Error-driven learning

<h2 id="formal-definition">Formal Definition</h2>
Error-driven learning models are ones that rely on the feedback of prediction errors to adjust the expectations or parameters of a model. The key components of error-driven learning include the following:

<ul><li>A set 
 
 
 
 S
 
 
 {\displaystyle S}
 
 of states representing the different situations that the learner can encounter.</li>
<li>A set 
 
 
 
 A
 
 
 {\displaystyle A}
 
 of actions that the learner can take in each state.</li>
<li>A prediction function 
 
 
 
 P
 (
 s
 ,
 a
 )
 
 
 {\displaystyle P(s,a)}
 
 that gives the learner’s current prediction of the outcome of taking action 
 
 
 
 a
 
 
 {\displaystyle a}
 
 in state 
 
 
 
 s
 
 
 {\displaystyle s}
 
.</li>
<li>An error function 
 
 
 
 E
 (
 o
 ,
 p
 )
 
 
 {\displaystyle E(o,p)}
 
 that compares the actual outcome 
 
 
 
 o
 
 
 {\displaystyle o}
 
 with the prediction 
 
 
 
 p
 
 
 {\displaystyle p}
 
 and produces an error value.</li>
<li>An update rule 
 
 
 
 U
 (
 p
 ,
 e
 )
 
 
 {\displaystyle U(p,e)}
 
 that adjusts the prediction 
 
 
 
 p
 
 
 {\displaystyle p}
 
 in light of the error 
 
 
 
 e
 
 
 {\displaystyle e}
 
.<a class="footnote-ref" id="fnref:10" href="#fn:10">10</a></li></ul>
<h2 id="algorithms">Algorithms</h2>
Error-driven learning algorithms refer to a category of <a href="/facts/Reinforcement_learning/NrgPPS0Q">reinforcement learning</a> algorithms that leverage the disparity between the real <a href="/facts/Input/output/WQTE8Jas">output</a> and the expected output of a system to regulate the system's parameters. Typically applied in supervised learning, these algorithms are provided with a collection of input-output pairs to facilitate the process of generalization. <a class="footnote-ref" id="fnref:11" href="#fn:11">11</a>
The widely utilized error <a href="/facts/Backpropagation/lCsIdKHc">backpropagation</a> learning algorithm is known as <a href="/facts/GeneRec/QxEEq31J">GeneRec</a>, a generalized recirculation algorithm primarily employed for <a href="/facts/Gene/e1swwPY6">gene</a> prediction in <a href="/facts/DNA/nB89Iauz">DNA</a> sequences. Many other error-driven learning algorithms are derived from alternative versions of GeneRec. <a class="footnote-ref" id="fnref:12" href="#fn:12">12</a>

<h2 id="applications">Applications</h2>
<h3>Cognitive science</h3>
See also: <a href="/facts/Cognitive_science/8qoggl7r">Cognitive science</a>
Simpler error-driven learning models effectively capture complex human cognitive phenomena and anticipate elusive behaviors. They provide a flexible mechanism for modeling the brain's learning process, encompassing <a href="/facts/Perception/xLK0n2q4">perception</a>, <a href="/facts/Attention/pleJPaeQ">attention</a>, <a href="/facts/Memory/zucwQIEX">memory</a>, and <a href="/facts/Decision-making/NbJYprSw">decision-making</a>. By using errors as guiding signals, these algorithms adeptly adapt to changing environmental demands and objectives, capturing statistical regularities and structure. <a class="footnote-ref" id="fnref:13" href="#fn:13">13</a> 
Furthermore, cognitive science has led to the creation of new error-driven learning algorithms that are both biologically acceptable and <a href="/facts/Big_O_notation/weFFjSWg">computationally efficient</a>. These algorithms, including <a href="/facts/Deep_belief_network/aPkAjLIU">deep belief networks</a>, <a href="/facts/Spiking_neural_network/DeT3wPPV">spiking neural networks</a>, and <a href="/facts/Reservoir_computing/YJKlaRQK">reservoir computing</a>, follow the principles and constraints of the brain and nervous system. Their primary aim is to capture the emergent properties and dynamics of <a href="/facts/Neural_circuit/pgngqMLf">neural circuits</a> and systems.<a class="footnote-ref" id="fnref:14" href="#fn:14">14</a><a class="footnote-ref" id="fnref:15" href="#fn:15">15</a>

