Error-correction Rule Research Articles

Seq2Parse: neurosymbolic parse error repair

We present Seq2Parse, a language-agnostic neurosymbolic approach to automatically repairing parse errors. Seq2Parse is based on the insight that Symbolic Error Correcting (EC) Parsers can, in principle, synthesize repairs, but, in practice, are overwhelmed by the many error-correction rules that are not relevant to the particular program that requires repair. In contrast, Neural approaches are fooled by the large space of possible sequence level edits, but can precisely pinpoint the set of EC-rules that are relevant to a particular program. We show how to combine their complementary strengths by using neural methods to train a sequence classifier that predicts the small set of relevant EC-rules for an ill-parsed program, after which, the symbolic EC-parsing algorithm can make short work of generating useful repairs. We train and evaluate our method on a dataset of 1,100,000 Python programs, and show that Seq2Parse is accurate and efficient : it can parse 94% of our tests within 2.1 seconds, while generating the exact user fix in 1 out 3 of the cases; and useful : humans perceive both Seq2Parse-generated error locations and repairs to be almost as good as human-generated ones in a statistically-significant manner.

Iterative Shaping of Error Patterns For Normal Syndrome Decoding of Iterative Codes

The problem of two-dimensional syndrome-norm decoding of iterative codes based on a library of error patterns is considered. In two-dimensional coding, sequence code is first transformed into a code matrix, and then the row and column check code are calculated. In the decoder, the error position of the twodimensional can be obtained by the operations that first calculate the syndromes and norms, then match with the error patterns in the existing library. The error pattern library is stored in the memory and generated by the subset of the error pattern. Subset patterns are generated from the base pattern using row and column permutations. The norm calculated based on the syndrome unambiguously determines the base pattern and the corresponding subset of error patterns, which reduces the search space for the syndrome to a subset. In this case, the syndrome is used as an address for retrieving a specific error pattern and correction rule from the memory. With the error rate increased, the size of the error pattern library is raised and the computational complexity of its formation is enlarged. As a result, the known methods for generating the error pattern library become non sufficient. This paper proposed a mathematical model, a generator structure, and an algorithm for fast generation of an error pattern library based on the iterative expansion of the error patterns, which makes it possible to reduce the number of generated redundant error patterns by orders of magnitude and significantly shorten the computational complexity in comparison with the known approaches.

A Cognitive Diagnostic Module Based on the Repair Theory for a Personalized User Experience in E-Learning Software

This paper presents a novel cognitive diagnostic module which is incorporated in e-learning software for the tutoring of the markup language HTML. The system is responsible for detecting the learners’ cognitive bugs and delivering personalized guidance. The novelty of this approach is that it is based on the Repair theory that incorporates additional features, such as student negligence and test completion times, in its diagnostic mechanism; also, it employs a recommender module that suggests students optimal learning paths based on their misconceptions using descriptive test feedback and adaptability of learning content. Considering the Repair theory, the diagnostic mechanism uses a library of error correction rules to explain the cause of errors observed by the student during the assessment. This library covers common errors, creating a hypothesis space in that way. Therefore, the test items are expanded, so that they belong to the hypothesis space. Both the system and the cognitive diagnostic tool were evaluated with promising results, showing that they offer a personalized experience to learners.

The Error Cost of Marriage

Since its inception in 1918, the joint filing election has been one of the U.S. tax system’s most controversial concepts. This tax election allows married taxpayers to file a joint tax return or file two separate returns. Some err, either because they do not know they have a choice or simply because they choose unwisely and elect the less beneficial filing status. The writers of the Code acknowledged taxpayers may need to correct a filing status error. Married taxpayers filing separately can retroactively amend their filing status for a previous year to joint filing under certain circumstances at no cost. Surprisingly, joint filers do not enjoy this opportunity to amend prior returns to filing separately in any circumstance. Scholars have extensively argued for and against treating married taxpayers as a single economic unit rather than on an individual basis. But they have yet to notice this asymmetric amendment rule. This Article is the first to examine the overlooked problem of the asymmetric treatment of married taxpayers who wish to amend their initial filing status election. This asymmetric error-correction rule has two problems: it is unfair and inefficient. First, it enables only one group of married taxpayers to revisit their election and correct their filing status. Given that the U.S. tax system incentivizes joint filing in several ways, married taxpayers assume joint filing is the sole or favorable election for them. That, however, is not always the case. This rule has adverse effects on the fairness of the tax system, especially when it comes to female taxpayers who usually bear the cost of joint filing. Second, those who can correct their election do not bear correction’s administrative costs, producing an administrative inefficiency. After identifying and explaining this puzzling problem, the Article proposes an elegant solution: a Pigouvian rule enabling all married taxpayers to amend but requiring them to internalize all the associated administrative costs through a reduced tax refund. This rule eliminates both inefficiencies and unfairness.

