Recent research in feature learning has been extended to sequence data, where each instance consists of a sequence of heterogeneous items with a variable length. However, in many real-world applications, the data exists in the form of attributed sequences, which is composed of a set of fixed-size attributes and variable-length sequences with dependencies between them. In the attributed sequence context, feature learning remains challenging due to the dependencies between sequences and their associated attributes. In this dissertation, we focus on analyzing and building deep learning models for four new problems on attributed sequences. First, we propose a framework, called NAS, to produce feature representations of attributed sequences in an unsupervised fashion. The NAS is capable of producing task independent embeddings that can be used in various mining tasks of attributed sequences. Second, we study the problem of deep metric learning on attributed sequences. The goal is to learn a distance metric based on pairwise user feedback. In this task, we propose a framework, called MLAS, to learn a distance metric that measures the similarity and dissimilarity between attributed sequence feedback pairs. Third, we study the problem of one-shot learning on attributed sequences. This problem is important for a variety of real-world applications ranging from fraud prevention to network intrusion detection. We design a deep learning framework OLAS to tackle this problem. Once the OLAS is trained, we can then use it to make predictions for not only the new data but also for entire previously unseen new classes. Lastly, we investigate the problem of attributed sequence classification with attention model. This is challenging that now we need to assess the importance of each item in each sequence considering both the sequence itself and the associated attributes. In this work, we propose a framework, called AMAS, to classify attributed sequences using the information from the sequences, metadata, and the computed attention. Our extensive experiments on real-world datasets demonstrate that the proposed solutions significantly improve the performance of each task over the state-of-the-art methods on attributed sequences.

Deep learning and convolutional neural networks have become the dominant tool for computer vision. These techniques excel at learning complicated representations from data using supervised learning. In particular, image recognition models now out-perform human baselines under constrained settings. However, the science of computer vision aims to build machines which can see. This requires models which can extract richer information than recognition, from images and video. In general, applying these deep learning models from recognition to other problems in computer vision is significantly more challenging. This thesis presents end-to-end deep learning architectures for a number of core computer vision problems; scene understanding, camera pose estimation, stereo vision and video semantic segmentation. Our models outperform traditional approaches and advance state-of-the-art on a number of challenging computer vision benchmarks. However, these end-to-end models are often not interpretable and require enormous quantities of training data. To address this, we make two observations: (i) we do not need to learn everything from scratch, we know a lot about the physical world, and (ii) we cannot know everything from data, our models should be aware of what they do not know. This thesis explores these ideas using concepts from geometry and uncertainty. Specifically, we show how to improve end-to-end deep learning models by leveraging the underlying geometry of the problem. We explicitly model concepts such as epipolar geometry to learn with unsupervised learning, which improves performance. Secondly, we introduce ideas from probabilistic modelling and Bayesian deep learning to understand uncertainty in computer vision models. We show how to quantify different types of uncertainty, improving safety for real world applications.

Learning discriminative feature representations has attracted a great deal of attention since it is a critical step to facilitate the subsequent classification, retrieval and recommendation tasks. In this dissertation, besides incorporating prior knowledge about image labels into the image classification as most prevalent feature learning methods currently do, we also explore some other general-purpose priors and verify their effectiveness in the discriminant feature learning. As a more powerful representation can be learned by implementing such general priors, our approaches achieve state-of-the-art results on challenging benchmarks. We elaborate on these general-purpose priors and highlight where we have made novel contributions. We apply sparsity and hierarchical priors to the explanatory factors that describe the data, in order to better discover the data structure. More specifically, in the first approach we propose that we only incorporate sparse priors into the feature learning. To this end, we present a support discrimination dictionary learning method, which finds a dictionary under which the feature representation of images from the same class have a common sparse structure while the size of the overlapped signal support of different classes is minimised. Then we incorporate sparse priors and hierarchical priors into a unified framework, that is capable of controlling the sparsity of the neuron activation in deep neural networks. Our proposed approach automatically selects the most useful low-level features and effectively combines them into more powerful and discriminative features for our specific image classification problem. We also explore priors on the relationships between multiple factors. When multiple independent factors exist in the image generation process and only some of them are of interest to us, we propose a novel multi-task adversarial network to learn a disentangled feature which is optimized with respect to the factor of interest to us, while being distraction factors agnostic. When common factors exist in multiple tasks, leveraging common factors cannot only make the learned feature representation more robust, but also enable the model to generalise from very few labelled samples. More specifically, we address the domain adaptation problem and propose the re-weighted adversarial adaptation network to reduce the feature distribution divergence and adapt the classifier from source to target domains.

