Tesis sobre el tema "Explicability"
Crea una cita precisa en los estilos APA, MLA, Chicago, Harvard y otros
Consulte los 18 mejores tesis para su investigación sobre el tema "Explicability".
Junto a cada fuente en la lista de referencias hay un botón "Agregar a la bibliografía". Pulsa este botón, y generaremos automáticamente la referencia bibliográfica para la obra elegida en el estilo de cita que necesites: APA, MLA, Harvard, Vancouver, Chicago, etc.
También puede descargar el texto completo de la publicación académica en formato pdf y leer en línea su resumen siempre que esté disponible en los metadatos.
Explore tesis sobre una amplia variedad de disciplinas y organice su bibliografía correctamente.
Bettinger, Alexandre. "Influence indépendante et explicabilité de l’exploration et de l’exploitation dans les métaheuristiques". Electronic Thesis or Diss., Université de Lorraine, 2022. http://www.theses.fr/2022LORR0190.
Texto completoRecommendation is the act of filtering information to target items (resources) that may be of interest to one or more users. In the context of digital textbooks, items are educational resources (lesson, exercise, chapter, video and others). This task can be seen as processing a large search space that represents the set of possible recommendations. Depending on the context of the recommendation, a recommendation can take different forms such as items, itemsets or item sequences.Note that recommender environments can be subject to a number of randomness and recommendation constraints.In this thesis, we are interested in the recommendation of itemsets (also called vectors or solutions) by metaheuristics.The issues of this thesis are interested in the influence of exploration and exploitation, in data reduction and in the explicability of exploration and exploitation
Risser-Maroix, Olivier. "Similarité visuelle et apprentissage de représentations". Electronic Thesis or Diss., Université Paris Cité, 2022. http://www.theses.fr/2022UNIP7327.
Texto completoThe objective of this CIFRE thesis is to develop an image search engine, based on computer vision, to assist customs officers. Indeed, we observe, paradoxically, an increase in security threats (terrorism, trafficking, etc.) coupled with a decrease in the number of customs officers. The images of cargoes acquired by X-ray scanners already allow the inspection of a load without requiring the opening and complete search of a controlled load. By automatically proposing similar images, such a search engine would help the customs officer in his decision making when faced with infrequent or suspicious visual signatures of products. Thanks to the development of modern artificial intelligence (AI) techniques, our era is undergoing great changes: AI is transforming all sectors of the economy. Some see this advent of "robotization" as the dehumanization of the workforce, or even its replacement. However, reducing the use of AI to the simple search for productivity gains would be reductive. In reality, AI could allow to increase the work capacity of humans and not to compete with them in order to replace them. It is in this context, the birth of Augmented Intelligence, that this thesis takes place. This manuscript devoted to the question of visual similarity is divided into two parts. Two practical cases where the collaboration between Man and AI is beneficial are proposed. In the first part, the problem of learning representations for the retrieval of similar images is still under investigation. After implementing a first system similar to those proposed by the state of the art, one of the main limitations is pointed out: the semantic bias. Indeed, the main contemporary methods use image datasets coupled with semantic labels only. The literature considers that two images are similar if they share the same label. This vision of the notion of similarity, however fundamental in AI, is reductive. It will therefore be questioned in the light of work in cognitive psychology in order to propose an improvement: the taking into account of visual similarity. This new definition allows a better synergy between the customs officer and the machine. This work is the subject of scientific publications and a patent. In the second part, after having identified the key components allowing to improve the performances of thepreviously proposed system, an approach mixing empirical and theoretical research is proposed. This secondcase, augmented intelligence, is inspired by recent developments in mathematics and physics. First applied tothe understanding of an important hyperparameter (temperature), then to a larger task (classification), theproposed method provides an intuition on the importance and role of factors correlated to the studied variable(e.g. hyperparameter, score, etc.). The processing chain thus set up has demonstrated its efficiency byproviding a highly explainable solution in line with decades of research in machine learning. These findings willallow the improvement of previously developed solutions
Bourgeade, Tom. "Interprétabilité a priori et explicabilité a posteriori dans le traitement automatique des langues". Thesis, Toulouse 3, 2022. http://www.theses.fr/2022TOU30063.
