Academic literature on the topic 'Transfer of Learning'

Lors de l’apprentissage d’un modèle de classification pour un nouveau domaine cible avec seulement une petite quantité d’échantillons de formation, l’application des algorithmes d’apprentissage automatiques conduit généralement à des classifieurs surdimensionnés avec de mauvaises compétences de généralisation. D’autre part, recueillir un nombre suffisant d’échantillons de formation étiquetés manuellement peut s’avérer très coûteux. Les méthodes de transfert d’apprentissage visent à résoudre ce type de problèmes en transférant des connaissances provenant d’un domaine source associé qui contient beaucoup plus de données pour faciliter la classification dans le domaine cible. Selon les différentes hypothèses sur le domaine cible et le domaine source, l’apprentissage par transfert peut être classé en trois catégories: apprentissage par transfert inductif, apprentissage par transfert transducteur (adaptation du domaine) et apprentissage par transfert non surveillé. Nous nous concentrons sur le premier qui suppose que la tâche cible et la tâche source sont différentes mais liées. Plus précisément, nous supposons que la tâche cible et la tâche source sont des tâches de classification, tandis que les catégories cible et les catégories source sont différentes mais liées. Nous proposons deux méthodes différentes pour aborder ce problème. Dans le premier travail, nous proposons une nouvelle méthode d’apprentissage par transfert discriminatif, à savoir DTL(Discriminative Transfer Learning), combinant une série d’hypothèses faites à la fois par le modèle appris avec les échantillons de cible et les modèles supplémentaires appris avec des échantillons des catégories sources. Plus précisément, nous utilisons le résidu de reconstruction creuse comme discriminant de base et améliore son pouvoir discriminatif en comparant deux résidus d’un dictionnaire positif et d’un dictionnaire négatif. Sur cette base, nous utilisons des similitudes et des dissemblances en choisissant des catégories sources positivement corrélées et négativement corrélées pour former des dictionnaires supplémentaires. Une nouvelle fonction de coût basée sur la statistique de Wilcoxon-Mann-Whitney est proposée pour choisir les dictionnaires supplémentaires avec des données non équilibrées. En outre, deux processus de Boosting parallèles sont appliqués à la fois aux distributions de données positives et négatives pour améliorer encore les performances du classificateur. Sur deux bases de données de classification d’images différentes, la DTL proposée surpasse de manière constante les autres méthodes de l’état de l’art du transfert de connaissances, tout en maintenant un temps d’exécution très efficace. Dans le deuxième travail, nous combinons le pouvoir du transport optimal (OT) et des réseaux de neurones profond (DNN) pour résoudre le problème ITL. Plus précisément, nous proposons une nouvelle méthode pour affiner conjointement un réseau de neurones avec des données source et des données cibles. En ajoutant une fonction de perte du transfert optimal (OT loss) entre les prédictions du classificateur source et cible comme une contrainte sur le classificateur source, le réseau JTLN (Joint Transfer Learning Network) proposé peut effectivement apprendre des connaissances utiles pour la classification cible à partir des données source. En outre, en utilisant différents métriques comme matrice de coût pour la fonction de perte du transfert optimal, JTLN peut intégrer différentes connaissances antérieures sur la relation entre les catégories cibles et les catégories sources. Nous avons effectué des expérimentations avec JTLN basées sur Alexnet sur les jeux de données de classification d’image et les résultats vérifient l’efficacité du JTLN proposé. A notre connaissances, ce JTLN proposé est le premier travail à aborder ITL avec des réseaux de neurones profond (DNN) tout en intégrant des connaissances antérieures sur la relation entre les catégories cible et source<br>When learning a classification model for a new target domain with only a small amount of training samples, brute force application of machine learning algorithms generally leads to over-fitted classifiers with poor generalization skills. On the other hand, collecting a sufficient number of manually labeled training samples may prove very expensive. Transfer Learning methods aim to solve this kind of problems by transferring knowledge from related source domain which has much more data to help classification in the target domain. Depending on different assumptions about target domain and source domain, transfer learning can be further categorized into three categories: Inductive Transfer Learning, Transductive Transfer Learning (Domain Adaptation) and Unsupervised Transfer Learning. We focus on the first one which assumes that the target task and source task are different but related. More specifically, we assume that both target task and source task are classification tasks, while the target categories and source categories are different but related. We propose two different methods to approach this ITL problem. In the first work we propose a new discriminative transfer learning method, namely DTL, combining a series of hypotheses made by both the model learned with target training samples, and the additional models learned with source category samples. Specifically, we use the sparse reconstruction residual as a basic discriminant, and enhance its discriminative power by comparing two residuals from a positive and a negative dictionary. On this basis, we make use of similarities and dissimilarities by choosing both positively correlated and negatively correlated source categories to form additional dictionaries. A new Wilcoxon-Mann-Whitney statistic based cost function is proposed to choose the additional dictionaries with unbalanced training data. Also, two parallel boosting processes are applied to both the positive and negative data distributions to further improve classifier performance. On two different image classification databases, the proposed DTL consistently out performs other state-of-the-art transfer learning methods, while at the same time maintaining very efficient runtime. In the second work we combine the power of Optimal Transport and Deep Neural Networks to tackle the ITL problem. Specifically, we propose a novel method to jointly fine-tune a Deep Neural Network with source data and target data. By adding an Optimal Transport loss (OT loss) between source and target classifier predictions as a constraint on the source classifier, the proposed Joint Transfer Learning Network (JTLN) can effectively learn useful knowledge for target classification from source data. Furthermore, by using different kind of metric as cost matrix for the OT loss, JTLN can incorporate different prior knowledge about the relatedness between target categories and source categories. We carried out experiments with JTLN based on Alexnet on image classification datasets and the results verify the effectiveness of the proposed JTLN in comparison with standard consecutive fine-tuning. To the best of our knowledge, the proposed JTLN is the first work to tackle ITL with Deep Neural Networks while incorporating prior knowledge on relatedness between target and source categories. This Joint Transfer Learning with OT loss is general and can also be applied to other kind of Neural Networks