<h3>Computer vision</h3>
See also: <a href="/facts/Computer_vision/Tl2Yyk66">Computer vision</a>
<a href="/facts/Computer_vision/Tl2Yyk66">Computer vision</a> is a complex task that involves understanding and interpreting visual data, such as images or videos.<a class="footnote-ref" id="fnref:16" href="#fn:16">16</a>
In the context of error-driven learning, the computer vision model learns from the mistakes it makes during the interpretation process. When an error is encountered, the model updates its internal parameters to avoid making the same mistake in the future. This repeated process of learning from errors helps improve the model’s performance over time.<a class="footnote-ref" id="fnref:17" href="#fn:17">17</a>
For NLP to do well at computer vision, it employs deep learning techniques. This form of computer vision is sometimes called neural computer vision (NCV), since it makes use of neural networks. NCV therefore interprets visual data based on a statistical, trial and error approach and can deal with context and other subtleties of visual data.<a class="footnote-ref" id="fnref:18" href="#fn:18">18</a>

<h3>Natural Language Processing</h3>
See also: <a href="/facts/Natural_language_processing/1hjMKsSN">Natural language processing</a>
<h4>Part-of-speech tagging</h4>
See also: <a href="/facts/Part-of-speech_tagging/BYAPmH3r">Part-of-speech tagging</a>
Part-of-speech (POS) tagging is a crucial component in Natural Language Processing (NLP). It helps resolve human language ambiguity at different analysis levels. In addition, its output (tagged data) can be used in various applications of NLP such as <a href="/facts/Information_extraction/DL9nMD2X">information extraction</a>, <a href="/facts/Information_retrieval/MFSmpeNw">information retrieval</a>, <a href="/facts/Question_answering/1gplmc6L">question Answering</a>, <a href="/facts/Speech_recognition/z7S7Pgk6">speech eecognition</a>, text-to-speech conversion, partial parsing, and grammar correction.<a class="footnote-ref" id="fnref:19" href="#fn:19">19</a> 

<h4>Parsing</h4>
See also: <a href="/facts/Part-of-speech_tagging/BYAPmH3r">Part-of-speech tagging</a>
Parsing in NLP involves breaking down a text into smaller pieces (<a href="/facts/Phrase/mbnD0ksH">phrases</a>) based on grammar rules. If a sentence cannot be parsed, it may contain grammatical errors.
In the context of error-driven learning, the parser learns from the mistakes it makes during the parsing process. When an error is encountered, the parser updates its internal model to avoid making the same mistake in the future. This iterative process of learning from errors helps improve the parser’s performance over time.<a class="footnote-ref" id="fnref:20" href="#fn:20">20</a>
In conclusion, error-driven learning plays a crucial role in improving the accuracy and efficiency of NLP parsers by allowing them to learn from their mistakes and adapt their internal models accordingly.

<h4>Named entity recognition (NER)</h4>
See also: <a href="/facts/Named-entity_recognition/ko6GRQQd">Named-entity recognition</a>
NER is the task of identifying and classifying entities (such as persons, locations, organizations, etc.) in a text. Error-driven learning can help the model learn from its false positives and false negatives and improve its recall and precision on (NER).<a class="footnote-ref" id="fnref:21" href="#fn:21">21</a>
In the context of error-driven learning, the significance of NER is quite profound. Traditional sequence labeling methods identify nested <a href="/facts/Entity/yV29WTrT">entities</a> layer by layer. If an error occurs in the recognition of an inner <a href="/facts/Entity/yV29WTrT">entity</a>, it can lead to incorrect identification of the outer entity, leading to a problem known as <a href="/facts/Error_propagation/jJE2dzYB">error propagation</a> of nested entities.<a class="footnote-ref" id="fnref:22" href="#fn:22">22</a><a class="footnote-ref" id="fnref:23" href="#fn:23">23</a>
This is where the role of NER becomes crucial in error-driven learning. By accurately recognizing and classifying entities, it can help minimize these errors and improve the overall accuracy of the learning process. Furthermore, <a href="/facts/Deep_learning/JLuwD3ea">deep learning</a>-based NER methods have shown to be more accurate as they are capable of assembling words, enabling them to understand the semantic and syntactic relationship between various words better.<a class="footnote-ref" id="fnref:24" href="#fn:24">24</a><a class="footnote-ref" id="fnref:25" href="#fn:25">25</a>