Texto completoWith the advent of Transformer architectures in Natural Language Processing a few years ago, we have observed unprecedented progress in various text classification or generation tasks. However, the explosion in the number of parameters, and the complexity of these state-of-the-art blackbox models, is making ever more apparent the now urgent need for transparency in machine learning approaches. The ability to explain, interpret, and understand algorithmic decisions will become paramount as computer models start becoming more and more present in our everyday lives. Using eXplainable AI (XAI) methods, we can for example diagnose dataset biases, spurious correlations which can ultimately taint the training process of models, leading them to learn undesirable shortcuts, which could lead to unfair, incomprehensible, or even risky algorithmic decisions. These failure modes of AI, may ultimately erode the trust humans may have otherwise placed in beneficial applications. In this work, we more specifically explore two major aspects of XAI, in the context of Natural Language Processing tasks and models: in the first part, we approach the subject of intrinsic interpretability, which encompasses all methods which are inherently easy to produce explanations for. In particular, we focus on word embedding representations, which are an essential component of practically all NLP architectures, allowing these mathematical models to process human language in a more semantically-rich way. Unfortunately, many of the models which generate these representations, produce them in a way which is not interpretable by humans. To address this problem, we experiment with the construction and usage of Interpretable Word Embedding models, which attempt to correct this issue, by using constraints which enforce interpretability on these representations. We then make use of these, in a simple but effective novel setup, to attempt to detect lexical correlations, spurious or otherwise, in some popular NLP datasets. In the second part, we explore post-hoc explainability methods, which can target already trained models, and attempt to extract various forms of explanations of their decisions. These can range from diagnosing which parts of an input were the most relevant to a particular decision, to generating adversarial examples, which are carefully crafted to help reveal weaknesses in a model. We explore a novel type of approach, in parts allowed by the highly-performant but opaque recent Transformer architectures: instead of using a separate method to produce explanations of a model's decisions, we design and fine-tune an architecture which jointly learns to both perform its task, while also producing free-form Natural Language Explanations of its own outputs. We evaluate our approach on a large-scale dataset annotated with human explanations, and qualitatively judge some of our approach's machine-generated explanations
Raizonville, Adrien. "Regulation and competition policy of the digital economy : essays in industrial organization". Electronic Thesis or Diss., Institut polytechnique de Paris, 2021. http://www.theses.fr/2021IPPAT028.
Texto completoThis thesis addresses two issues facing regulators in the digital economy: the informational challenge generated by the use of new artificial intelligence technologies and the problem of the market power of large digital platforms. The first chapter of this thesis explores the implementation of a (costly and imperfect) audit system by a regulator seeking to limit the risk of damage generated by artificial intelligence technologies as well as its cost of regulation. Firms may invest in explainability to better understand their technologies and, thus, reduce their cost of compliance. When audit efficacy is not affected by explainability, firms invest voluntarily in explainability. Technology-specific regulation induces greater explainability and compliance than technology-neutral regulation. If, instead, explainability facilitates the regulator's detection of misconduct, a firm may hide its misconduct behind algorithmic opacity. Regulatory opportunism further deters investment in explainability. To promote explainability and compliance, command-and-control regulation with minimum explainability standards may be needed. The second chapter studies the effects of implementing a coopetition strategy between two two-sided platforms on the subscription prices of their users, in a growing market (i.e., in which new users can join the platform) and in a mature market. More specifically, the platforms cooperatively set the subscription prices of one group of users (e.g., sellers) and the prices of the other group (e.g., buyers) non-cooperatively. By cooperating on the subscription price of sellers, each platform internalizes the negative externality it exerts on the other platform when it reduces its price. This leads the platforms to increase the subscription price for sellers relative to the competitive situation. At the same time, as the economic value of sellers increases and as buyers exert a positive cross-network effect on sellers, competition between platforms to attract buyers intensifies, leading to a lower subscription price for buyers. The increase in total surplus only occurs when new buyers can join the market. Finally, the third chapter examines interoperability between an incumbent platform and a new entrant as a regulatory tool to improve market contestability and limit the market power of the incumbent platform. Interoperability allows network effects to be shared between the two platforms, thereby reducing the importance of network effects in users' choice of subscription to a platform. The preference to interact with exclusive users of the other platform leads to multihoming when interoperability is not perfect. Interoperability leads to a reduction in demand for the incumbent platform, which reduces its subscription price. In contrast, for relatively low levels of interoperability, demand for the entrant platform increases, as does its price and profit, before decreasing for higher levels of interoperability. Users always benefit from the introduction of interoperability
Parekh, Jayneel. "A Flexible Framework for Interpretable Machine Learning : application to image and audio classification". Electronic Thesis or Diss., Institut polytechnique de Paris, 2023. http://www.theses.fr/2023IPPAT032.