The problem of developing skill repertoires autonomously in robotics and artificial intelligence is becoming ever more pressing. Currently, the issues of how to apply prior knowledge to new situations and which knowledge to apply have not been sufficiently studied. We present a transfer setting where a reinforcement learning agent faces multiple problem solving tasks drawn from an unknown generative process, where each task has similar dynamics. The task dynamics are changed by varying in the transition function between states. The tasks are presented sequentially with the latest task presented considered as the target for transfer. We describe two approaches to solving this problem. Firstly we present an algorithm for transfer of the function encoding the stateaction value, defined as value function transfer. This algorithm uses the value function of a source policy to initialise the policy of a target task. We varied the type of basis the algorithm used to approximate the value function. Empirical results in several well known domains showed that the learners benefited from the transfer in the majority of cases. Results also showed that the Radial basis performed better in general than the Fourier. However contrary to expectation the Fourier basis benefited most from the transfer. Secondly, we present an algorithm for learning an informative prior which encodes beliefs about the underlying dynamics shared across all tasks. We call this agent the Informative Prior agent (IP). The prior is learnt though experience and captures the commonalities in the transition dynamics of the domain and allows for a quantification of the agent's uncertainty about these. By using a sparse distribution of the uncertainty in the dynamics as a prior, the IP agent can successfully learn a model of 1) the set of feasible transitions rather than the set of possible transitions, and 2) the likelihood of each of the feasible transitions. Analysis focusing on the accuracy of the learned model showed that IP had a very good accuracy bound, which is expressible in terms of only the permissible error and the diffusion, a factor that describes the concentration of the prior mass around the truth, and which decreases as the number of tasks experienced grows. The empirical evaluation of IP showed that an agent which uses the informative prior outperforms several existing Bayesian reinforcement learning algorithms on tasks with shared structure in a domain where multiple related tasks were presented only once to the learners. IP is a step towards the autonomous acquisition of behaviours in artificial intelligence. IP also provides a contribution towards the analysis of exploration and exploitation in the transfer paradigm.

In this experiment I investigated the relationship between set-switching and transfer learning, both of which presumably invoke executive functioning (EF), which may in turn be correlated with intelligence. Set-switching was measured by a computerized version of the Wisconsin Card Sort Task. Another computer task was written to measure learning-transfer ability. The data indicate little correlation between the ability to transfer learning and the capacity for set-switching. That is, these abilities may draw from independent cognitive mechanisms. The major difference may be requirement to utilize previous learning in a new way in the learning-transfer task.