<h4>Machine translation</h4>
See also: <a href="/facts/Machine_translation/DGF3NwuI">Machine translation</a>
Machine translation is a complex task that involves converting text from one language to another.<a class="footnote-ref" id="fnref:26" href="#fn:26">26</a> In the context of error-driven learning, the machine translation model learns from the mistakes it makes during the translation process. When an error is encountered, the model updates its internal parameters to avoid making the same mistake in the future. This iterative process of learning from errors helps improve the model’s performance over time.<a class="footnote-ref" id="fnref:27" href="#fn:27">27</a>

<h4>Speech recognition</h4>
See also: <a href="/facts/Speech_recognition/z7S7Pgk6">Speech recognition</a>
Speech recognition is a complex task that involves converting spoken language into written text. In the context of error-driven learning, the speech recognition model learns from the mistakes it makes during the recognition process. When an error is encountered, the model updates its internal parameters to avoid making the same mistake in the future. This iterative process of learning from errors helps improve the model’s performance over time.<a class="footnote-ref" id="fnref:28" href="#fn:28">28</a>

<h4>Dialogue systems</h4>
See also: <a href="/facts/Dialogue_systems/gbMVkBVf">Dialogue systems</a>
Dialogue systems are a popular NLP task as they have promising real-life applications. They are also complicated tasks since many NLP tasks deserving study are involved.
In the context of error-driven learning, the dialogue system learns from the mistakes it makes during the dialogue process. When an error is encountered, the model updates its internal parameters to avoid making the same mistake in the future. This iterative process of learning from errors helps improve the model’s performance over time.<a class="footnote-ref" id="fnref:29" href="#fn:29">29</a>

<h2 id="advantages">Advantages</h2>
Error-driven learning has several advantages over other types of machine learning algorithms:

<ul><li>They can learn from feedback and correct their mistakes, which makes them adaptive and robust to noise and changes in the data.</li>
<li>They can handle large and <a href="/facts/Dimension/0ktmUyac">high-dimensional</a> <a href="/facts/Data_set/eDvegUTK">data sets</a>, as they do not require explicit feature engineering or prior knowledge of the data distribution.</li>
<li>They can achieve high accuracy and performance, as they can learn complex and nonlinear relationships between the input and the output.<a class="footnote-ref" id="fnref:30" href="#fn:30">30</a></li></ul>
<h2 id="limitations">Limitations</h2>
Although error driven learning has its advantages, their algorithms also have the following limitations:

<ul><li>They can suffer from <a href="/facts/Overfitting/5xnFLcMg">overfitting</a>, which means that they memorize the training data and fail to generalize to new and unseen data. This can be mitigated by using <a href="/facts/Regularization_(mathematics)/K601A3y2">regularization</a> techniques, such as adding a penalty term to the <a href="/facts/Loss_function/xv5ozuhl">loss function</a>, or reducing the <a href="/facts/Complexity/KjgY905l">complexity</a> of the model.<a class="footnote-ref" id="fnref:31" href="#fn:31">31</a></li>
<li>They can be sensitive to the choice of the <a href="/facts/Error_function/Ca2H7pGr">error function</a>, the <a href="/facts/Learning_rate/EClSgMCR">learning rate</a>, the initialization of the weights, and other <a href="/facts/Hyperparameter_(machine_learning)/jCxm3fTA">hyperparameters</a>, which can affect the <a href="/facts/Convergence_of_random_variables/pWdatFlY">convergence</a> and the quality of the solution. This requires careful tuning and experimentation, or using adaptive methods that adjust the hyperparameters automatically.</li>
<li>They can be <a href="/facts/Algorithmic_efficiency/VutjvPTd">computationally</a> expensive and time-consuming, especially for nonlinear and deep models, as they require multiple iterations(repetitions) and calculations to update the weights of the system. This can be alleviated by using parallel and <a href="/facts/Distributed_computing/o5nyhqTF">distributed computing</a>, or using specialized hardware such as GPUs or TPUs.<a class="footnote-ref" id="fnref:32" href="#fn:32">32</a></li></ul>
<h2 id="see-also">See also</h2>
<ul><li><a href="/facts/Predictive_coding/DRRQQcTB">Predictive coding</a></li></ul>