Texto completoMachine learning systems and specially neural networks, have rapidly grown in their ability to address complex learning problems. Consequently, they are being integrated into society with an ever-rising influence on all levels of human experience. This has resulted in a need to gain human-understandable insights in their decision making process to ensure the decisions are being made ethically and reliably. The study and development of methods which can generate such insightsbroadly constitutes the field of interpretable machine learning. This thesis aims to develop a novel framework that can tackle two major problem settings in this field, post-hoc and by-design interpretation. Posthoc interpretability devises methods to interpret decisionsof a pre-trained predictive model, while by-design interpretability targets to learn a single model capable of both prediction and interpretation. To this end, we extend the traditional supervised learning formulation to include interpretation as an additional task besides prediction,each addressed by separate but related models, a predictor and an interpreter. Crucially, the interpreter is dependent on the predictor through its hidden layers and utilizes a dictionary of concepts as its representation for interpretation with the capacity to generate local and globalinterpretations. The framework is separately instantiated to address interpretability problems in the context of image and audio classification. Both systems are extensively evaluated for their interpretations on multiple publicly available datasets. We demonstrate high predictiveperformance and fidelity of interpretations in both cases. Despite adhering to the same underlying structure the two systems are designed differently for interpretations.The image interpretability system advances the pipeline for discovering learnt concepts for improvedunderstandability that is qualitatively evaluated. The audio interpretability system instead is designed with a novel representation based on non-negative matrix factorization to facilitate listenable interpretations whilst modeling audio objects composing a scene
Fauvel, Kevin. "Enhancing performance and explainability of multivariate time series machine learning methods : applications for social impact in dairy resource monitoring and earthquake early warning". Thesis, Rennes 1, 2020. http://www.theses.fr/2020REN1S043.
Texto completoThe prevalent deployment and usage of sensors in a wide range of sectors generate an abundance of multivariate data which has proven to be instrumental for researches, businesses and policies. More specifically, multivariate data which integrates temporal evolution, i.e. Multivariate Time Series (MTS), has received significant interests in recent years, driven by high resolution monitoring applications (e.g. healthcare, mobility) and machine learning. However, for many applications, the adoption of machine learning methods cannot rely solely on their prediction performance. For example, the European Union’s General Data Protection Regulation, which became enforceable on 25 May 2018, introduces a right to explanation for all individuals so that they can obtain “meaningful explanations of the logic involved” when automated decision-making has “legal effects” on individuals or similarly “significantly affecting” them. The current best performing state-of-the-art MTS machine learning methods are “black-box” models, i.e. complicated-to-understand models, which rely on explainability methods providing explanations from any machine learning model to support their predictions (post-hoc model-agnostic). The main line of work in post-hoc model-agnostic explainability methods approximates the decision surface of a model using an explainable surrogate model. However, the explanations from the surrogate models cannot be perfectly faithful with respect to the original model, which is a prerequisite for numerous applications. Faithfulness is critical as it corresponds to the level of trust an end-user can have in the explanations of model predictions, i.e. the level of relatedness of the explanations to what the model actually computes. This thesis introduces new approaches to enhance both performance and explainability of MTS machine learning methods, and derive insights from the new methods about two real-world applications
Radulovic, Nedeljko. "Post-hoc Explainable AI for Black Box Models on Tabular Data". Electronic Thesis or Diss., Institut polytechnique de Paris, 2023. http://www.theses.fr/2023IPPAT028.