Transfer Learning is an emerging framework for learning from data that aims at intelligently transferring information between tasks. This is achieved by developing algorithms that can perform multiple tasks simultaneously, as well as translating previously acquired knowledge to novel learning problems. In this thesis, we investigate the application of Gaussian Processes to various forms of transfer learning with a focus on classification problems. This process initiates with a thorough introduction to the framework of Transfer learning, providing a clear taxonomy of the areas of research. Following that, we continue by reviewing the recent advances on Multi-task learning for regression with Gaussian processes, and compare the performance of some of these methods on a real data set. This review gives insights about the strengths and weaknesses of each method, which acts as a point of reference to apply these methods to other forms of transfer learning. The main contributions of this thesis are reported in the three following chapters. The third chapter investigates the application of Multi-task Gaussian processes to classification problems. We extend a previously proposed model to the classification scenario, providing three inference methods due to the non-Gaussian likelihood the classification paradigm imposes. The forth chapter extends the multi-task scenario to the semi-supervised case. Using labeled and unlabeled data, we construct a novel covariance function that is able to capture the geometry of the distribution of each task. This setup allows unlabeled data to be utilised to infer the level of correlation between the tasks. Moreover, we also discuss the potential use of this model to situations where no labeled data are available for certain tasks. The fifth chapter investigates a novel form of transfer learning called meta-generalising. The question at hand is if, after training on a sufficient number of tasks, it is possible to make predictions on a novel task. In this situation, the predictor is embedded in an environment of multiple tasks but has no information about the origins of the test task. This elevates the concept of generalising from the level of data to the level of tasks. We employ a model based on a hierarchy of Gaussian processes, in a mixtures of expert sense, to make predictions based on the relation between the distributions of the novel and the training tasks. Each chapter is accompanied with a thorough experimental part giving insights about the potentials and the limits of the proposed methods.

Le transfert d‘apprentissage regroupe les méthodes permettant de transférer l’apprentissage réalisé sur des données (appelées Source) à des données nouvelles, différentes, mais liées aux données Source. Ces travaux sont une contribution au transfert d’apprentissage homogène (les domaines de représentation des Source et Cible sont identiques) et transductif (la tâche à effectuer sur les données Cible est identique à celle sur les données Source), lorsque nous ne disposons pas d’étiquettes des données Cible. Dans ces travaux, nous relâchons la contrainte d’égalité des lois des étiquettes conditionnellement aux observations, souvent considérée dans la littérature. Notre approche permet de traiter des cas de plus en plus généraux. Elle repose sur la recherche de transformations permettant de rendre similaires les données Source et Cible. Dans un premier temps, nous recherchons cette transformation par Maximum de Vraisemblance. Ensuite, nous adaptons les Machines à Vecteur de Support en intégrant une contrainte additionnelle sur la similitude des données Source et Cible. Cette similitude est mesurée par la Maximum Mean Discrepancy. Enfin, nous proposons l’utilisation de l’Analyse en Composantes Principales à noyau pour rechercher un sous espace, obtenu à partir d’une transformation non linéaire des données Source et Cible, dans lequel les lois des observations sont les plus semblables possibles. Les résultats expérimentaux montrent l’efficacité de nos approches<br>Transfer Learning aims to take advantage of source data to help the learning task of related but different target data. This thesis contributes to homogeneous transductive transfer learning where no labeled target data is available. In this thesis, we relax the constraint on conditional probability of labels required by covariate shift to be more and more general, based on which the alignment of marginal probabilities of source and target observations renders source and target similar. Thus, firstly, a maximum likelihood based approach is proposed. Secondly, SVM is adapted to transfer learning with an extra MMD-like constraint where Maximum Mean Discrepancy (MMD) measures this similarity. Thirdly, KPCA is used to align data in a RKHS on minimizing MMD. We further develop the KPCA based approach so that a linear transformation in the input space is enough for a good and robust alignment in the RKHS. Experimentally, our proposed approaches are very promising

