Global ETD Search

Search theses and dissertations gathered from participating repositories worldwide. Every result links back to the library that holds it. No account is needed.

Results

Showing 1 to 20 of 20 for “"Algorithms, Learning"”.

  1. ALGORITHMS, LEARNING, AND OPTIMIZATION

    … some algorithmic aspects of online machine learning and optimization. In Chapter 1 we design algorithms with state-of-the-art regret guarantees for the problem dynamic pricing. In Chapter 2 we move on to an asynchronous online learning setting in which only some of the agents in the network …

    milano Repository record for ALGORITHMS, LEARNING, AND OPTIMIZATION (opens in a new tab)

  2. Design and evaluation of a hybrid multi-task learning model for optimizing deep reinforcement learning agents

    … within the artificial intelligence domain, deep learning has emerged as a promising representation learning technique. This in turn has given rise to the evolution of deep reinforcement learning that combines deep learning with reinforcement learning methods. Subsequently, performance …

    uoit Repository record for Design and evaluation of a hybrid multi-task learning model for optimizing deep reinforcement learning agents (opens in a new tab)

  3. Study of static and dynamic damage identification in multifield materials with artificial intelligence, BEM and X-FEM

    … networks) and unsupervised (self-organizing algorithms) learning techniques, providing excellent identification results despite the presence of high levels of external interference in the measured response. Experimental damage assessment was also investigated in this Thesis, and a methodology …

    sevilla Repository record for Study of static and dynamic damage identification in multifield materials with artificial intelligence, BEM and X-FEM (opens in a new tab)

  4. Evaluation of sample efficiency in offline reinforcement learning

    Reinforcement learning (RL) has shown great promise with algorithms learning in environments with large state and action spaces purely from scalar reward signals. A crucial challenge for current deep RL algorithms is that they require a tremendous amount of environment interactions for learning. …

    ets-quebec Download PDF for Evaluation of sample efficiency in offline reinforcement learning (opens in a new tab)

  5. Quantitative convergence analysis of dynamical processes in machine learning

    … convergence of selected important machine learning processes, from a dynamical perspective, in order to understand and guide machine learning practices. Machine learning is becoming increasingly popular in various fields. Typical machine learning models consist of optimization and …

    gatech Repository record for Quantitative convergence analysis of dynamical processes in machine learning (opens in a new tab)

  6. Fairness-aware Spatio-temporal Prediction for Cities

    … impact on underrepresented minorities. Machine learning based spatio-temporal prediction models have been widely adopted in urban settings, but few of them have built fairness into their design. This dissertation is a pioneering work to explore a suite of fairness-aware spatio-temporal …

    washington Repository record for Fairness-aware Spatio-temporal Prediction for Cities (opens in a new tab)

  7. Learning in the Presence of Skew and Missing Labels Through Online Ensembles and Meta-reinforcement Learning

    … in radiotherapy and social media analysis. Algorithms learning from such streams need to be able to construct near real-time models that continuously adapt to potential changes in patterns, in order to retain high performance throughout the stream. It follows that there are numerous …

    ottawa-retro Repository record for Learning in the Presence of Skew and Missing Labels Through Online Ensembles and Meta-reinforcement Learning (opens in a new tab)

  8. Multi-output structured learning

    Real-world applications of Machine Learning (ML) require modeling and reasoning about complex, heterogeneous and high-dimensional data. Probabilistic Inference and Structured-Output Prediction (SOP) are frameworks within ML, which enable systems to learn and reason about complex output spaces by …

    uiuc Repository record for Multi-output structured learning (opens in a new tab)

  9. Deep neural networks for pose validation, affinity prediction, and input attribution

    … process. To this end, virtual screening algorithms which aim to screen a large number of potential binders in silico have been developed. These use scoring functions to assess the probability that a computationally predicted binding pose is correct, and to predict the binding affinity. …

    oxford Repository record for Deep neural networks for pose validation, affinity prediction, and input attribution (opens in a new tab)

  10. Collective Machine Learning: Team Learning and Classification in Multi-Agent Systems

    … sharing knowledge. The concept of collaborative learning in multi-agent and multi-robot systems is largely under studied, and represents an area where further research is needed to gain a deeper understanding of team learning. This work presents experimental results which illustrate the …

    ku Repository record for Collective Machine Learning: Team Learning and Classification in Multi-Agent Systems (opens in a new tab)

  11. Grafický výukový systém

    Účelem této diplomové práce je přiblížit problematiku návrhu výukového software pro výuku algoritmizace. Práce přistupuje k problému, jak z teoretického hlediska vzdělávání se a učení se novým věcem, tak z praktického pohledu důležitého pro osvojení si procesu algoritmizace. Zabývá se také stavem …

    brno-tech Repository record for Grafický výukový systém (opens in a new tab)

  12. Κατασκευή μοντέλου προσομοίωσης του οφθαλμοκινητικού νευρικού ολοκληρωτή σακκαδικών κινήσεων των ματιών

    Ένας από τους κύριους στόχους της επιστήμης των Νευροεπιστημών είναι να διερευνήσει και ακολούθως να προβάλλει τη νευρωνική βάση μιας Συμπεριφοράς όπως είναι οι σακκαδικές κινήσεις των ματιών. Οι κινήσεις αυτές έχουν σαν στόχο τη μεταφορά της εικόνας του ενδιαφέροντος στο κέντρο του …

    greece Repository record for Κατασκευή μοντέλου προσομοίωσης του οφθαλμοκινητικού νευρικού ολοκληρωτή σακκαδικών κινήσεων των ματιών (opens in a new tab)

  13. Evolutionary Strategies for Data Mining

    Learning classifier systems (LCS) have been successful in generating rules for solving classification problems in data mining. The rules are of the form IF condition THEN action. The condition encodes the features of the input space and the action encodes the class label. What is lacking in those …

    clemson Repository record for Evolutionary Strategies for Data Mining (opens in a new tab)

  14. Duality Between Deep Learning And Algorithm Design

    This thesis introduces 'Duality Between Deep Learning And Algorithm Design'. Deep learning is a data-driven method, whereas conventional algorithm design is a knowledge-driven method. Based on their connections and complementary features, this thesis develops new methods to combine the merits of …

    gatech Repository record for Duality Between Deep Learning And Algorithm Design (opens in a new tab)

  15. Matheuristic and learning methods in routing optimization

    This thesis investigates the design and development of efficient optimization methods for solving routing problems. Routing problems rise in various settings and can often be found to coexist with other difficult optimization problems. Facility location is one of those that often seem to emerge in …

    greece Repository record for Matheuristic and learning methods in routing optimization (opens in a new tab)

  16. Evolutionary Rule Learning for High Dimensional Classification Problems: Investigations and Remedies

    … data classification using evolutionary rule learning algorithms. High-dimensional data analysis problems are now commonplace due to the rapid advancement in technology which has resulted in the collection of large data sets in various domains. A systematic analysis of LCS, widely accepted as …

    unsw Repository record for Evolutionary Rule Learning for High Dimensional Classification Problems: Investigations and Remedies (opens in a new tab)

  17. Towards provably efficient algorithms for learning neural networks

    … natural language. Developing provably efficient algorithms for learning commonly used neural network architectures continues to be a core challenge in understanding deep learning. In particular, even the problem of learning very basic architectures remains open. The underlying difficulty arises …

    texas Repository record for Towards provably efficient algorithms for learning neural networks (opens in a new tab)