Browsing by Subject "Deep Learning"

Now showing 1 - 10 of 34
  • Thumbnail Image
    Item
    3-D Scene Reconstruction for Passive Ranging Using Depth from Defocus and Deep Learning
    (2019-08) Emerson, David R.; Christopher, Lauren A.; Ben Miled, Zina; King, Brian; Salama, Paul
    Depth estimation is increasingly becoming more important in computer vision. The requirement for autonomous systems to gauge their surroundings is of the utmost importance in order to avoid obstacles, preventing damage to itself and/or other systems or people. Depth measuring/estimation systems that use multiple cameras from multiple views can be expensive and extremely complex. And as these autonomous systems decrease in size and available power, the supporting sensors required to estimate depth must also shrink in size and power consumption. This research will concentrate on a single passive method known as Depth from Defocus (DfD), which uses an in-focus and out-of-focus image to infer the depth of objects in a scene. The major contribution of this research is the introduction of a new Deep Learning (DL) architecture to process the the in-focus and out-of-focus images to produce a depth map for the scene improving both speed and performance over a range of lighting conditions. Compared to the previous state-of-the-art multi-label graph cuts algorithms applied to the synthetically blurred dataset the DfD-Net produced a 34.30% improvement in the average Normalized Root Mean Square Error (NRMSE). Similarly the DfD-Net architecture produced a 76.69% improvement in the average Normalized Mean Absolute Error (NMAE). Only the Structural Similarity Index (SSIM) had a small average decrease of 2.68% when compared to the graph cuts algorithm. This slight reduction in the SSIM value is a result of the SSIM metric penalizing images that appear to be noisy. In some instances the DfD-Net output is mottled, which is interpreted as noise by the SSIM metric. This research introduces two methods of deep learning architecture optimization. The first method employs the use of a variant of the Particle Swarm Optimization (PSO) algorithm to improve the performance of the DfD-Net architecture. The PSO algorithm was able to find a combination of the number of convolutional filters, the size of the filters, the activation layers used, the use of a batch normalization layer between filters and the size of the input image used during training to produce a network architecture that resulted in an average NRMSE that was approximately 6.25% better than the baseline DfD-Net average NRMSE. This optimized architecture also resulted in an average NMAE that was 5.25% better than the baseline DfD-Net average NMAE. Only the SSIM metric did not see a gain in performance, dropping by 0.26% when compared to the baseline DfD-Net average SSIM value. The second method illustrates the use of a Self Organizing Map clustering method to reduce the number convolutional filters in the DfD-Net to reduce the overall run time of the architecture while still retaining the network performance exhibited prior to the reduction. This method produces a reduced DfD-Net architecture that has a run time decrease of between 14.91% and 44.85% depending on the hardware architecture that is running the network. The final reduced DfD-Net resulted in a network architecture that had an overall decrease in the average NRMSE value of approximately 3.4% when compared to the baseline, unaltered DfD-Net, mean NRMSE value. The NMAE and the SSIM results for the reduced architecture were 0.65% and 0.13% below the baseline results respectively. This illustrates that reducing the network architecture complexity does not necessarily reduce the reduction in performance. Finally, this research introduced a new, real world dataset that was captured using a camera and a voltage controlled microfluidic lens to capture the visual data and a 2-D scanning LIDAR to capture the ground truth data. The visual data consists of images captured at seven different exposure times and 17 discrete voltage steps per exposure time. The objects in this dataset were divided into four repeating scene patterns in which the same surfaces were used. These scenes were located between 1.5 and 2.5 meters from the camera and LIDAR. This was done so any of the deep learning algorithms tested would see the same texture at multiple depths and multiple blurs. The DfD-Net architecture was employed in two separate tests using the real world dataset. The first test was the synthetic blurring of the real world dataset and assessing the performance of the DfD-Net trained on the Middlebury dataset. The results of the real world dataset for the scenes that were between 1.5 and 2.2 meters from the camera the DfD-Net trained on the Middlebury dataset produced an average NRMSE, NMAE and SSIM value that exceeded the test results of the DfD-Net tested on the Middlebury test set. The second test conducted was the training and testing solely on the real world dataset. Analysis of the camera and lens behavior led to an optimal lens voltage step configuration of 141 and 129. Using this configuration, training the DfD-Net resulted in an average NRMSE, NMAE and SSIM of 0.0660, 0.0517 and 0.8028 with a standard deviation of 0.0173, 0.0186 and 0.0641 respectively.
