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 35 for “"Automatic learning"”.
-
Automatic learning of British Sign Language from signed TV broadcasts
… we will present several contributions towards automatic recognition of BSL signs from continuous signing video sequences. Specifically, we will address three main points: (i) automatic detection and tracking of the hands using a generative model of the image; (ii) automatic learning of signs …
-
Automatic Learning of Augmentation Strategies Based on Deep Learning Generative Models
… of training data can hamper supervised machine learning methods that generally need large amounts of data to avoid overfitting. Data augmentation has a long history of using machine learning algorithms and is a straightforward method to overcome overfitting and improve model generalisation. …
-
Computational Models for the Automatic Learning and Recognition of Irish Sign Language
This thesis presents a framework for the automatic recognition of Sign Language sentences. In previous sign language recognition works, the issues of; user independent recognition, movement epenthesis modeling and automatic or weakly supervised training have not been fully addressed in a single …
-
Towards intelligent missile guidance by applying the multi-layer perceptron
… possess capabilities associated with autonomous learning and decision-making. These traits are usually associated with the notion of ‘intelligence’ as it is widely understood. This thesis is oriented towards this direction. It is scoped to help advance some of the knowledge associated with one …
-
Contributions to decision tree induction: bias/variance tradeoff and time series classification
… data are nowadays available in a lot of domains. Automatic learning aims at developing algorithms able to produce synthetic high-level information, or models, from this data. Learning algorithms are generally evaluated according to three different criteria: interpretability (how well the model …
-
Fable: Finite automata based learning engine
… of building a system that is capable of automatically learning how to increase performance at a task that is presented to it by means of modeling the problem with a finite automation and the learning engine of FABLE. Current work in the field of automatic learning of FA's (Finite …
-
Fable: Finite automata based learning engine
… of building a system that is capable of automatically learning how to increase performance at a task that is presented to it by means of modeling the problem with a finite automation and the learning engine of FABLE. Current work in the field of automatic learning of FA's (Finite …
-
Nuotolinių studijų stilių modeliai Šiaulių universiteto virtualioje studijų aplinkoje /
… studying of visual means. Knowledge of students learning styles helps to the teacher to provide the proper subject matter using a variety of teaching methods and tools. The VARK model was selected after analysis of the study's models. Designed conceptual data model, which prepare VARK …
-
Advanced control of active magnetic bearings with learning control schemes
… active magnetic bearings. Time-domain iterative learning control (ILC) scheme and automatic learning control (ALC) scheme are proposed to compensate the unbalance force. ALC is based on time-domain ILC and gain-scheduled control. The controller can obtain the optimized control current for …
-
Auditing the Reasoning Processes of Medical-Image AI
… Since the modern wave of medical AI relies on automatic learning of statistical patterns from large datasets---via 'machine--learning' techniques such as neural networks---they are prone to learning unexpected and potentially undesirable patterns, which may lead to pathological behavior in …
-
Energy-efficient information inference in wireless sensor networks based on graphical modeling
… Our MRF model is first constructed through automatic learning from historical sensed data, by using Iterative Proportional Fitting (IPF). When the MRF model is constructed, Loopy Belief Propagation (LBP) is then employed to perform information inference to estimate the missing data given …
-
Domain Adaptation for Autonomous Driving
… The adversarial methods can be considered as an automatic learning approach for the metric function. Instead of depending on the quality of metric function, this thesis outlines a generalized framework for domain randomization which first introduces moderate perturbation as randomness and then …
-
A hybrid artificial neural networks and knowledge-based expert systems approach to flexible manufacturing system scheduling
… is developed displaying the capabilities of automatic learning and self-improvement, providing the necessary adaptive scheme to respond to the dynamic nature of flexible manufacturing systems. This proposed framework uses a hybrid architecture that integrates artificial neural networks and …
-
MADM Framework for Strategic Resource Planning of Electric Utilities
… this study are summarized as follows. First, an automatic learning method is introduced for decision data expansion aiming at reducing the amount of computations involved in the creation of decision database. Test results have shown that the proposed method is feasible, easy to implement, and …
-
Reinforcement learning in high-diameter, continuous environments
… of a continuous environment. Reinforcement learning (RL) has shown promise as a method for automatic learning of robot behavior, but current methods work best on lowdiameter, low-dimensional tasks. Because of this problem, the success of RL on real-world tasks still depends on human analysis …
-
Adaptive forgetting with uncontrolled and controlled removal processes
… in both unintentional (“bottom-up” implicit learning) and controlled processes (“top-down” cognitive control). To identify the neural mechanisms of removal and link these to specific behavioral outcomes, my approach relies on using functional MRI (fMRI) with multivariate pattern analyses …
-
Active visual category learning
… annotating them in specific ways, and then learning models to explain the annotated examples. However, this is a rather limited way to transfer human knowledge to visual recognition systems, particularly considering the immense number of visual concepts that are to be learned. I propose new …
-
Learning and discovery in incremental knowledge acquisition
… approaches, case-based approaches and machine-learning approaches. One particular technique is Ripple Down Rules (RDR) which may be classified as an incremental case-based approach. Knowledge needs to be acquired from experts in the context of individual cases viewed by them. In the RDR …
-
Real-time applications of synchrophasor-based wide-area measurement systems
… we develop a tool for real-time TSA based on automatic learning approaches. We use Classification and Regression Tree (CART) as the classification tool and Multivariate Adaptive Regression Splines (MARS) as the regression tool. To train and validate these tools in a practical setting, we …
-
Efficient deep learning of 3D structural brain MRIs for manifold learning and lesion segmentation with application to multiple sclerosis
Deep learning methods have shown great success in many research areas such as object recognition, speech recognition, and natural language understanding, due to their ability to automatically learn a hierarchical set of features that is tuned to a given domain and robust to large variability. This …
Page 1 of 2