Research on rapid planning of intelligent aircraft trajectory under multiple constraints

Intelligent aircraft trajectory planning is an important support to ensure the successful completion of the mission of the aircraft, and it is also a key component of the intelligent aircraft mission planning system. Due to system performance constraints and environmental constraints, the positioning system of the intelligent aircraft cannot be accurately positioned during flight, which will cause flight errors. Excessive flight errors will lead to the failure of the mission. Therefore, error correction plays an increasingly important role in trajectory planning. This paper studies the rapid trajectory planning of intelligent aircraft under the limitation of system positioning accuracy. Based on the optimization theory, with the error generation rules and correction rules of the intelligent aircraft in flight as constraints, establishes the optimization model, and uses the fast non-dominated multi-objective optimization algorithm (NSGA-II) with elite retention strategy. This paper corrects the vertical and horizontal errors during the flight, and finally designs a reasonable intelligent aircraft trajectory that meets the minimum trajectory length and the minimum number of corrections during the flight.

Alteration of a motor learning rule under mirror-reversal transformation does not depend on the amplitude of visual error

Human's sophisticated motor learning system paradoxically interferes with motor performance when visual information is mirror-reversed (MR), because normal movement error correction further aggravates the error. This error-increasing mechanism makes performing even a simple reaching task difficult, but is overcome by alterations in the error correction rule during the trials. To isolate factors that trigger learners to change the error correction rule, we manipulated the gain of visual angular errors when participants made arm-reaching movements with mirror-reversed visual feedback, and compared the rule alteration timing between groups with normal or reduced gain. Trial-by-trial changes in the visual angular error was tracked to explain the timing of the change in the error correction rule. Under both gain conditions, visual angular errors increased under the MR transformation, and suddenly decreased after 3–5 trials with increase. The increase became degressive at different amplitude between the two groups, nearly proportional to the visual gain. The findings suggest that the alteration of the error-correction rule is not dependent on the amplitude of visual angular errors, and possibly determined by the number of trials over which the errors increased or statistical property of the environment. The current results encourage future intensive studies focusing on the exact rule-change mechanism.

모바일 환경을 고려한 규칙기반 음성인식 오류교정

본 논문에서는 모바일 환경에서 음성인식한 결과에 포함된 오류를 교정하는 규칙기반 접근방법을 제안한다. 제안하는 방법은 처리시간이나 메모리에 제약을 받는 모바일 환경을 고려하여 다음과 같이 구성된다. 오류 교정 속도를 최소화하기 위해서, 음절 해체 및 조합 과정이나 형태소 분석 등의 처리를 줄이고, 최장일치 규칙 선택기준을 바탕으로 오류 발생 추정 지점에서 교정 후보도 하나만 생성한다. 제안하는 방법은 메모리를 효율적으로 사용하기 위해서, 어절사전이나 형태소분석기를 사용하지 않고, 규칙도 유형별로 따로 구분하지 않고 통합하여 저장한다. 제안하는 방법은 모델의 수정 및 유지보수가 용이하도록, 오류교정규칙을 학습말뭉치에서 자동으로 추출하여 구축한다. 실험결과 제안하는 방법은 음성인식 결과에 대하여 정확률을 5.27% 정도 재현율을 5.60% 정도 개선하였다. In this paper, we propose a rule-based model to correct errors in a speech recognition result in the mobile device environment. The proposed model considers the mobile device environment with limited resources such as processing time and memory, as follows. In order to minimize the error correction processing time, the proposed model removes some processing steps such as morphological analysis and the composition and decomposition of syllable. Also, the proposed model utilizes the longest match rule selection method to generate one error correction candidate per point, assumed that an error occurs. For the purpose of deploying memory resource, the proposed model uses neither the Eojeol dictionary nor the morphological analyzer, and stores a combined rule list without any classification. Considering the modification and maintenance of the proposed model, the error correction rules are automatically extracted from a training corpus. Experimental results show that the proposed model improves 5.27% on the precision and 5.60% on the recall based on Eojoel unit for the speech recognition result.

광범위 고정형 무선 통신 시스템을 위한 상향 링크 초기 레인징 기법 설계

In this paper, an enhanced initial ranging algorithm for large-cell coverage fixed wireless communication system is proposed. In typical wireless communication system such as WiBro, because a round-trip delay between a transmitter and a receiver is within one OFDM (Orthogonal Frequency Division Multiplexing) symbol duration, a frequency-domain differential correlation method is generally used. However, the conventional method cannot be applied due to an increase of a maximum time delay in large-cell system. In case of an accumulative differential method, estimation errors can occur because of frequent sign transitions. In this paper, therefore, we propose an algorithm which can estimate a total timing offset in a ranging channel structure for 15 km cell. The proposed method can improve performance by sign comparison based sign error correction rule between the estimated values and using a weighting scheme based on channel correlation, the number of accumulations, and the noise reduction effect in normalization process. Also, it can estimate the integer timing offset of symbol duration by comparing peak-powers after compensating for the fractional timing offset of symbol duration.