Fault detection and diagnostics are crucial tasks in condition-based maintenance. Industries nowadays are in need of fault identification in their machines as early as possible to save money and take precautionary measures in case of fault occurrence. Also, it is beneficial for the smooth interference in the manufacturing process in which it avoids sudden malfunctioning. Having sufficient training data for industrial machines is also a major challenge which is a prerequisite for deep neural networks to train an accurate prediction model. Transfer learning in such cases is beneficial as it can be helpful in adapting different operating conditions and characteristics which is the casein real-life applications. Our work is focused on a pneumatic system which utilizes compressed air to perform operations and is used in different types of machines in the industrial field. Our novel contribution is to build upon a Domain Adversarial Neural Network (DANN) with a unique approach by incorporating ensembling techniques for diagnostics of air leakage problem in the pneumatic system under transfer learning settings. Our approach of using ensemble methods for feature extraction shows up to 5 % improvement in the performance. We have also performed a comparative analysis of our work with conventional machine and deep learning methods which depicts the importance of transfer learning and we have also demonstrated the generalization ability of our model. Lastly, we also mentioned a problem specific contribution by suggesting a feature engineering approach, such that it could be implemented on almost every pneumatic system and could potentially impact the prediction result positively. We demonstrate that our designed model with domain adaptation ability will be quite useful and beneficial for the industry by saving their time and money and providing promising results for this air leakage problem in the pneumatic system.

Successful learning of behaviors in Reinforcement Learning (RL) are often learned tabula rasa, requiring many observations and interactions in the environment. Performing this outside of a simulator, in the real world, often becomes infeasible due to the large amount of interactions needed. This has motivated the use of Transfer Learning for Reinforcement Learning, where learning is accelerated by using experiences from previous learning in related tasks. In this thesis, I explore how we can transfer from a simple single-object pushing policy, to a wide array of non-prehensile rearrangement problems. I then explain how we can model task differences using a low-dimensional latent variable representation to make adaption to novel tasks efficient. Lastly, the dependence of accurate function approximation is sometimes problematic, especially in RL, where statistics of target variables are not known a priori. I present observations, along with explanations, that small target variances along with momentum optimization of ReLU-activated neural network parameters leads to dying ReLU.<br>Framgångsrik inlärning av beteenden inom ramen för Reinforcement Learning (RL) sker ofta tabula rasa och kräver stora mängder observationer och interaktioner. Att använda RL-algoritmer utanför simulering, i den riktiga världen, är därför ofta inte praktiskt utförbart. Detta har motiverat studier i Transfer Learning för RL, där inlärningen accelereras av erfarenheter från tidigare inlärning av liknande uppgifter. I denna licentiatuppsats utforskar jag hur vi kan vi kan åstadkomma transfer från en enklare manipulationspolicy, till en större samling omarrangeringsproblem. Jag fortsätter sedan med att beskriva hur vi kan modellera hur olika inlärningsproblem skiljer sig åt med hjälp av en lågdimensionell parametrisering, och på så vis effektivisera inlärningen av nya problem. Beroendet av bra funktionsapproximation är ibland problematiskt, särskilt inom RL där statistik om målvariabler inte är kända i förväg. Jag presenterar därför slutligen observationer, och förklaringar, att små varianser för målvariabler tillsammans med momentum-optimering leder till dying ReLU.<br><p>QC 20200819</p>

Motivating employees to learn and transfer their learning to their jobs is an important activity to ensure that employees - and the organisation - continuously adapt, evolve and survive in this highly turbulent environment. The literature shows that both intrinsic and extrinsic motivators influence learning and learning transfer, and the extent of influence could be different for different people. This research sets out to explore and identify the intrinsic and extrinsic motivational factors that drive learning and learning transfer. A qualitative study in the form of focus groups was conducted. Three focus groups were conducted in which a total of 25 middle managers from two different multinational companies participated. Content and frequency analysis were used to identify the key themes from the focus group discussion. The outcome of the study resulted in the identification of the key intrinsic and extrinsic motivation factors that drive learning and learning transfer. The findings have been used to develop a Motivation-to-learn-and-transfer catalyst framework indicating that individual intrinsic motivators are at the core of driving motivation to learn and transfer learning. It also indicates which training design and work environment factors to focus on in support of intrinsic motivation to learn and transfer learning in the workplace for middle managers. It is hoped that the outcome of this research will contribute to catalysing learning and learning transfer for middle managers to achieve higher organisational effectiveness.<br>Mini Dissertation (MBA)--University of Pretoria, 2015.<br>pa2016<br>Gordon Institute of Business Science (GIBS)<br>MBA<br>Unrestricted