Texto completoCurrent state-of-the-art Artificial Intelligence (AI) models have been proven to be verysuccessful in solving various tasks, such as classification, regression, Natural Language Processing(NLP), and image processing. The resources that we have at our hands today allow us to trainvery complex AI models to solve different problems in almost any field: medicine, finance, justice,transportation, forecast, etc. With the popularity and widespread use of the AI models, the need toensure the trust in them also grew. Complex as they come today, these AI models are impossible to be interpreted and understood by humans. In this thesis, we focus on the specific area of research, namely Explainable Artificial Intelligence (xAI), that aims to provide the approaches to interpret the complex AI models and explain their decisions. We present two approaches STACI and BELLA which focus on classification and regression tasks, respectively, for tabular data. Both methods are deterministic model-agnostic post-hoc approaches, which means that they can be applied to any black-box model after its creation. In this way, interpretability presents an added value without the need to compromise on black-box model's performance. Our methods provide accurate, simple and general interpretations of both the whole black-box model and its individual predictions. We confirmed their high performance through extensive experiments and a user study
Bennetot, Adrien. "A Neural-Symbolic learning framework to produce interpretable predictions for image classification". Electronic Thesis or Diss., Sorbonne université, 2022. http://www.theses.fr/2022SORUS418.
Texto completoArtificial Intelligence has been developing exponentially over the last decade. Its evolution is mainly linked to the progress of computer graphics card processors, allowing to accelerate the calculation of learning algorithms, and to the access to massive volumes of data. This progress has been principally driven by a search for quality prediction models, making them extremely accurate but opaque. Their large-scale adoption is hampered by their lack of transparency, thus causing the emergence of eXplainable Artificial Intelligence (XAI). This new line of research aims at fostering the use of learning models based on mass data by providing methods and concepts to obtain explanatory elements concerning their functioning. However, the youth of this field causes a lack of consensus and cohesion around the key definitions and objectives governing it. This thesis contributes to the field through two perspectives, one through a theory of what is XAI and how to achieve it and one practical. The first is based on a thorough review of the literature, resulting in two contributions: 1) the proposal of a new definition for Explainable Artificial Intelligence and 2) the creation of a new taxonomy of existing explainability methods. The practical contribution consists of two learning frameworks, both based on a paradigm aiming at linking the connectionist and symbolic paradigms
Bove, Clara. "Conception et évaluation d’interfaces utilisateur explicatives pour systèmes complexes en apprentissage automatique". Electronic Thesis or Diss., Sorbonne université, 2023. https://accesdistant.sorbonne-universite.fr/login?url=https://theses-intra.sorbonne-universite.fr/2023SORUS247.pdf.
Texto completoThis thesis focuses on human-centered eXplainable AI (XAI) and more specif- ically on the intelligibility of Machine Learning (ML) explanations for non-expert users. The technical context is as follows: on one side, either an opaque classifier or regressor provides a prediction, with an XAI post-hoc approach that generates pieces of information as explanations; on the other side, the user receives both the prediction and the explanations. Within this XAI technical context, several is- sues might lessen the quality of explanations. The ones we focus on are: the lack of contextual information in ML explanations, the unguided design of function- alities or the user’s exploration, as well as confusion that could be caused when delivering too much information. To solve these issues, we develop an experimental procedure to design XAI functional interfaces and evaluate the intelligibility of ML explanations by non-expert users. Doing so, we investigate the XAI enhancements provided by two types of local explanation components: feature importance and counterfac- tual examples. Thus, we propose generic XAI principles for contextualizing and allowing exploration on feature importance; and for guiding users in their com- parative analysis of counterfactual explanations with plural examples. We pro- pose an implementation of such principles into two distinct explanation-based user interfaces, respectively for an insurance and a financial scenarios. Finally, we use the enhanced interfaces to conduct users studies in lab settings and to measure two dimensions of intelligibility, namely objective understanding and subjective satisfaction. For local feature importance, we demonstrate that con- textualization and exploration improve the intelligibility of such explanations. Similarly for counterfactual examples, we demonstrate that the plural condition improve the intelligibility as well, and that comparative analysis appears to be a promising tool for users’ satisfaction. At a fundamental level, we consider the issue of inconsistency within ML explanations from a theoretical point of view. In the explanation process consid- ered for this thesis, the quality of an explanation relies both on the ability of the Machine Learning system to generate a coherent explanation and on the ability of the end user to make a correct interpretation of these explanations. Thus, there can be limitations: on one side, as reported in the literature, technical limitations of ML systems might produce potentially inconsistent explanations; on the other side, human inferences can be inaccurate, even if users are presented with con- sistent explanations. Investigating such inconsistencies, we propose an ontology to structure the most common ones from the literature. We advocate that such an ontology can be useful to understand current XAI limitations for avoiding explanations pitfalls
Faille, Juliette. "Data-Based Natural Language Generation : Evaluation and Explainability". Electronic Thesis or Diss., Université de Lorraine, 2023. http://www.theses.fr/2023LORR0305.