How are Exchange Rates Managed? Evidence of Error-Correction Around a Reference

In managed floats, central banks often intervene in the foreign exchange market to obtain politically desirable exchange rates. How this is done has remained totally opaque although central banks are likely to adopt a satisfying rather than optimizing strategy since they need to intervene frequently in a timely manner under incomplete information. In this paper, we propose a simple exchange rate management rule that balances the amount of variation between currency pairs around a reference rate. We test out this rule using the Chinese Yuan as a case study before extending the study to 9 other currencies. Empirical results are consistent with the hypothesis that central banks follow the error correction rule in exchange rate management.

Periodic Activation Function and a Modified Learning Algorithm for the Multivalued Neuron

In this paper, we consider a new periodic activation function for the multivalued neuron (MVN). The MVN is a neuron with complex-valued weights and inputs/output, which are located on the unit circle. Although the MVN outperforms many other neurons and MVN-based neural networks have shown their high potential, the MVN still has a limited capability of learning highly nonlinear functions. A periodic activation function, which is introduced in this paper, makes it possible to learn nonlinearly separable problems and non-threshold multiple-valued functions using a single multivalued neuron. We call this neuron a multivalued neuron with a periodic activation function (MVN-P). The MVN-Ps functionality is much higher than that of the regular MVN. The MVN-P is more efficient in solving various classification problems. A learning algorithm based on the error-correction rule for the MVN-P is also presented. It is shown that a single MVN-P can easily learn and solve those benchmark classification problems that were considered unsolvable using a single neuron. It is also shown that a universal binary neuron, which can learn nonlinearly separable Boolean functions, and a regular MVN are particular cases of the MVN-P.

Attentional and error-correcting associative mechanisms in classical conditioning.

R. A. Rescorla (2000, Rescorla, 2001, Rescorla, 2002) reported that the associative changes undergone by 2 conditioned stimuli that are reinforced or not reinforced in compound depend on their initial associations. The results contradict the predictions of simple error-correction models but can be explained by models that incorporate a "constrained" error-correction rule. A model of classical conditioning presented by N. A. Schmajuk, Y. Lam, and J. A. Gray (1996) suggests that attentional mechanisms, acting during both compound training and testing, have an important role in producing those results. Moreover, the model suggests that those attentional mechanisms might obscure the evaluation of the associative changes undergone by the conditioned stimuli during compound training. Two experiments that differentiate our model from competing theories are proposed.

Multilayer Feedforward Neural Network Based on Multi-valued Neurons (MLMVN) and a Backpropagation Learning Algorithm

A multilayer neural network based on multi-valued neurons (MLMVN) is considered in the paper. A multi-valued neuron (MVN) is based on the principles of multiple-valued threshold logic over the field of the complex numbers. The most important properties of MVN are: the complex-valued weights, inputs and output coded by the kth roots of unity and the activation function, which maps the complex plane into the unit circle. MVN learning is reduced to the movement along the unit circle, it is based on a simple linear error correction rule and it does not require a derivative. It is shown that using a traditional architecture of multilayer feedforward neural network (MLF) and the high functionality of the MVN, it is possible to obtain a new powerful neural network. Its training does not require a derivative of the activation function and its functionality is higher than the functionality of MLF containing the same number of layers and neurons. These advantages of MLMVN are confirmed by testing using parity n, two spirals and "sonar" benchmarks and the Mackey---Glass time series prediction.

Finite Memory Loading in Hairy Neurons

This paper presents a method to expand the basins of stable patterns in associative memory. It examines fully-connected associative memory geometrically and translate the learning process into an algebraic optimization procedure. It finds that locating all the patterns at certain stable corners of the neurons’ hypercube as far from the decision hyperplanes as possible can produce excellent error tolerance. It then devises a method based on this finding to develop the hyperplanes. This paper further shows that this method leads to the hairy model, or the deterministic analogue of the Gibb’s free energy model. Through simulations, it shows that this method gives better error tolerance than does the Hopfield model and the error-correction rule in both synchronous and asynchronous modes.

