Ce travail a pour objet le développement d’un système combinant un algorithme génétique d’optimisation multiobjectifs avec des outils de thermodynamique prédictive de type calphad (calcul des diagrammes de phases) et de fouille de données permettant l’estimation des propriétés thermochimiques et thermomécaniques d’alliages multicomposants. L’intégration de ces techniques permet l’optimisation quasi-autonome de la composition d’alliages complexes vis-à-vis de plusieurs critères antagonistes telles les résistances mécaniques et chimiques, la stabilité microstructurelle à haute température et le coût. La méthode est complétée d’une technique d’analyse décisionnelle multicritères pour assister la sélection d’alliages. L’approche est illustrée par l’optimisation de la chimie de deux familles d’alliages multicomposants. Le premier cas d’étude porte sur les superalliages à base de nickel polycristallins corroyés renforcés par précipitation de la phase 0 destinés à la fabrication de disques de turbines dans l’aéronautique ou de tuyauteries de centrales thermiques. L’optimisation résulte en la conception d’alliages moins onéreux et prédits plus résistants que l’Inconel 740H et le Haynes 282, deux superalliages de dernière génération. Le second cas d’étude concerne les alliages dits « à forte entropie » dont la métallurgie singulière est emblématique des problèmes combinatoires. À l’issue de l’optimisation, quelques alliages à forte entropie ont été sélectionnés et fabriqués ; leur caractérisation expérimentale préliminaire met en évidence des propriétés attrayantes tel un ratio dureté sur masse volumique inédit. / The present work revolves around the development of an integrated system combining a multi-objective genetic algorithm with calphad-type computational thermodynamics (calculations of phase diagrams) and data mining techniques enabling the estimation of thermochemical and thermomechanical properties of multicomponent alloys. This integration allows the quasiautonomous chemistry optimisation of complex alloys against antagonistic criteria such as mechanical and chemical resistance, high-temperature microstructural stability, and cost. Further alloy selection capability is provided by a multi-criteria decision analysis technique. The proposed design methodology is illustrated on two multicomponent alloy families. The first case study relates to the design of wrought, polycrystalline 0-hardened nickel-base superalloys intended for aerospace turbine disks or tubing applications in the energy industry. The optimisation leads to the discovery of novel superalloys featuring lower costs and higher predicted strength than Inconel 740H and Haynes 282, two state-of-the-art superalloys. The second case study concerns the so-called “high-entropy alloys” whose singular metallurgy embodies typical combinatorial issues. Following the optimisation, several high-entropy alloys are produced; preliminary experimental characterisation highlights attractive properties such as an unprecedented hardness to density ratio.

The present thesis addresses machine learning in a domain of naturallanguage phrases that are names of universities. It describes two approaches to this problem and a software implementation that has made it possible to evaluate them and to compare them. In general terms, the system's task is to learn to 'understand' the significance of the various components of a university name, such as the city or region where the university is located, the scienti c disciplines that are studied there, or the name of a famous person which may be part of the university name. A concrete test for whether the system has acquired this understanding is when it is able to compose a plausible university name given some components that should occur in the name. In order to achieve this capability, our system learns the structure of available names of some universities in a given data set, i.e. it acquires a grammar for the microlanguage of university names. One of the challenges is that the system may encounter ambiguities due to multi meaning words. This problem is addressed using a small ontology that is created during the training phase. Both domain knowledge and grammatical knowledge is represented using decision trees, which is an ecient method for concept learning. Besides for inductive inference, their role is to partition the data set into a hierarchical structure which is used for resolving ambiguities. The present report also de nes some modi cations in the de nitions of parameters, for example a parameter for entropy, which enable the system to deal with cognitive uncertainties. Our method for automatic syntax acquisition, ADIOS, is an unsupervised learning method. This method is described and discussed here, including a report on the outcome of the tests using our data set. The software that has been implemented and used in this project has been implemented in C.

Artificial intelligence has made a big impact on the world in recent years, and more knowledge inthe subject seems to be of vital importance as the possibilities seems endless. Is it possible to teacha computer to drive a car in a virtual environment, by training a neural network to act intelligentlythrough the usage of supervised machine learning? With less than 2 hours of data collected whenpersonally driving the car, I show that yes, it is indeed possible. This is done by applying thetechniques of supervised machine learning combined in conjunction with a deep convolutional neuralnetwork. This were applied through software developed to interact between the network and the agentinside the virtual environment. I believe the dataset could have been cut down to about 10 percentof the size and still achieve the research goal. This shows not just the possibility of teaching aneural network a good policy in stochastic environments with supervised machine learning, but alsothat it can draw accurate (enough) conclusions to imitate human behavior when driving a car.