Texto completoRecent Natural Language Generation (NLG) models achieve very high average performance. Their output texts are generally grammatically and syntactically correct which makes them sound natural. Though the semantics of the texts are right in most cases, even the state-of-the-art NLG models still produce texts with partially incorrect meanings. In this thesis, we propose evaluating and analyzing content-related issues of models used in the NLG tasks of Resource Description Framework (RDF) graphs verbalization and conversational question generation. First, we focus on the task of RDF verbalization and the omissions and hallucinations of RDF entities, i.e. when an automatically generated text does not mention all the input RDF entities or mentions other entities than those in the input. We evaluate 25 RDF verbalization models on the WebNLG dataset. We develop a method to automatically detect omissions and hallucinations of RDF entities in the outputs of these models. We propose a metric based on omissions or hallucination counts to quantify the semantic adequacy of the NLG models. We find that this metric correlates well with what human annotators consider to be semantically correct and show that even state-of-the-art models are subject to omissions and hallucinations. Following this observation about the tendency of RDF verbalization models to generate texts with content-related issues, we propose to analyze the encoder of two such state-of-the-art models, BART and T5. We use the probing explainability method and introduce two probing classifiers (one parametric and one non-parametric) to detect omissions and distortions of RDF input entities in the embeddings of the encoder-decoder models. We find that such probing classifiers are able to detect these mistakes in the encodings, suggesting that the encoder of the models is responsible for some loss of information about omitted and distorted entities. Finally, we propose a T5-based conversational question generation model that in addition to generating a question based on an input RDF graph and a conversational context, generates both a question and its corresponding RDF triples. This setting allows us to introduce a fine-grained evaluation procedure automatically assessing coherence with the conversation context and the semantic adequacy with the input RDF. Our contributions belong to the fields of NLG evaluation and explainability and use techniques and methodologies from these two research fields in order to work towards providing more reliable NLG models
De, oliveira Hugo. "Modélisation prédictive des parcours de soins à l'aide de techniques de process mining et de deep learning". Thesis, Lyon, 2020. http://www.theses.fr/2020LYSEM021.
Texto completoInitially created for a reimbursement purpose, non-clinical claim databases are exhaustive Electronic Health Records (EHRs) which are particularly valuable for evidence-based studies. The objective of this work is to develop predictive methods for patient pathways data, which leverage the complexity of non-clinical claims data and produce explainable results. Our first contribution focuses on the modeling of event logs extracted from such databases. New process models and an adapted process discovery algorithm are introduced, with the objective of accurately model characteristic transitions and time hidden in non-clinical claims data. The second contribution is a preprocessing solution to handle one complexity of such data, which is the representation of medical events by multiple codes belonging to different standard coding systems, organized in hierarchical structures. The proposed method uses auto-encoders and clustering in an adequate latent space to automatically produce relevant and explainable labels. From these contributions, an optimization-based predictive method is introduced, which uses a process model to perform binary classification from event logs and highlight distinctive patterns as a global explanation. A second predictive method is also proposed, which uses images to represent patient pathways and a modified Variational Auto-Encoders (VAE) to predict. This method globally explains predictions by showing an image of identified predictive factors which can be both frequent and infrequent
Jeyasothy, Adulam. "Génération d'explications post-hoc personnalisées". Electronic Thesis or Diss., Sorbonne université, 2024. http://www.theses.fr/2024SORUS027.
Texto completoThis thesis is in the field of eXplainable AI (XAI). We focus on post-hoc interpretability methods that aim to explain to a user the prediction for a specific data made by a trained decision model. To increase the interpretability of explanations, this thesis studies the integration of user knowledge into these methods, and thus aims to improve the understandability of the explanation by generating personalized explanations tailored to each user. To this end, we propose a general formalism that explicitly integrates knowledge via a new criterion in the interpretability objectives. This formalism is then declined for different types of knowledge and different types of explanations, particularly counterfactual examples, leading to the proposal of several algorithms (KICE, Knowledge Integration in Counterfactual Explanation, rKICE for its variant including knowledge expressed by rules and KISM, Knowledge Integration in Surrogate Models). The issue of aggregating classical quality and knowledge compatibility constraints is also studied, and we propose to use Gödel's integral as an aggregation operator. Finally, we discuss the difficulty of generating a single explanation suitable for all types of users and the notion of diversity in explanations
Afchar, Darius. "Interpretable Music Recommender Systems". Electronic Thesis or Diss., Sorbonne université, 2023. http://www.theses.fr/2023SORUS608.