Effective classification with imbalanced data is an important area of research, as high class imbalance is naturally inherent in many real-world applications, e.g. anomaly detection. Modeling such skewed data distributions is often very difficult, and non-standard methods are sometimes required to combat these negative effects. These challenges have been studied thoroughly using traditional machine learning algorithms, but very little empirical work exists in the area of deep learning with class imbalanced big data. Following an in-depth survey of deep learning methods for addressing class imbalance, we evaluate various methods for addressing imbalance on the task of detecting Medicare fraud, a big data problem characterized by extreme class imbalance. Case studies herein demonstrate the impact of class imbalance on neural networks, evaluate the efficacy of data-level and algorithm-level methods, and achieve state-of-the-art results on the given Medicare data set. Results indicate that combining under-sampling and over-sampling maximizes both performance and efficiency. / Includes bibliography. / Thesis (M.S.)--Florida Atlantic University, 2019. / FAU Electronic Theses and Dissertations Collection

This thesis shows how children’s learning is influenced and modified by the teaching environment. The metacognitive, self-regulatory learning behaviours of sixteen kindergarten students were examined in order to determine how students perceive learning, either by adopting deep approaches, where the focus is on understanding and meaning, or surface approaches, where the meeting of institutional demands frequently subjugate the former goals. The data have been analysed within a qualitative paradigm from a phenomenographic perspective. The study addresses three issues: the nature and frequency of the strategic learning behaviours displayed by the students; the contribution strategic behaviours make to the adoption of deep or surface learning approaches; and how metacognitive teaching environments influence higher-order thinking. Findings reveal that where teachers had metcognitive training, the frequency of strategy use increased irrespective of student performance. High achieving students used more strategic behaviours, used them with greater efficiency, and tended to display more of the characteristics of deep approach learners. This study suggests that many of the differential outcomes evident amongst students may be substantially reduced through early and consistent training within a teaching environment conductive to the development of metacognitive, self-regulatory behaviours and deep learning approaches / Doctor of Philosophy (PhD)

Deep generative neural networks such as the Deep Belief Network and Deep Boltzmann Machines have been used successfully to model high dimensional visual data. However, they are not robust to common variations such as occlusion and random noise. In this thesis, we explore two strategies for improving the robustness of DBNs. First, we show that a DBN with sparse connections in the first layer is more robust to variations that are not in the training set. Second, we develop a probabilistic denoising algorithm to determine a subset of the hidden layer nodes to unclamp. We show that this can be applied to any feedforward network classifier with localized first layer connections. By utilizing the already available generative model for denoising prior to recognition, we show significantly better performance over the standard DBN implementations for various sources of noise on the standard and Variations MNIST databases.

Deep generative neural networks such as the Deep Belief Network and Deep Boltzmann Machines have been used successfully to model high dimensional visual data. However, they are not robust to common variations such as occlusion and random noise. In this thesis, we explore two strategies for improving the robustness of DBNs. First, we show that a DBN with sparse connections in the first layer is more robust to variations that are not in the training set. Second, we develop a probabilistic denoising algorithm to determine a subset of the hidden layer nodes to unclamp. We show that this can be applied to any feedforward network classifier with localized first layer connections. By utilizing the already available generative model for denoising prior to recognition, we show significantly better performance over the standard DBN implementations for various sources of noise on the standard and Variations MNIST databases.

This qualitative research study seeks to answer the question: Which instructional design approaches for blended learning encourage deep learning? This grounded theory research captures the lived experiences of instructional designers and faculty members in converting courses at the post-secondary level from traditional, face-to-face delivery to blended delivery using educational technology. Study results provide insight into the complexities involved in the design and development of blended delivery courses and shed light on the complications that can arise with course conversion. The study also opens a window into design approaches to foster deep learning, clarifying the importance of targeting high levels of learning in the course syllabus / outline, and then aligning every part of the course to the specific learning outcomes identified. Study results culminate in a set of recommended instructional design approaches that foster deep learning in a blended learning environment. / 2013-08