<h2 id="references">References</h2>

<ol>
<li id="fn:1">Sadre, Ramin; Pras, Aiko (2009-06-19). Scalability of Networks and Services: Third International Conference on Autonomous Infrastructure, Management and Security, AIMS 2009 Enschede, The Netherlands, June 30 - July 2, 2009, Proceedings. Springer. ISBN 978-3-642-02627-0. <a href="978-3-642-02627-0" target="_blank">978-3-642-02627-0</a> <a href="#fnref:1" class="footnote-back-ref">↩</a></li>
<li id="fn:2">Hoppe, Dorothée B.; Hendriks, Petra; Ramscar, Michael; van Rij, Jacolien (2022-10-01). "An exploration of error-driven learning in simple two-layer networks from a discriminative learning perspective". Behavior Research Methods. 54 (5): 2221–2251. doi:10.3758/s13428-021-01711-5. ISSN 1554-3528. PMC 9579095. PMID 35032022. <a href="https://doi.org/10.3758/s13428-021-01711-5" target="_blank">https://doi.org/10.3758/s13428-021-01711-5</a> <a href="#fnref:2" class="footnote-back-ref">↩</a></li>
<li id="fn:3">O'Reilly, Randall C. (1996-07-01). "Biologically Plausible Error-Driven Learning Using Local Activation Differences: The Generalized Recirculation Algorithm". Neural Computation. 8 (5): 895–938. doi:10.1162/neco.1996.8.5.895. ISSN 0899-7667. <a href="https://doi.org/10.1162/neco.1996.8.5.895" target="_blank">https://doi.org/10.1162/neco.1996.8.5.895</a> <a href="#fnref:3" class="footnote-back-ref">↩</a></li>
<li id="fn:4">Mohammad, Saif, and Ted Pedersen. "Combining lexical and syntactic features for supervised word sense disambiguation." Proceedings of the Eighth Conference on Computational Natural Language Learning (CoNLL-2004) at HLT-NAACL 2004. 2004.

APA <a href="https://aclanthology.org/W04-2404.pdf" target="_blank">https://aclanthology.org/W04-2404.pdf</a> <a href="#fnref:4" class="footnote-back-ref">↩</a></li>
<li id="fn:5">Mohammad, Saif, and Ted Pedersen. "Combining lexical and syntactic features for supervised word sense disambiguation." Proceedings of the Eighth Conference on Computational Natural Language Learning (CoNLL-2004) at HLT-NAACL 2004. 2004.

APA <a href="https://aclanthology.org/W04-2404.pdf" target="_blank">https://aclanthology.org/W04-2404.pdf</a> <a href="#fnref:5" class="footnote-back-ref">↩</a></li>
<li id="fn:6">Florian, Radu, et al. "Named entity recognition through classifier combination." Proceedings of the seventh conference on Natural language learning at HLT-NAACL 2003. 2003. <a href="https://aclanthology.org/W03-0425.pdf" target="_blank">https://aclanthology.org/W03-0425.pdf</a> <a href="#fnref:6" class="footnote-back-ref">↩</a></li>
<li id="fn:7">Rozovskaya, Alla, and Dan Roth. "Grammatical error correction: Machine translation and classifiers." Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2016. <a href="https://aclanthology.org/P16-1208.pdf" target="_blank">https://aclanthology.org/P16-1208.pdf</a> <a href="#fnref:7" class="footnote-back-ref">↩</a></li>
<li id="fn:8">Mohammad, Saif, and Ted Pedersen. "Combining lexical and syntactic features for supervised word sense disambiguation." Proceedings of the Eighth Conference on Computational Natural Language Learning (CoNLL-2004) at HLT-NAACL 2004. 2004.