Invariant object recognition in the visual system with error correction and temporal difference learning

It has been proposed that invariant pattern recognition might be implemented using a learning rule that utilizes a trace of previous neural activity which, given the spatio-temporal continuity of the statistics of sensory input, is likely to be about the same object though with differing transforms in the short time scale. Recently, it has been demonstrated that a modified Hebbian rule which incorporates a trace of previous activity but no contribution from the current activity can offer substantially improved performance. In this paper we show how this rule can be related to error correction rules, and explore a number of error correction rules that can be applied to and can produce good invariant pattern recognition. An explicit relationship to temporal difference learning is then demonstrated, and from this further learning rules related to temporal difference learning are developed. This relationship to temporal difference learning allows us to begin to exploit established analyses of temporal difference learning to provide a theoretical framework for better understanding the operation and convergence properties of these learning rules, and more generally, of rules useful for learning invariant representations. The efficacy of these different rules for invariant object recognition is compared using VisNet, a hierarchical competitive network model of the operation of the visual system.

Invariant object recognition in the visual system with error correction and temporal difference learning

It has been proposed that invariant pattern recognition might be implemented using a learning rule that utilizes a trace of previous neural activity which, given the spatio-temporal continuity of the statistics of sensory input, is likely to be about the same object though with differing transforms in the short time scale. Recently, it has been demonstrated that a modified Hebbian rule which incorporates a trace of previous activity but no contribution from the current activity can offer substantially improved performance. In this paper we show how this rule can be related to error correction rules, and explore a number of error correction rules that can be applied to and can produce good invariant pattern recognition. An explicit relationship to temporal difference learning is then demonstrated, and from this further learning rules related to temporal difference learning are developed. This relationship to temporal difference learning allows us to begin to exploit established analyses of temporal difference learning to provide a theoretical framework for better understanding the operation and convergence properties of these learning rules, and more generally, of rules useful for learning invariant representations. The efficacy of these different rules for invariant object recognition is compared using VisNet, a hierarchical competitive network model of the operation of the visual system.

30 years of adaptive neural networks: perceptron, Madaline, and backpropagation

Fundamental developments in feedforward artificial neural networks from the past thirty years are reviewed. The history, origination, operating characteristics, and basic theory of several supervised neural-network training algorithms (including the perceptron rule, the least-mean-square algorithm, three Madaline rules, and the backpropagation technique) are described. The concept underlying these iterative adaptation algorithms is the minimal disturbance principle, which suggests that during training it is advisable to inject new information into a network in a manner that disturbs stored information to the smallest extent possible. The two principal kinds of online rules that have developed for altering the weights of a network are examined for both single-threshold elements and multielement networks. They are error-correction rules, which alter the weights of a network to correct error in the output response to the present input pattern, and gradient rules, which alter the weights of a network during each pattern presentation by gradient descent with the objective of reducing mean-square error (averaged over all training patterns).< <ETX xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">&gt;</ETX>

LMS rules and the inverse base-rate effect: Comment on Gluck and Bower (1988).

(}luck and Bower (1988) suggestmi that through the use of the Rescorla-Wagner learning rule, a connectionist network might be ~ble to model the inverse base-rate phenomenon found by Medin and Edelson (1988). I prove that a network of the type that they proposed does not capture this effect. However, one can also prove that with additional assumptions about the encoding of features, the Rescorla-Wagner learning rule can be made to model the inverse baserate effect. The importance of these assumptions and an outline of how they might be tested are then discussed. Gluck and Bower (1988) recently showed how a version of the Rescorla-Wagner learning rule (a variant of the least mean squared [LMS] error correction rule) could be used to predict human behavior in a category-learning task. At the end of their article, they theorized that this rule might be able to account for subjects' incorrect use of base-rate information found in a set of experiments by Medin and Edelson (1988). The inverse base-rate phenomenon (Medin & Edelson, 1988) is a surprising and counterintuitive effect shown by subjects in category-learning experiments in which the frequency of presentation of the categories is varied. Table 1 illustrates a simple case: Subjects are presented ~h exemplars for each of two categories. In the simple case, these categories have one common feature (A) and one distinctive feature (B or C). When one category is presented more frequently than the other, an interesting pattern or responses results. If subjects • are given the common feature and asked which category is more likely to be described by this feature, subjects respond with the more frequently presented category. If either of the distinctive features is presented during testing, the appropriate category is selected. However, ifboth of the distinctive features are presented together, the subject is more likely to select the less frequently presented category, responding in opposition to the base-rate information. Medin and Edelson (1988) discussed the possibility that the inverse base-rate effect stems from a competition between features. In a context in which the categories are diseases and the features are symptoms, they stated that

On the potential function method and the increment error correction rule in pattern classification

Based on the basic property that the solution weight vector of the linear pattern classifier can be expressed as a linear function of the training patterns, it is shown that the increment error correction algorithm is a special case of the potential function method. For linearly separable training patterns, a form of potential function which appears to be useful is also proposed.