Texto completo‘‘Why do they keep recommending me this music track?’’ ‘‘Why did our system recommend these tracks to users?’’ Nowadays, streaming platforms are the most common way to listen to recorded music. Still, music recommendations — at the heart of these platforms — are not an easy feat. Sometimes, both users and engineers may be equally puzzled about the behaviour of a music recommendation system (MRS). MRS have been successfully employed to help explore catalogues that may be as large as tens of millions of music tracks. Built and optimised for accuracy, real-world MRS often end up being quite complex. They may further rely on a range of interconnected modules that, for instance, analyse audio signals, retrieve metadata about albums and artists, collect and aggregate user feedbacks on the music service, and compute item similarities with collaborative filtering. All this complexity hinders the ability to explain recommendations and, more broadly, explain the system. Yet, explanations are essential for users to foster a long-term engagement with a system that they can understand (and forgive), and for system owners to rationalise failures and improve said system. Interpretability may also be needed to check the fairness of a decision or can be framed as a means to control the recommendations better. Moreover, we could also recursively question: Why does an explanation method explain in a certain way? Is this explanation relevant? What could be a better explanation? All these questions relate to the interpretability of MRSs. In the first half of this thesis, we explore the many flavours that interpretability can have in various recommendation tasks. Indeed, since there is not just one recommendation task but many (e.g., sequential recommendation, playlist continuation, artist similarity), as well as many angles through which music may be represented and processed (e.g., metadata, audio signals, embeddings computed from listening patterns), there are as many settings that require specific adjustments to make explanations relevant. A topic like this one can never be exhaustively addressed. This study was guided along some of the mentioned modalities of musical objects: interpreting implicit user logs, item features, audio signals and similarity embeddings. Our contribution includes several novel methods for eXplainable Artificial Intelligence (XAI) and several theoretical results, shedding new light on our understanding of past methods. Nevertheless, similar to how recommendations may not be interpretable, explanations about them may themselves lack interpretability and justifications. Therefore, in the second half of this thesis, we found it essential to take a step back from the rationale of ML and try to address a (perhaps surprisingly) understudied question in XAI: ‘‘What is interpretability?’’ Introducing concepts from philosophy and social sciences, we stress that there is a misalignment in the way explanations from XAI are generated and unfold versus how humans actually explain. We highlight that current research tends to rely too much on intuitions or hasty reduction of complex realities into convenient mathematical terms, which leads to the canonisation of assumptions into questionable standards (e.g., sparsity entails interpretability). We have treated this part as a comprehensive tutorial addressed to ML researchers to better ground their knowledge of explanations with a precise vocabulary and a broader perspective. We provide practical advice and highlight less popular branches of XAI better aligned with human cognition. Of course, we also reflect back and recontextualise our methods proposed in the previous part. Overall, this enables us to formulate some perspective for our field of XAI as a whole, including its more critical and promising next steps as well as its shortcomings to overcome
El, Qadi El Haouari Ayoub. "An EXplainable Artificial Intelligence Credit Rating System". Electronic Thesis or Diss., Sorbonne université, 2023. http://www.theses.fr/2023SORUS486.
