High Dynamic Range (HDR) image acquisition from a single image capture, also known as snapshot HDR imaging, is challenging because the bit depths of camera sensors are far from sufficient to cover the full dynamic range of the scene. Existing HDR techniques focus either on algorithmic reconstruction or hardware modification to extend the dynamic range. In this thesis, we propose a joint design for snapshot HDR imaging by devising a spatially varying modulation mask in the hardware combined with a deep learning algorithm to reconstruct the HDR image. In this approach, we achieve a reconfigurable HDR camera design that does not require custom sensors, and instead can be reconfigured between HDR and conventional mode with very simple calibration steps. We demonstrate that the proposed hardware-software solution offers a flexible, yet robust, way to modulate per-pixel exposures, and the network requires little knowledge of the hardware to faithfully reconstruct the HDR image. Comparative analysis demonstrated that our method outperforms the state-of-the-art in terms of visual perception quality. We leverage transfer learning to overcome the lack of sufficiently large HDR datasets available. We show how transferring from a different large scale task (image classification on ImageNet) leads to considerable improvements in HDR reconstruction

As deep learning continues to push the boundaries with applications previously thought impossible, it has become more important than ever to reduce the associated resource costs. Data is not always abundant, labelling costs valuable human time, and deep models are demanding of computer hardware. In this dissertation, I will examine questions of minimalism in deep learning. I will show that deep learning can learn with fewer measurements, fewer weights, and less information. With minimalism, deep learning can become even more ubiquitous, succeeding in more applications and on more everyday devices.

Prediction of initial velocity of artillery system is a feature that is hard to determine with statistical and analytical models. Machine learning is therefore to be tested, in order to achieve a higher accuracy than the current method (baseline). An ensemble approach will be explored in this paper, centered around feed forward deep neural network and random forest regression. Furthermore, collinearity of features and their importance will be investigated. The impact of the measured error on the range of the projectile will also be derived by finding a numerical solution with Newton Raphsons method. For the five systemstest data was used on, the mean absolute errors were 26, 9.33, 8.72 and 9.06 for deep neural networks,random forest regression, ensemble learning and conventional method, respectively. For future works,more models should be tested with ensemble learning, as well as investigation on the feature space for the input data.

Indiana University-Purdue University Indianapolis (IUPUI) / Textual emotion classification is a task in affective AI that branches from sentiment analysis and focuses on identifying emotions expressed in a given text excerpt. It has a wide variety of applications that improve human-computer interactions, particularly to empower computers to understand subjective human language better. Significant research has been done on this task, but very little of that research leverages one of the most emotion-bearing symbols we have used in modern communication: Emojis. In this thesis, we propose several transformer-based models for emotion classification that processes emojis as input tokens and leverages pretrained models and uses them , a model that processes Emojis as textual inputs and leverages DeepMoji to generate affective feature vectors used as reference when aggregating different modalities of text encoding. To evaluate ReferEmo, we experimented on the SemEval 2018 and GoEmotions datasets, two benchmark datasets for emotion classification, and achieved competitive performance compared to state-of-the-art models tested on these datasets. Notably, our model performs better on the underrepresented classes of each dataset.

No description available.

No description available.

Trimap-free natural image matting problem is an important computer vision task in which we extract foreground objects from given images without extra trimap input. Compared with trimap-based matting algorithms, trimap-free algorithms are easier to make false detection when the foreground object is not well defined. To solve the problem, we design a novel structure (SegMatting) to handle foreground segmentation and alpha matte prediction simultaneously, which is able to produce high-quality mattes based on RGB inputs alone. This entangled structure enables information exchange between the binary segmentation task and the alpha matte prediction task interactively, and we further design a hybrid loss to adaptively balance two tasks during the multitask learning process. Additionally, we adopt a salient object detection dataset to pretrain our network so that we could obtain a more accurate foreground segment before our training process. Experiments indicate that the proposed SegMatting qualitatively and quantitatively outperforms most previous trimap-free models with a significant margin, while remains competitive among trimap-based methods. / Thesis / Master of Science in Electrical and Computer Engineering (MSECE)

Anomaly detection is the process of finding unusual events in a given dataset. Anomaly detection is often performed on datasets with a fixed set of predefined features. As a result of this, if the normal features bear a close resemblance to the anomalous features, most anomaly detection algorithms exhibit poor performance. This work seeks to answer the question, can we deform these features so as to make the anomalies standout and hence improve the anomaly detection outcome? We employ a Deep Learning and an Active Learning framework to learn features for anomaly detection. In Active Learning, an Oracle (usually a domain expert) labels a small amount of data over a series of training rounds. The deep neural network is trained after each round to incorporate the feedback from the Oracle into the model. Results on the MNIST, CIFAR-10 and Galaxy Zoo datasets show that our algorithm, Ahunt, significantly outperforms other anomaly detection algorithms used on a fixed, static, set of features. Ahunt can therefore overcome a poor choice of features that happen to be suboptimal for detecting anomalies in the data, learning more appropriate features. We also explore the role of the loss function and Active Learning query strategy, showing these are important, especially when there is a significant variation in the anomalies.

No description available.

Fractures are ubiquitous in the subsurface, and they provide dominant pathways for fluid flow in low permeability formations. Therefore, fractures usually play an essential role in many engineering fields, such as hydrology, waste disposal, geothermal reservoir and petroleum reservoir exploitation. Since fractures are invisible and have variable sizes from micrometers to kilometers, there is limited knowledge of their structure. We aim to deepen the understanding of fracture networks in the subsurface from their topological structures, hydraulic connectivity and characteristics at different scales. We adopt the discrete fracture network method and develop an efficient C++ code, HatchFrac, to make in-depth investigations possible. We start from generating stochastic fracture networks by constraining fracture geometries with different stochastic distributions. We apply percolation theory to investigate the global connectivity of fracture networks. We find that commonly adopted percolation parameters are unsuitable for the characterization of the percolation state of complex fracture networks. We implement the concept of global efficiency to quantify the impact of fracture geometries on the connectivity of fracture networks. Furthermore, we constrain the fracture networks with geological data and geomechanics principles. We investigate the correlation of fracture intensities with different dimensionality and find that it is not feasible to obtain correct 3D intensity parameters from 1D or 2D samples. We utilize a deep-learning technique and propose a pixel-based detection algorithm to automatically interpret fractures from raw outcrop images. Interpreted fracture maps provide abundant resources to investigate fracture intensities, lengths,orientations, and generations. For large scale faults, we develop a method to generate fault segments from a rough fault trace on a seismic map. Accurate fault geometries have significant impacts on damage zones and fault-related flow problems. For small scale fractures, we consider the impact of fracture sealing on the percolation state of orthogonal fracture networks. We emphasize the importance of non-critically stressed and partially sealed fractures, which are usually neglected because usually they are nonconductive. However, with significant stress perturbations, those noncritically stressed and partially sealed fractures can also contribute to the production by enlarging the stimulated reservoir volume.