  • Thumbnail Image
    Item
    A Multi-head Attention Approach with Complementary Multimodal Fusion for Vehicle Detection
    (2024-05) Tabassum, Nujhat; El-Sharkawy, Mohamed; King, Brian; Rizkalla, Maher
    The advancement of autonomous vehicle technologies has taken a significant leap with the development of an improved version of the Multimodal Vehicle Detection Network (MVDNet), distinguished by the integration of a multi-head attention layer. This key enhancement significantly refines the network's capability to process and integrate multimodal sensor data, an aspect that becomes crucial in the face of challenging weather conditions. The effectiveness of this upgraded Multi-Head MVDNet is rigorously verified through an extensive dataset acquired from the Oxford Radar Robotcar, demonstrating its enhanced performance capabilities. Notably, in complex environmental conditions, the Multi-Head MVDNet shows a marked superiority in terms of Average Precision (AP) compared to existing models, underscoring its advanced detection capabilities. The transition from the traditional MVDNet to the enhanced Multi-Head Vehicle Detection Network signifies a notable breakthrough in the arena of vehicle detection technologies, with a special emphasis on operation under severe meteorological conditions, such as the obscuring presence of dense fog or the complexities introduced by heavy snowfall. This significant enhancement capitalizes on the foundational principles of the original MVDNet, which skillfully amalgamates the individual strengths of lidar and radar sensors. This is achieved through an intricate and refined process of feature tensor fusion, creating a more robust and comprehensive sensory data interpretation framework. A major innovation introduced in this updated model is the implementation of a multi-head attention layer. This layer serves as a sophisticated replacement for the previously employed self-attention mechanism. Segmenting the attention mechanism into several distinct partitions enhances the network's efficiency and accuracy in processing and interpreting vast arrays of sensor data. An exhaustive series of experimental analyses was undertaken to determine the optimal configuration of this multi-head attention mechanism. These experiments explored various combinations and settings, ultimately identifying a configuration consisting of seven distinct attention heads as the most effective. This setup was found to optimize the balance between computational efficiency and detection accuracy. When tested using the rich radar and lidar datasets from the ORR project, this advanced Multi-Head MVDNet configuration consistently demonstrated its superiority. It not only surpassed the performance of the original MVDNet but also showed marked improvements over models that relied solely on lidar data or the DEF models, especially in terms of vehicular detection accuracy. This enhancement in the MVDNet model, with its focus on multi-head attention, not only represents a significant leap in the field of autonomous vehicle detection but also lays a foundation for future research. It opens new pathways for exploring various attention mechanisms and their potential applicability in scenarios requiring real-time vehicle detection. Furthermore, it accentuates the importance of sophisticated sensor fusion techniques as vital tools in overcoming the challenges posed by adverse environmental conditions, thus paving the way for more resilient and reliable autonomous vehicular technologies.
  • Thumbnail Image
    Item
    A-MnasNet and Image Classification on NXP Bluebox 2.0
    (ASTES, 2021-01) Shah, Prasham; El-Sharkawy, Mohamed; Electrical and Computer Engineering, School of Engineering and Technology
    Computer Vision is a domain which deals with the challenge of enabling technology with vision capabilities. This goal is accomplished with the use of Convolutional Neural Networks. They are the backbone of implementing vision applications on embedded systems. They are complex but highly efficient in extracting features, thus, enabling embedded systems to perform computer vision applications. After AlexNet won the ImageNet Large Scale Visual Recognition Challenge in 2012, there was a drastic increase in research on Convolutional Neural Networks. The convolutional neural networks were made deeper and wider, in order to make them more efficient. They were able to extract features efficiently, but the computational complexity and the computational cost of those networks also increased. It became very challenging to deploy such networks on embedded hardware. Since embedded systems have limited resources like power, speed and computational capabilities, researchers got more inclined towards the goal of making convolutional neural networks more compact, with efficiency of extracting features similar to that of the novel architectures. This research has a similar goal of proposing a convolutional neural network with enhanced efficiency and further using it for a vision application like Image Classification on NXP Bluebox 2.0, an autonomous driving platform by NXP Semiconductors. This paper gives an insight on the Design Space Exploration technique used to propose A-MnasNet (Augmented MnasNet) architecture, with enhanced capabilities, from MnasNet architecture. Furthermore, it explains the implementation of A-MnasNet on Bluebox 2.0 for Image Classification.