APA <a href="https://aclanthology.org/W04-2404.pdf" target="_blank">https://aclanthology.org/W04-2404.pdf</a> <a href="#fnref:8" class="footnote-back-ref">↩</a></li>
<li id="fn:9">Iosif, Elias; Klasinas, Ioannis; Athanasopoulou, Georgia; Palogiannidi, Elisavet; Georgiladakis, Spiros; Louka, Katerina; Potamianos, Alexandros (2018-01-01). "Speech understanding for spoken dialogue systems: From corpus harvesting to grammar rule induction". Computer Speech & Language. 47: 272–297. doi:10.1016/j.csl.2017.08.002. ISSN 0885-2308. <a href="https://www.sciencedirect.com/science/article/pii/S0885230816302613" target="_blank">https://www.sciencedirect.com/science/article/pii/S0885230816302613</a> <a href="#fnref:9" class="footnote-back-ref">↩</a></li>
<li id="fn:10">Hoppe, Dorothée B.; Hendriks, Petra; Ramscar, Michael; van Rij, Jacolien (2022-10-01). "An exploration of error-driven learning in simple two-layer networks from a discriminative learning perspective". Behavior Research Methods. 54 (5): 2221–2251. doi:10.3758/s13428-021-01711-5. ISSN 1554-3528. PMC 9579095. PMID 35032022. <a href="https://doi.org/10.3758/s13428-021-01711-5" target="_blank">https://doi.org/10.3758/s13428-021-01711-5</a> <a href="#fnref:10" class="footnote-back-ref">↩</a></li>
<li id="fn:11">Hoppe, Dorothée B.; Hendriks, Petra; Ramscar, Michael; van Rij, Jacolien (2022-10-01). "An exploration of error-driven learning in simple two-layer networks from a discriminative learning perspective". Behavior Research Methods. 54 (5): 2221–2251. doi:10.3758/s13428-021-01711-5. ISSN 1554-3528. PMC 9579095. PMID 35032022. <a href="https://doi.org/10.3758/s13428-021-01711-5" target="_blank">https://doi.org/10.3758/s13428-021-01711-5</a> <a href="#fnref:11" class="footnote-back-ref">↩</a></li>
<li id="fn:12">O'Reilly, Randall C. (1996-07-01). "Biologically Plausible Error-Driven Learning Using Local Activation Differences: The Generalized Recirculation Algorithm". Neural Computation. 8 (5): 895–938. doi:10.1162/neco.1996.8.5.895. ISSN 0899-7667. <a href="https://doi.org/10.1162/neco.1996.8.5.895" target="_blank">https://doi.org/10.1162/neco.1996.8.5.895</a> <a href="#fnref:12" class="footnote-back-ref">↩</a></li>
<li id="fn:13">Hoppe, Dorothée B.; Hendriks, Petra; Ramscar, Michael; van Rij, Jacolien (2022-10-01). "An exploration of error-driven learning in simple two-layer networks from a discriminative learning perspective". Behavior Research Methods. 54 (5): 2221–2251. doi:10.3758/s13428-021-01711-5. ISSN 1554-3528. PMC 9579095. PMID 35032022. <a href="https://doi.org/10.3758/s13428-021-01711-5" target="_blank">https://doi.org/10.3758/s13428-021-01711-5</a> <a href="#fnref:13" class="footnote-back-ref">↩</a></li>
<li id="fn:14">Hoppe, Dorothée B.; Hendriks, Petra; Ramscar, Michael; van Rij, Jacolien (2022-10-01). "An exploration of error-driven learning in simple two-layer networks from a discriminative learning perspective". Behavior Research Methods. 54 (5): 2221–2251. doi:10.3758/s13428-021-01711-5. ISSN 1554-3528. PMC 9579095. PMID 35032022. <a href="https://doi.org/10.3758/s13428-021-01711-5" target="_blank">https://doi.org/10.3758/s13428-021-01711-5</a> <a href="#fnref:14" class="footnote-back-ref">↩</a></li>
<li id="fn:15">Bengio, Y. (2009). Learning deep architectures for AI. Foundations and trends® in Machine Learning, 2(1), 1-127 <a href="#fnref:15" class="footnote-back-ref">↩</a></li>
<li id="fn:16">Voulodimos, Athanasios; Doulamis, Nikolaos; Doulamis, Anastasios; Protopapadakis, Eftychios (2018-02-01). "Deep Learning for Computer Vision: A Brief Review". Computational Intelligence and Neuroscience. 2018: e7068349. doi:10.1155/2018/7068349. ISSN 1687-5265. PMC 5816885. PMID 29487619. <a href="https://www.ncbi.nlm.nih.gov/pmc/articles/PMC5816885" target="_blank">https://www.ncbi.nlm.nih.gov/pmc/articles/PMC5816885</a> <a href="#fnref:16" class="footnote-back-ref">↩</a></li>
<li id="fn:17">Voulodimos, Athanasios; Doulamis, Nikolaos; Doulamis, Anastasios; Protopapadakis, Eftychios (2018-02-01). "Deep Learning for Computer Vision: A Brief Review". Computational Intelligence and Neuroscience. 2018: e7068349. doi:10.1155/2018/7068349. ISSN 1687-5265. PMC 5816885. PMID 29487619. <a href="https://www.ncbi.nlm.nih.gov/pmc/articles/PMC5816885" target="_blank">https://www.ncbi.nlm.nih.gov/pmc/articles/PMC5816885</a> <a href="#fnref:17" class="footnote-back-ref">↩</a></li>
<li id="fn:18">Voulodimos, Athanasios; Doulamis, Nikolaos; Doulamis, Anastasios; Protopapadakis, Eftychios (2018-02-01). "Deep Learning for Computer Vision: A Brief Review". Computational Intelligence and Neuroscience. 2018: e7068349. doi:10.1155/2018/7068349. ISSN 1687-5265. PMC 5816885. PMID 29487619. <a href="https://www.ncbi.nlm.nih.gov/pmc/articles/PMC5816885" target="_blank">https://www.ncbi.nlm.nih.gov/pmc/articles/PMC5816885</a> <a href="#fnref:18" class="footnote-back-ref">↩</a></li>
<li id="fn:19">Mohammad, Saif, and Ted Pedersen. "Combining lexical and syntactic features for supervised word sense disambiguation." Proceedings of the Eighth Conference on Computational Natural Language Learning (CoNLL-2004) at HLT-NAACL 2004. 2004.

