, miniaturization has been quite important, but one major area, software, was mentioned by Assemblyman Hikind, and reported by The Times of Israel is the "AI-driven algorithms" that "reports .. how many people are in a room. In addition to reading printed text, it can also aid in "seeing" what is on a television or computer screen. Although OrCam can't help with handwritten information, it can reuse information, the basis of recognizing "US currency, and even faces." === Features === While early language support was for English, French, German, Hebrew and Spanish, others now available include Danish, Dutch, Finnish, Italian, Norwegian, Portuguese and Swedish. == History == OrCam Technologies Ltd was founded in 2010 by Professor Amnon Shashua and Ziv Aviram. Before co-founding OrCam, the two in 1999 co-founded Mobileye, an Israeli company that develops vision-based advanced driver-assistance systems (ADAS) providing warnings for collision prevention and mitigation, which was acquired by Intel for $15.3 billion in 2017. OrCam launched OrCam MyEye in 2013 after years of development and testing, and began selling it commercially in 2015. In its early years, the company raised $22 million, $6 million of which came from Intel Capital. By 2014, Intel, which was also investing in Google Glass, had invested $15 million in Orcam. In March 2017, OrCam had raised $41 million in capital, making it worth $600 million. === Marketing === One outcome of initial marketing in the USA was that they "reached a deal with the California Department of Rehabilitation, ...qualifying blind and visually impaired state residents." == OrCam Technologies Ltd == OrCam Technologies Ltd. is the Israeli-based company producing these OrCam devices, which are wearable artificial intelligence space. The company develops and manufactures assistive technology devices for individuals who are visually impaired, partially sighted, blind, print disabilities, or have other disabilities. OrCam headquarters is located in Jerusalem, operating under the company name OrCam Technologies Ltd. OrCam has over 150 employees, is headquartered in Jerusalem, and has offices in New York, Toronto, and London. == Awards == 2018 Last Gadget Standing Winner 2018 CES Innovation Awards Honoree in Accessible Tech 2017 NAIDEX Innovation Award 2016 Louise Braille Corporate Recognition Award 2016 Silmo-d-Or Award
BulSemCor
The Bulgarian Sense-annotated Corpus (BulSemCor) (Bulgarian: Български семантично анотиран корпус (БулСемКор)) is a structured corpus of Bulgarian texts in which each lexical item is assigned a sense tag. BulSemCor was created by the Department of Computational Linguistics at the Institute for Bulgarian Language of the Bulgarian Academy of Sciences. == Structure == BulSemCor was created as part of a nationally funded project titled "BulNet – A lexico-semantic network for the Bulgarian Language" (2005–2010). It follows the general methodology of SemCor combined with some specific principles. The corpus for annotation consists of 101,791 tokens covering an excerpt from the Bulgarian "Brown" Corpus modelled on the Brown Corpus.Francis Kucera An important feature of BulSemCor is that the samples are selected using heuristics that provide optimal coverage of ambiguous lexis. BulSemCor is manually sense-annotated according to the Bulgarian WordNet. Its size is comparable to that of other contemporary semantically annotated corpora or pool of acceptable linguistic components. The semantic annotation consists in associating each lexical item in the corpus with exactly one synonym set (synset) in the Bulgarian WordNet that best describes its sense in the particular context. The selection of the best match among the suggested candidates is based on a set of procedures, such as the other synset members, the synset gloss (explanatory definition) and the position of a given candidate in the WordNet structure. == Scale == The number of annotated tokens is 99,480 (the difference in the number of tokens compared to the initial corpus is due to the fact that some of them are not linguistic items). The simple word count is 86,842 and multiword expressions (MWE) are 5,797 (12,638 tokens). == Specific features == All words in BulSemCor are assigned a sense, while according to established practice only simple content words or content word classes (typically nouns and verbs) are annotated. Since 2000 the development of language resources, has broadened to include annotation of function words and multiword expressions covering particular senses or types of words and expressions. In this respect, BulSemCor's annotation is more exhaustive and hence provides greater opportunities for linguistic observations and non-linear programming (NLP) applications. Annotated items inherit the linguistic information associated with the corresponding synset, which along with morphological and semantic tags may include annotation on one or more of the following additional levels: Partial information about the syntactic structure of MWE types – particularly, information about syntactic heads and their dependents; Information about the category of the named entities – names, locations, organisations, dates, numbers, etc.; Information about the taxonomic category of adverbs, such as time, place, manner, degree, quantity, etc.; Information about the type of the syntactic relationships – coordination or subordination – expressed by conjunctions; Information about the original part-of-speech of substantivised words (non-nouns that act as nouns in a particular context); Stylistic/register, grammatical and other information about synsets or individual synset members;
Dailyhunt