Face recognition, although being a popular area of research for over a decade has still many open research challenges. Some of these challenges include the recognition of poorly illuminated faces, recognition under pose variations and also the challenge of capturing sufficient training data to enable recognition under pose/viewpoint changes. With the appearance of cheap and effective multimodal image capture hardware, such as the Microsoft Kinect device, new possibilities of research have been uncovered. One opportunity is to explore the potential use of the depth maps generated by the Kinect as an additional data source to recognize human faces under low levels of scene illumination, and to generate new images through creating a 3D model using the depth maps and visible-spectrum/RGB images that can then be used to enhance face recognition accuracy by improving the training phase of a classification task. With the goal of enhancing face recognition, this research first investigated how depth maps, since not affected by illumination, can improve face recognition, if algorithms traditionally used in face recognition were used. To this effect a number of popular benchmark face recognition algorithms are tested. It is proved that algorithms based on LBP and Eigenfaces are able to provide high level of accuracy in face recognition due to the significantly high resolution of the depth map images generated by the latest version of the Kinect device. To complement this work a novel algorithm named the Dense Feature Detector is presented and is proven to be effective in face recognition using depth map images, in particular under wellilluminated conditions. Another technique that was presented for the goal of enhancing face recognition is to be able to reconstruct face images in different angles, through the use of the data of one frontal RGB image and the corresponding depth map captured by the Kinect, using faster and effective 3D object reconstruction technique. Using the Overfeat network based on Convolutional Neural Networks for feature extraction and a SVM for classification it is shown that a technically unlimited number of multiple views can be created from the proposed 3D model that consists features of the face if captured real at similar angles. Thus these images can be used as real training images, thus removing the need to capture many examples of a facial image from different viewpoints for the training of the image classifier. Thus the proposed 3D model will save significant amount of time and effort in capturing sufficient training data that is essential in recognition of the human face under variations of pose/viewpoint. The thesis argues that the same approach can also be used as a novel approach to face recognition, which promises significantly high levels of face recognition accuracy base on depth images. Finally following the recent trends in replacing traditional face recognition algorithms with the effective use of deep learning networks, the thesis investigates the use of four popular networks, VGG-16, VGG-19, VGG-S and GoogLeNet in depth maps based face recognition and proposes the effective use of Transfer Learning to enhance the performance of such Deep Learning networks.

Deep neural networks (DNNs) and deep learning approaches yield state-of-the-art performance in a range of machine learning tasks, including automatic speech recognition. The multi-layer transformations and activation functions in DNNs, or related network variations, allow complex and difficult data to be well modelled. However, the highly distributed representations associated with these models make it hard to interpret the parameters. The whole neural network is commonly treated a ``black box''. The behaviours of activation functions and the meanings of network parameters are rarely controlled in the standard DNN training. Though a sensible performance can be achieved, the lack of interpretations to network structures and parameters causes better regularisation and adaptation on DNN models challenging. In regularisation, parameters have to be regularised universally and indiscriminately. For instance, the widely used L2 regularisation encourages all parameters to be zeros. In adaptation, it requires to re-estimate a large number of independent parameters. Adaptation schemes in this framework cannot be effectively performed when there are limited adaptation data. This thesis investigates structured deep neural networks. Special structures are explicitly designed, and they are imposed with desired interpretation to improve DNN regularisation and adaptation. For regularisation, parameters can be separately regularised based on their functions. For adaptation, parameters can be adapted in groups or partially adapted according to their roles in the network topology. Three forms of structured DNNs are proposed in this thesis. The contributions of these models are presented as follows. The first contribution of this thesis is the multi-basis adaptive neural network. This form of structured DNN introduces a set of parallel sub-networks with restricted connections. The design of restricted connectivity allows different aspects of data to be explicitly learned. Sub-network outputs are then combined, and this combination module is used as the speaker-dependent structure that can be robustly estimated for adaptation. The second contribution of this thesis is the stimulated deep neural network. This form of structured DNN relates and smooths activation functions in regions of the network. It aids the visualisation and interpretation of DNN models but also has the potential to reduce over-fitting. Novel adaptation schemes can be performed on it, taking advantages of the smooth property that the stimulated DNN offer. The third contribution of this thesis is the deep activation mixture model. Also, this form of structured DNN encourages the outputs of activation functions to achieve a smooth surface. The output of one hidden layer is explicitly modelled as the sum of a mixture model and a residual model. The mixture model forms an activation contour, and the residual model depicts fluctuations around this contour. The smoothness yielded by a mixture model helps to regularise the overall model and allows novel adaptation schemes.