Texto completoOver the past few years, the trade finance gap has surged to an alarming 1.5 trillion dollars, underscoring a growing crisis in global commerce. This gap is particularly detrimental tosmall and medium-sized enterprises (SMEs), which often find it difficult to access trade finance. Traditional credit scoring systems, which are the backbone of trade finance, are not always tailored to assess the credit worthiness of SMEs adequately. The term credit scoring stands for the methods and techniques used to evaluate the credit worthiness of individuals or business. The score generated is then used by financial institutions to make decisions on loan approvals, interest rates, and credit limits. Credit scoring present several characteristics that makes it a challenging task. First, the lack of explainability in complex machine learning models often results in less acceptance of credit assessments, particulary among stakeholders who require transparent decision-making process. This opacity can be an obstacle in the widespread adoption of advanced scoring techniques. Another significant challenge is the variability in data availability across countries and the often incomplete financial records of SME's which makes it difficult to develop universally applicable models.In this thesis, we initially tackled the issue of explainability by employing state-of-the-art techniques in Explainable Artificial Intelligence (XAI). We introduced a novel strategy that involved comparing the explanations generated by machine learning models with the criteria used by credit experts. This comparative analysis revealed a divergence between the model's reasoning and the expert's judgment, underscoring the necessity of incorporating expert criteria into the training phase of the model. The findings suggest that aligning machine-generated explanations with human expertise could be a pivotal step in enhancing the model's acceptance and trustworthiness. Subsequently, we shifted our focus to address the challenge of sparse or incomplete financial data. We incorporated textual credit assessments into the credit scoring model using cutting-edge Natural Language Processing (NLP) techniques. Our results demon-strated that models trained with both financial data and textual credit assessments out-performed those relying solely on financial data. Moreover, we showed that our approach could effectively generate credit scores using only textual risk assessments, thereby offer-ing a viable solution for scenarios where traditional financial metrics are unavailable or insufficient
Ayats, H. Ambre. "Construction de graphes de connaissances à partir de textes avec une intelligence artificielle explicable et centrée-utilisateur·ice". Electronic Thesis or Diss., Université de Rennes (2023-....), 2023. http://www.theses.fr/2023URENS095.
Texto completoWith recent advances in artificial intelligence, the question of human control has become central. Today, this involves both research into explainability and designs centered around interaction with the user. What's more, with the expansion of the semantic web and automatic natural language processing methods, the task of constructing knowledge graphs from texts has become an important issue. This thesis presents a user-centered system for the construction of knowledge graphs from texts. This thesis presents several contributions. First, we introduce a user-centered workflow for the aforementioned task, having the property of progressively automating the user's actions while leaving them a fine-grained control over the outcome. Next, we present our contributions in the field of formal concept analysis, used to design an explainable instance-based learning module for relation classification. Finally, we present our contributions in the field of relation extraction, and how these fit into the presented workflow
Li, Honghao. "Interpretable biological network reconstruction from observational data". Electronic Thesis or Diss., Université Paris Cité, 2021. http://www.theses.fr/2021UNIP5207.
Texto completoThis thesis is focused on constraint-based methods, one of the basic types of causal structure learning algorithm. We use PC algorithm as a representative, for which we propose a simple and general modification that is applicable to any PC-derived methods. The modification ensures that all separating sets used during the skeleton reconstruction step to remove edges between conditionally independent variables remain consistent with respect to the final graph. It consists in iterating the structure learning algorithm while restricting the search of separating sets to those that are consistent with respect to the graph obtained at the end of the previous iteration. The restriction can be achieved with limited computational complexity with the help of block-cut tree decomposition of the graph skeleton. The enforcement of separating set consistency is found to increase the recall of constraint-based methods at the cost of precision, while keeping similar or better overall performance. It also improves the interpretability and explainability of the obtained graphical model. We then introduce the recently developed constraint-based method MIIC, which adopts ideas from the maximum likelihood framework to improve the robustness and overall performance of the obtained graph. We discuss the characteristics and the limitations of MIIC, and propose several modifications that emphasize the interpretability of the obtained graph and the scalability of the algorithm. In particular, we implement the iterative approach to enforce separating set consistency, and opt for a conservative rule of orientation, and exploit the orientation probability feature of MIIC to extend the edge notation in the final graph to illustrate different causal implications. The MIIC algorithm is applied to a dataset of about 400 000 breast cancer records from the SEER database, as a large-scale real-life benchmark
Cárdenas, Chapellín Julio José. "Inversion of geophysical data by deep learning". Electronic Thesis or Diss., Sorbonne université, 2022. http://www.theses.fr/2022SORUS185.