APA <a href="https://aclanthology.org/W04-2404.pdf" target="_blank">https://aclanthology.org/W04-2404.pdf</a> <a href="#fnref:19" class="footnote-back-ref">↩</a></li>
<li id="fn:20">Mohammad, Saif, and Ted Pedersen. "Combining lexical and syntactic features for supervised word sense disambiguation." Proceedings of the Eighth Conference on Computational Natural Language Learning (CoNLL-2004) at HLT-NAACL 2004. 2004.

APA <a href="https://aclanthology.org/W04-2404.pdf" target="_blank">https://aclanthology.org/W04-2404.pdf</a> <a href="#fnref:20" class="footnote-back-ref">↩</a></li>
<li id="fn:21">Florian, Radu, et al. "Named entity recognition through classifier combination." Proceedings of the seventh conference on Natural language learning at HLT-NAACL 2003. 2003. <a href="https://aclanthology.org/W03-0425.pdf" target="_blank">https://aclanthology.org/W03-0425.pdf</a> <a href="#fnref:21" class="footnote-back-ref">↩</a></li>
<li id="fn:22">Chang, Haw-Shiuan; Vembu, Shankar; Mohan, Sunil; Uppaal, Rheeya; McCallum, Andrew (2020-09-01). "Using error decay prediction to overcome practical issues of deep active learning for named entity recognition". Machine Learning. 109 (9): 1749–1778. arXiv:1911.07335. doi:10.1007/s10994-020-05897-1. ISSN 1573-0565. <a href="https://doi.org/10.1007%2Fs10994-020-05897-1" target="_blank">https://doi.org/10.1007%2Fs10994-020-05897-1</a> <a href="#fnref:22" class="footnote-back-ref">↩</a></li>
<li id="fn:23">Gao, Wenchao; Li, Yu; Guan, Xiaole; Chen, Shiyu; Zhao, Shanshan (2022-08-25). "Research on Named Entity Recognition Based on Multi-Task Learning and Biaffine Mechanism". Computational Intelligence and Neuroscience. 2022: e2687615. doi:10.1155/2022/2687615. ISSN 1687-5265. PMC 9436550. PMID 36059424. <a href="https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9436550" target="_blank">https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9436550</a> <a href="#fnref:23" class="footnote-back-ref">↩</a></li>
<li id="fn:24">Chang, Haw-Shiuan; Vembu, Shankar; Mohan, Sunil; Uppaal, Rheeya; McCallum, Andrew (2020-09-01). "Using error decay prediction to overcome practical issues of deep active learning for named entity recognition". Machine Learning. 109 (9): 1749–1778. arXiv:1911.07335. doi:10.1007/s10994-020-05897-1. ISSN 1573-0565. <a href="https://doi.org/10.1007%2Fs10994-020-05897-1" target="_blank">https://doi.org/10.1007%2Fs10994-020-05897-1</a> <a href="#fnref:24" class="footnote-back-ref">↩</a></li>
<li id="fn:25">Gao, Wenchao; Li, Yu; Guan, Xiaole; Chen, Shiyu; Zhao, Shanshan (2022-08-25). "Research on Named Entity Recognition Based on Multi-Task Learning and Biaffine Mechanism". Computational Intelligence and Neuroscience. 2022: e2687615. doi:10.1155/2022/2687615. ISSN 1687-5265. PMC 9436550. PMID 36059424. <a href="https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9436550" target="_blank">https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9436550</a> <a href="#fnref:25" class="footnote-back-ref">↩</a></li>
<li id="fn:26">Rozovskaya, Alla, and Dan Roth. "Grammatical error correction: Machine translation and classifiers." Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2016. <a href="https://aclanthology.org/P16-1208.pdf" target="_blank">https://aclanthology.org/P16-1208.pdf</a> <a href="#fnref:26" class="footnote-back-ref">↩</a></li>
