Spelling suggestions: "subject:"1earning bias"" "subject:"_learning bias""
1 |
Methodology Development for Improving the Performance of Critical Classification ApplicationsAfrose, Sharmin 17 January 2023 (has links)
People interact with different critical applications in day-to-day life. Some examples of critical applications include computer programs, anonymous vehicles, digital healthcare, smart homes, etc. There are inherent risks in these critical applications if they fail to perform properly. In my dissertation, we mainly focus on developing methodologies for performance improvement for software security and healthcare prognosis. Cryptographic vulnerability tools are used to detect misuses of Java cryptographic APIs and thus classify secure and insecure parts of code. These detection tools are critical applications as misuse of cryptographic libraries and APIs causes devastating security and privacy implications. We develop two benchmarks that help developers to identify secure and insecure code usage as well as improve their tools. We also perform a comparative analysis of four static analysis tools. The developed benchmarks enable the first scientific comparison of the accuracy and scalability of cryptographic API misuse detection. Many published detection tools (CryptoGuard, CrySL, Oracle Parfait) have used our benchmarks to improve their performance in terms of the detection capability of insecure cases. We also examine the need for performance improvement for healthcare applications. Numerous prediction applications are developed to predict patients' health conditions. These are critical applications where misdiagnosis can cause serious harm to patients, even death. Due to the imbalanced nature of many clinical datasets, our work provides empirical evidence showing various prediction deficiencies in a typical machine learning model. We observe that missed death cases are 3.14 times higher than missed survival cases for mortality prediction. Also, existing sampling methods and other techniques are not well-equipped to achieve good performance. We design a double prioritized (DP) technique to mitigate representational bias or disparities across race and age groups. we show DP consistently boosts the minority class recall for underrepresented groups, by up to 38.0%. Our DP method also shows better performance than the existing methods in terms of reducing relative disparity by up to 88% in terms of minority class recall. Incorrect classification in these critical applications can have significant ramifications. Therefore, it is imperative to improve the performance of critical applications to alleviate risk and harm to people. / Doctor of Philosophy / We interact with many software using our devices in our everyday life. Examples of software usage include calling transport using Lyft or Uber, doing online shopping using eBay, using social media via Twitter, check payment status from credit card accounts or bank accounts. Many of these software use cryptography to secure our personal and financial information. However, the inappropriate or improper use of cryptography can let the malicious party gain sensitive information. To capture the inappropriate usage of cryptographic functions, there are several detection tools are developed. However, to compare the coverage of the tools, and the depth of detection of these tools, suitable benchmarks are needed. To bridge this gap, we aim to build two cryptographic benchmarks that are currently used by many tool developers to improve their performance and compare their tools with the existing tools. In another aspect, people see physicians and are admitted to hospitals if needed. Physicians also use different software that assists them in caring the patients. Among this software, many of them are built using machine learning algorithms to predict patients' conditions. The historical medical information or clinical dataset is taken as input to the prediction models. Clinical datasets contain information about patients of different races and ages. The number of samples in some groups of patients may be larger than in other groups. For example, many clinical datasets contain more white patients (i.e., majority group) than Black patients (i.e., minority group). Prediction models built on these imbalanced clinical data may provide inaccurate predictions for minority patients. Our work aims to improve the prediction accuracy for minority patients in important medical applications, such as estimating the likelihood of a patient dying in an emergency room visit or surviving cancer. We design a new technique that builds customized prediction models for different demographic groups. Our results reveal that subpopulation-specific models show better performance for minority groups. Our work contributes to improving the medical care of minority patients in the age of digital health. Overall, our aim is to improve the performance of critical applications to help people by decreasing risk. Our developed methods can be applicable to other critical application domains.