Texto completoThis thesis presents the characterization ofmagnetic anomalies using convolutional neural networks, and the application of visualization tools to understand and validate their predictions. The developed approach allows the localization of magnetic dipoles, including counting the number of dipoles, their geographical position, and the prediction of their parameters (magnetic moment, depth, and declination). Our results suggest that the combination of two deep learning models, "YOLO" and "DenseNet", performs best in achieving our classification and regression goals. Additionally, we applied visualization tools to understand our model’s predictions and its working principle. We found that the Grad-CAM tool improved prediction performance by identifying several layers that had no influence on the prediction and the t-SNE tool confirmed the good ability of our model to differentiate among different parameter combinations. Then, we tested our model with real data to establish its limitations and application domain. Results demonstrate that our model detects dipolar anomalies in a real magnetic map even after learning from a synthetic database with a lower complexity, which indicates a significant generalization capability. We also noticed that it is not able to identify dipole anomalies of shapes and sizes different from those considered for the creation of the synthetic database. Our current work consists in creating new databases by combining synthetic and real data to compare their potential influence in improving predictions. Finally, the perspectives of this work consist in validating the operational relevance and adaptability of our model under realistic conditions and in testing other applications with alternative geophysical methods
Esta tesis presenta la caracterización de anomalías magnéticas mediante redes neuronales convolucionales, y la aplicación de herramientas de visualización para entender y validar sus predicciones. El enfoque desarrollado permite la localización de dipolos magnéticos, incluyendo el recuento delnúmero de dipolos, su posición geográfica y la predicción de sus parámetros (momento magnético, profundidad y declinación). Nuestros resultados sugieren que la combinación de dos modelos de aprendizaje profundo, "YOLO" y "DenseNet", es la que mejor se ajusta a nuestros objetivos de clasificación y regresión. Adicionalmente, aplicamos herramientas de visualización para entender las predicciones de nuestromodelo y su principio de funcionamiento. Descubrimos que la herramienta Grad-CAM mejoraba el rendimiento de la predicción al identificar varias capas que no influían enla predicción y la herramienta t-SNE confirmaba la buena capacidad de nuestro modelo para diferenciar entre distintas combinaciones de parámetros. Seguidamente, probamos nuestro modelo con datos reales para establecer sus limitaciones y su rango de aplicación. Los resultados demuestran quenuestro modelo detecta anomalías dipolares en unmapa magnético real incluso después de aprender de una base de datos sintética con una complejidad menor, lo que indica una capacidad de generalización significativa. También observamos que no es capaz de identificar anomalías dipolares de formas y tamaños diferentes a los considerados para la creación de la base de datos sintética. Nuestro trabajo actual consiste en crear nuevas bases de datos combinando datos sintéticos y reales para comparar su posible influencia en la mejora de las predicciones. Por último, las perspectivas de este trabajo consisten en validar la pertinencia operativa y la adaptabilidad de nuestro modelo en condiciones realistas y en probar otras aplicaciones con métodos geofísicos alternativos
Barbieri, Emanuele. "Discrete Event Modeling and Simulation of Large Markov Decision Process : Application to the Leverage Effects in Financial Asset Optimization Processes". Electronic Thesis or Diss., Corte, 2023. http://hal-univ-corse.archives-ouvertes.fr/view_by_stamp.php?&action_todo=view&id.
Texto completoMarkov Decision Process (MDP) models are widely used to model decision-making problems in manyresearch fields. MDPs can be readily designed through modeling and simulation (M&S) using theDiscrete Event System Specification formalism (DEVS) due to its modular and hierarchical aspects,which improve the explainability of the models. In particular, the separation between the agent andthe environment components involved in the traditional reinforcement learning (RL) algorithm, suchas Q-Learning, is clearly formalized to enhance observability and envision the integration of AIcomponents in the decision-making process. Our proposed DEVS model also improves the trust ofdecision makers by mitigating the risk of delegation to machines in decision-making processes. Themain focus of this work is to provide the possibility of designing a Markovian system with a modelingand simulation formalism to optimize a decision-making process with greater explainability throughsimulation. Furthermore, the work involves an investigation based on financial process management,its specification as an MDP-based RL system, and its M&S with DEVS formalism. The DEVSimPyPython M&S environment is used to implement the Agent-Environment RL system as event-basedinteractions between Agent and Environment atomic models stored in a new DEVS-RL library. Theresearch work proposed in this thesis focused on a concrete case of portfolio management of stockmarket indices. Our DEVS-RL model allows for a leverage effect three times higher than some of themost important naive market indexes in the world over a thirty-year period and may contribute toaddressing the modern portfolio theory with a novel approach. The results of the DEVS-RL model arecompared in terms of compatibility and combined with popular optimization algorithms such asefficient frontier semivariance and neural network models like LSTM. This combination is used toaddress a decision-making management policy for complex systems evolving in highly volatileenvironments in which, the state evolution depends entirely on the occurrence of discreteasynchronous events over time