<li id="fn:27">Tan, Zhixing; Wang, Shuo; Yang, Zonghan; Chen, Gang; Huang, Xuancheng; Sun, Maosong; Liu, Yang (2020-01-01). "Neural machine translation: A review of methods, resources, and tools". AI Open. 1: 5–21. arXiv:2012.15515. doi:10.1016/j.aiopen.2020.11.001. ISSN 2666-6510. <a href="https://doi.org/10.1016%2Fj.aiopen.2020.11.001" target="_blank">https://doi.org/10.1016%2Fj.aiopen.2020.11.001</a> <a href="#fnref:27" class="footnote-back-ref">↩</a></li>
<li id="fn:28">A. Thakur, L. Ahuja, R. Vashisth and R. Simon, "NLP & AI Speech Recognition: An Analytical Review," 2023 10th International Conference on Computing for Sustainable Global Development (INDIACom), New Delhi, India, 2023, pp. 1390-1396. <a href="https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10112511" target="_blank">https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10112511</a> <a href="#fnref:28" class="footnote-back-ref">↩</a></li>
<li id="fn:29">Iosif, Elias; Klasinas, Ioannis; Athanasopoulou, Georgia; Palogiannidi, Elisavet; Georgiladakis, Spiros; Louka, Katerina; Potamianos, Alexandros (2018-01-01). "Speech understanding for spoken dialogue systems: From corpus harvesting to grammar rule induction". Computer Speech & Language. 47: 272–297. doi:10.1016/j.csl.2017.08.002. ISSN 0885-2308. <a href="https://www.sciencedirect.com/science/article/pii/S0885230816302613" target="_blank">https://www.sciencedirect.com/science/article/pii/S0885230816302613</a> <a href="#fnref:29" class="footnote-back-ref">↩</a></li>
<li id="fn:30">Hoppe, Dorothée B.; Hendriks, Petra; Ramscar, Michael; van Rij, Jacolien (2022-10-01). "An exploration of error-driven learning in simple two-layer networks from a discriminative learning perspective". Behavior Research Methods. 54 (5): 2221–2251. doi:10.3758/s13428-021-01711-5. ISSN 1554-3528. PMC 9579095. PMID 35032022. <a href="https://doi.org/10.3758/s13428-021-01711-5" target="_blank">https://doi.org/10.3758/s13428-021-01711-5</a> <a href="#fnref:30" class="footnote-back-ref">↩</a></li>
<li id="fn:31">Ajila, Samuel A.; Lung, Chung-Horng; Das, Anurag (2022-06-01). "Analysis of error-based machine learning algorithms in network anomaly detection and categorization". Annals of Telecommunications. 77 (5): 359–370. Bibcode:2022AnTel..77..359A. doi:10.1007/s12243-021-00836-0. ISSN 1958-9395. <a href="https://doi.org/10.1007/s12243-021-00836-0" target="_blank">https://doi.org/10.1007/s12243-021-00836-0</a> <a href="#fnref:31" class="footnote-back-ref">↩</a></li>
<li id="fn:32">Hoppe, Dorothée B.; Hendriks, Petra; Ramscar, Michael; van Rij, Jacolien (2022-10-01). "An exploration of error-driven learning in simple two-layer networks from a discriminative learning perspective". Behavior Research Methods. 54 (5): 2221–2251. doi:10.3758/s13428-021-01711-5. ISSN 1554-3528. PMC 9579095. PMID 35032022. <a href="https://doi.org/10.3758/s13428-021-01711-5" target="_blank">https://doi.org/10.3758/s13428-021-01711-5</a> <a href="#fnref:32" class="footnote-back-ref">↩</a></li>
</ol>

Error-driven learning open-in-new

Error-driven learning