|
2 |
Les biais dans le traitement et l'apprentissage phonologiques / Biases in phonological processing and learningMartin, Alexander 30 June 2017 (has links)
Pendant la perception de la parole, les locuteurs sont biaisés par un grand nombre de facteurs. Par exemple, il existe des limitations cognitives comme la mémoire ou l’attention, mais aussi des limitations linguistiques comme leur langue maternelle. Cette thèse se concentre sur deux de ces facteurs : les biais de traitement pendant la reconnaissance des mots, et les biais d’apprentissage pendant le processus de transmission. Ces facteurs peuvent se combiner et, au cours du temps, influencer l’évolution des langues. Dans la première partie de cette thèse, nous nous concentrons sur le processus de la reconnaissance des mots. Des recherches antérieures ont établi l’importance des traits phonologiques (p. ex. le voisement ou le lieu d’articulation) pendant le traitement de la parole. Cependant, nous en savons peu sur leur poids relatif les uns par rapport aux autres, et comment cela peut influencer la capacité des locuteurs à reconnaître les mots. Nous avons testé des locuteurs français sur leur capacité à reconnaître des mots mal prononcés et avons trouvé que les traits de mode et de lieu sont plus importants que le trait de voisement. Nous avons ensuite considéré deux sources de cette asymétrie et avons trouvé que les locuteurs sont biaisés et par la perception acoustique ascendante (les contrastes de mode sont plus facile à percevoir à cause de leur distance acoustique importante) et par la connaissance lexicale descendante (le trait de lieu est plus exploité dans le lexique français que les autres traits). Nous suggérons que ces deux sources de biais se combinent pour influencer les locuteurs lors de la reconnaissance des mots. Dans la seconde partie de cette thèse, nous nous concentrons sur la question d’un biais d’apprentissage. Il a été suggéré que les apprenants peuvent être biaisés vers l’apprentissage de certains patrons phonologiques grâce à leurs connaissances phonétiques. Cela peut alors expliquer pourquoi certains patrons sont récurrents dans la typologie, tandis que d’autres restent rares ou non-attestés. Plus spécifiquement, nous avons exploré le rôle d’un biais d’apprentissage sur l’acquisition de la règle typologiquement commune de l’harmonie vocalique comparée à celle de la règle non-attestée (mais logiquement équivalente) de la disharmonie vocalique. Nous avons trouvé des preuves d’un biais d’apprentissage aussi bien en perception qu’en production. En utilisant un modèle d’apprentissage itéré simulé, nous avons ensuite montré comment un biais, même petit, favorisant l’un des patrons, peut influencer la typologie linguistique au cours du temps et donc expliquer (en partie) la prépondérance de systèmes harmoniques. De plus, nous avons exploré le rôle du sommeil sur la consolidation mnésique. Nous avons montré que seul le patron commun bénéficie d’une consolidation et que cela est un facteur supplémentaire pouvant contribuer à l’asymétrie typologique. Dans l’ensemble, cette thèse considère certaines des sources de biais possibles chez l’individu et discute de comment ces influences peuvent, au cours du temps, faire évoluer les systèmes linguistiques. Nous avons démontré la nature dynamique et complexe du traitement de la parole, à la fois en perception et dans l’apprentissage. De futurs travaux devront explorer plus en détail comment ces différentes sources de biais sont pondérées les unes relativement aux autres. / During speech perception, listeners are biased by a great number of factors, including cognitive limitations such as memory and attention and linguistic limitations such as their native language. This thesis focuses on two of these factors: processing bias during word recognition, and learning bias during the transmission process. These factors are combinatorial and can, over time, affect the way languages evolve. In the first part of this thesis, we focus on the process of word recognition. Previous research has established the importance of phonological features (e.g., voicing or place of articulation) during speech processing, but little is known about their weight relative to one another, and how this influences listeners' ability to recognize words. We tested French participants on their ability to recognize mispronounced words and found that the manner and place features were more important than the voicing feature. We then explored two sources of this asymmetry and found that listeners were biased both by bottom-up acoustic perception (manner contrasts are easier to perceive because of their acoustic distance compared to the other features) and top-down lexical knowledge (the place feature is used more in the French lexicon than the other two features). We suggest that these two sources of bias coalesce during the word recognition process to influence listeners. In the second part of this thesis, we turn to the question of bias during the learning process. It has been suggested that language learners may be biased towards the learning of certain phonological patterns because of phonetic knowledge they have. This in turn can explain why certain patterns are recurrent in the typology while others remain rare or unattested. Specifically, we explored the role of learning bias on the acquisition of the typologically common rule of vowel harmony compared to the unattested (but logically equivalent) rule of vowel disharmony. We found that in both perception and production, there was evidence of a learning bias, and using a simulated iterated learning model, showed how even a small bias favoring one pattern over the other could influence the linguistic typology over time, thus explaining (in part) the prevalence of harmonic systems. We additionally explored the role of sleep on memory consolidation and showed evidence that the common pattern benefits from consolidation that the unattested pattern does not, a factor that may also contribute to the typological asymmetry. Overall, this thesis considers a few of the wide-ranging sources of bias in the individual and discusses how these influences can over time shape linguistic systems. We demonstrate the dynamic and complicated nature of speech processing (both in perception and learning) and open the door for future research to explore in finer detail just how these different sources of bias are weighted relative to one another.
|
Page generated in 0.0542 seconds