This master thesis is a collaboration with Jeppesen, a Boeing company to attempt applying machine learning techniques to predict “When does Operator manually solve the disruption? If he chooses to use Optimiser, then which option would he choose? And why?”. Through the course of this project, various techniques are employed to study, analyze and understand the historical labeled data of airline consisting of alerts during disruptions and tries to classify each data point into one of the categories: manual or optimizer option. This is done using various supervised machine learning classification methods.

abstract: Feature embeddings differ from raw features in the sense that the former obey certain properties like notion of similarity/dissimilarity in it's embedding space. word2vec is a preeminent example in this direction, where the similarity in the embedding space is measured in terms of the cosine similarity. Such language embedding models have seen numerous applications in both language and vision community as they capture the information in the modality (English language) efficiently. Inspired by these language models, this work focuses on learning embedding spaces for two visual computing tasks, 1. Image Hashing 2. Zero Shot Learning. The training set was used to learn embedding spaces over which similarity/dissimilarity is measured using several distance metrics like hamming / euclidean / cosine distances. While the above-mentioned language models learn generic word embeddings, in this work task specific embeddings were learnt which can be used for Image Retrieval and Classification separately. Image Hashing is the task of mapping images to binary codes such that some notion of user-defined similarity is preserved. The first part of this work focuses on designing a new framework that uses the hash-tags associated with web images to learn the binary codes. Such codes can be used in several applications like Image Retrieval and Image Classification. Further, this framework requires no labelled data, leaving it very inexpensive. Results show that the proposed approach surpasses the state-of-art approaches by a significant margin. Zero-shot classification is the task of classifying the test sample into a new class which was not seen during training. This is possible by establishing a relationship between the training and the testing classes using auxiliary information. In the second part of this thesis, a framework is designed that trains using the handcrafted attribute vectors and word vectors but doesn’t require the expensive attribute vectors during test time. More specifically, an intermediate space is learnt between the word vector space and the image feature space using the hand-crafted attribute vectors. Preliminary results on two zero-shot classification datasets show that this is a promising direction to explore. / Dissertation/Thesis / Masters Thesis Computer Engineering 2019

abstract: Endowing machines with the ability to understand digital images is a critical task for a host of high-impact applications, including pathology detection in radiographic imaging, autonomous vehicles, and assistive technology for the visually impaired. Computer vision systems rely on large corpora of annotated data in order to train task-specific visual recognition models. Despite significant advances made over the past decade, the fact remains collecting and annotating the data needed to successfully train a model is a prohibitively expensive endeavor. Moreover, these models are prone to rapid performance degradation when applied to data sampled from a different domain. Recent works in the development of deep adaptation networks seek to overcome these challenges by facilitating transfer learning between source and target domains. In parallel, the unification of dominant semi-supervised learning techniques has illustrated unprecedented potential for utilizing unlabeled data to train classification models in defiance of discouragingly meager sets of annotated data. In this thesis, a novel domain adaptation algorithm -- Domain Adaptive Fusion (DAF) -- is proposed, which encourages a domain-invariant linear relationship between the pixel-space of different domains and the prediction-space while being trained under a domain adversarial signal. The thoughtful combination of key components in unsupervised domain adaptation and semi-supervised learning enable DAF to effectively bridge the gap between source and target domains. Experiments performed on computer vision benchmark datasets for domain adaptation endorse the efficacy of this hybrid approach, outperforming all of the baseline architectures on most of the transfer tasks. / Dissertation/Thesis / Masters Thesis Computer Science 2019

There are many challenges facing society today, both socially and industrially. Whether it is to improve productivity in factories or with the intention of improving the quality of life of people in their homes, technological advances in robotics and computing have led to solutions to many problems in modern society. These areas are of great interest and are in constant development, especially in societies with a relatively ageing population. In this thesis, we address different challenges in which robotics, artificial intelligence and computer vision are used as tools to propose solutions oriented to home assistance. These tools can be organised into three main groups: “Grasping Challenges”, where we have addressed the problem of performing robot grasping in domestic environments; “Hand Interaction Challenges”, where we have addressed the detection of static and dynamic hand gestures, using approaches based on DeepLearning and GeometricLearning; and finally, “Human Behaviour Recognition”, where using a machine learning model based on hyperbolic geometry, we seek to group the actions that performed in a video sequence.

Yes / Point set registration has been actively studied in computer vision and graphics. Optimization algorithms are at the core of solving registration problems. Traditional optimization approaches are mainly based on the gradient of objective functions. The derivation of objective functions makes it challenging to find optimal solutions for complex optimization models, especially for those applications where accuracy is critical. Learning-based optimization is a novel approach to address this problem, which learns the gradient direction from datasets. However, many learning-based optimization algorithms learn gradient directions via a single feature extracted from the dataset, which will cause the updating direction to be vulnerable to perturbations around the data, thus falling into a bad stationary point. This paper proposes the General Discriminative Optimization (GDO) method that updates a gradient path automatically through the trade-off among contributions of different features on updating gradients. We illustrate the benefits of GDO with tasks of 3D point set registrations and show that GDO outperforms the state-of-the-art registration methods in terms of accuracy and robustness to perturbations.

Yes / Quality control has long been one of the most challenging fields of manufacturing. The development of advanced sensors and the easier collection of high amounts of data designate the machine learning techniques as a timely natural step forward to leverage quality decision support and manufacturing challenges. This paper introduces an original dataset provided by the automotive supplier company VALEO, coming from a production line, and hosted by the École Normale Supérieure (ENS) Data Challenge to predict defects using non-anonymised features, without access to final test results, to validate the part status (defective or not). We propose in this paper a complete workflow from data exploration to the modelling phase while addressing at each stage challenges and techniques to solve them, as a benchmark reference. The proposed workflow is validated in series of experiments that demonstrate the benefits, challenges and impact of data science adoption in manufacturing.

No description available.