Dailyhunt (formerly Newshunt) is an Indian content and news aggregator application based in Bangalore, India that provides local language content in 14 Indian languages from multiple content providers. Viru serves as Founder of Dailyhunt with Co-founder Umang Bedi. == History == Dailyhunt, earlier called Newshunt, was created as a Symbian app in 2009 by two ex-Nokia employees Umesh Kulkarni and Chandrashekhar Sohoni. Later in 2011, Newshunt became available on the Android platform. It was by that time that Virendra Gupta, founder of Verse acquired the application. Virendra Gupta, better known as Viru, had started Verse in 2007 as a value-added service (VAS) company. In 2011, he acquired Newshunt from its owners Umesh and Chandrashekhar. Umesh became the CTO and stayed on to oversee its transition towards the smartphone era. In 2015, Viru renamed Newshunt as Dailyhunt. In early 2018, Viru roped in Umang Bedi, to be the President of Dailyhunt and lead the business with him while focusing on making the benefits of the platform available to a larger audience. Umang was elevated to co-founder in 2020. == Funding == In September 2014, Dailyhunt (then known as Newshunt) closed its Series B funding of INR 1 billion ( or approx $12 million in 2014) from Sequoia Capital India. The Series C funding round was led by Falcon Capital and was closed with $40 million in February 2015. In October 2016, the company received its Series D funding of $25 million from ByteDance and a Series E funding of $6.39 million from Falcon Edge Capital in September 2018. Additionally, Dailyhunt raised $3 Mn (INR 21.75 Cr) in a Series F funding round from Stonebridge Capital in August 2019. Other investors of Dailyhunt include Matrix Partners India, Omidyar Network, Goldman Sachs and Sofina. == Tie-ups and partnerships == In January 2021, Dailyhunt partnered with Twitter to bring ‘Twitter Moments’ to the Indian social app. Dailyhunt app now has a dedicated tab called “Twitter Moments India” to showcase curated tweets pertaining to news and other events. In January 2021, Dailyhunt announced the premiere of Season 2 of the popular show QuoteUnquote with KK (Kapil Khandelwal) on the app. It was the first podcast to have been launched on the Dailyhunt app. In September 2020, Dailyhunt signed up as an Associate Sponsor with Star Sports for Dream 11 IPL 2020. In May 2020, Snapdeal partnered with Dailyhunt to add new content on marketplace. In March 2019, Discovery Communications India, the factual entertainment network, entered into a multi-year partnership with Dailyhunt to showcase short-form content.
Cache language model
A cache language model is a type of statistical language model. These occur in the natural language processing subfield of computer science and assign probabilities to given sequences of words by means of a probability distribution. Statistical language models are key components of speech recognition systems and of many machine translation systems: they tell such systems which possible output word sequences are probable and which are improbable. The particular characteristic of a cache language model is that it contains a cache component and assigns relatively high probabilities to words or word sequences that occur elsewhere in a given text. The primary, but by no means sole, use of cache language models is in speech recognition systems. To understand why it is a good idea for a statistical language model to contain a cache component one might consider someone who is dictating a letter about elephants to a speech recognition system. Standard (non-cache) N-gram language models will assign a very low probability to the word "elephant" because it is a very rare word in English. If the speech recognition system does not contain a cache component, the person dictating the letter may be annoyed: each time the word "elephant" is spoken another sequence of words with a higher probability according to the N-gram language model may be recognized (e.g., "tell a plan"). These erroneous sequences will have to be deleted manually and replaced in the text by "elephant" each time "elephant" is spoken. If the system has a cache language model, "elephant" will still probably be misrecognized the first time it is spoken and will have to be entered into the text manually; however, from this point on the system is aware that "elephant" is likely to occur again – the estimated probability of occurrence of "elephant" has been increased, making it more likely that if it is spoken it will be recognized correctly. Once "elephant" has occurred several times, the system is likely to recognize it correctly every time it is spoken until the letter has been completely dictated. This increase in the probability assigned to the occurrence of "elephant" is an example of a consequence of machine learning and more specifically of pattern recognition. There exist variants of the cache language model in which not only single words but also multi-word sequences that have occurred previously are assigned higher probabilities (e.g., if "San Francisco" occurred near the beginning of the text subsequent instances of it would be assigned a higher probability). The cache language model was first proposed in a paper published in 1990, after which the IBM speech-recognition group experimented with the concept. The group found that implementation of a form of cache language model yielded a 24% drop in word-error rates once the first few hundred words of a document had been dictated. A detailed survey of language modeling techniques concluded that the cache language model was one of the few new language modeling techniques that yielded improvements over the standard N-gram approach: "Our caching results show that caching is by far the most useful technique for perplexity reduction at small and medium training data sizes". The development of the cache language model has generated considerable interest among those concerned with computational linguistics in general and statistical natural language processing in particular: recently, there has been interest in applying the cache language model in the field of statistical machine translation. The success of the cache language model in improving word prediction rests on the human tendency to use words in a "bursty" fashion: when one is discussing a certain topic in a certain context, the frequency with which one uses certain words will be quite different from their frequencies when one is discussing other topics in other contexts. The traditional N-gram language models, which rely entirely on information from a very small number (four, three, or two) of words preceding the word to which a probability is to be assigned, do not adequately model this "burstiness". Recently, the cache language model concept – originally conceived for the N-gram statistical language model paradigm – has been adapted for use in the neural paradigm. For instance, recent work on continuous cache language models in the recurrent neural network (RNN) setting has applied the cache concept to much larger contexts than before, yielding significant reductions in perplexity. Another recent line of research involves incorporating a cache component in a feed-forward neural language model (FN-LM) to achieve rapid domain adaptation.