  • Thumbnail Image
    Item
    Adversarial Attacks and Defense Mechanisms to Improve Robustness of Deep Temporal Point Processes
    (2022-08) Khorshidi, Samira; Mohler, George; Al Hasan, Mohammad; Raje, Rajeev; Durresi, Arjan
    Temporal point processes (TPP) are mathematical approaches for modeling asynchronous event sequences by considering the temporal dependency of each event on past events and its instantaneous rate. Temporal point processes can model various problems, from earthquake aftershocks, trade orders, gang violence, and reported crime patterns, to network analysis, infectious disease transmissions, and virus spread forecasting. In each of these cases, the entity’s behavior with the corresponding information is noted over time as an asynchronous event sequence, and the analysis is done using temporal point processes, which provides a means to define the generative mechanism of the sequence of events and ultimately predict events and investigate causality. Among point processes, Hawkes process as a stochastic point process is able to model a wide range of contagious and self-exciting patterns. One of Hawkes process’s well-known applications is predicting the evolution of viral processes on networks, which is an important problem in biology, the social sciences, and the study of the Internet. In existing works, mean-field analysis based upon degree distribution is used to predict viral spreading across networks of different types. However, it has been shown that degree distribution alone fails to predict the behavior of viruses on some real-world networks. Recent attempts have been made to use assortativity to address this shortcoming. This thesis illustrates how the evolution of such a viral process is sensitive to the underlying network’s structure. In Chapter 3 , we show that adding assortativity does not fully explain the variance in the spread of viruses for a number of real-world networks. We propose using the graphlet frequency distribution combined with assortativity to explain variations in the evolution of viral processes across networks with identical degree distribution. Using a data-driven approach, by coupling predictive modeling with viral process simulation on real-world networks, we show that simple regression models based on graphlet frequency distribution can explain over 95% of the variance in virality on networks with the same degree distribution but different network topologies. Our results highlight the importance of graphlets and identify a small collection of graphlets that may have the most significant influence over the viral processes on a network. Due to the flexibility and expressiveness of deep learning techniques, several neural network-based approaches have recently shown promise for modeling point process intensities. However, there is a lack of research on the possible adversarial attacks and the robustness of such models regarding adversarial attacks and natural shocks to systems. Furthermore, while neural point processes may outperform simpler parametric models on in-sample tests, how these models perform when encountering adversarial examples or sharp non-stationary trends remains unknown. In Chapter 4 , we propose several white-box and black-box adversarial attacks against deep temporal point processes. Additionally, we investigate the transferability of whitebox adversarial attacks against point processes modeled by deep neural networks, which are considered a more elevated risk. Extensive experiments confirm that neural point processes are vulnerable to adversarial attacks. Such a vulnerability is illustrated both in terms of predictive metrics and the effect of attacks on the underlying point process’s parameters. Expressly, adversarial attacks successfully transform the temporal Hawkes process regime from sub-critical to into a super-critical and manipulate the modeled parameters that is considered a risk against parametric modeling approaches. Additionally, we evaluate the vulnerability and performance of these models in the presence of non-stationary abrupt changes, using the crimes and Covid-19 pandemic dataset as an example. Considering the security vulnerability of deep-learning models, including deep temporal point processes, to adversarial attacks, it is essential to ensure the robustness of the deployed algorithms that is despite the success of deep learning techniques in modeling temporal point processes. In Chapter 5 , we study the robustness of deep temporal point processes against several proposed adversarial attacks from the adversarial defense viewpoint. Specifically, we investigate the effectiveness of adversarial training using universal adversarial samples in improving the robustness of the deep point processes. Additionally, we propose a general point process domain-adopted (GPDA) regularization, which is strictly applicable to temporal point processes, to reduce the effect of adversarial attacks and acquire an empirically robust model. In this approach, unlike other computationally expensive approaches, there is no need for additional back-propagation in the training step, and no further network isrequired. Ultimately, we propose an adversarial detection framework that has been trained in the Generative Adversarial Network (GAN) manner and solely on clean training data. Finally, in Chapter 6 , we discuss implications of the research and future research directions.
  • Thumbnail Image
    Item
    AI on the Edge with CondenseNeXt: An Efficient Deep Neural Network for Devices with Constrained Computational Resources
    (2021-08) Kalgaonkar, Priyank B.; El-Sharkawy, Mohamed A.; King, Brian S.; Rizkalla, Maher E.
    Research work presented within this thesis propose a neoteric variant of deep convolutional neural network architecture, CondenseNeXt, designed specifically for ARM-based embedded computing platforms with constrained computational resources. CondenseNeXt is an improved version of CondenseNet, the baseline architecture whose roots can be traced back to ResNet. CondeseNeXt replaces group convolutions in CondenseNet with depthwise separable convolutions and introduces group-wise pruning, a model compression technique, to prune (remove) redundant and insignificant elements that either are irrelevant or do not affect performance of the network upon disposition. Cardinality, a new dimension to the existing spatial dimensions, and class-balanced focal loss function, a weighting factor inversely proportional to the number of samples, has been incorporated in order to relieve the harsh effects of pruning, into the design of CondenseNeXt’s algorithm. Furthermore, extensive analyses of this novel CNN architecture was performed on three benchmarking image datasets: CIFAR-10, CIFAR-100 and ImageNet by deploying the trained weight on to an ARM-based embedded computing platform: NXP BlueBox 2.0, for real-time image classification. The outputs are observed in real-time in RTMaps Remote Studio’s console to verify the correctness of classes being predicted. CondenseNeXt achieves state-of-the-art image classification performance on three benchmark datasets including CIFAR-10 (4.79% top-1 error), CIFAR-100 (21.98% top-1 error) and ImageNet (7.91% single model, single crop top-5 error), and up to 59.98% reduction in forward FLOPs compared to CondenseNet. CondenseNeXt can also achieve a final trained model size of 2.9 MB, however at the cost of 2.26% in accuracy loss. Thus, performing image classification on ARM-Based computing platforms without requiring a CUDA enabled GPU support, with outstanding efficiency.
  • Thumbnail Image
    Item
    Automatic Extraction of Computer Science Concept Phrases Using a Hybrid Machine Learning Paradigm
    (2023-05) Jahin, S M Abrar; Al Hasan, Mohammad; Fang, Shiaofen; Mukhopadhyay, Snehasis
    With the proliferation of computer science in recent years in modern society, the number of computer science-related employment is expanding quickly. Software engineer has been chosen as the best job for 2023 based on pay, stress level, opportunity for professional growth, and balance between work and personal life. This was decided by a rankings of different news, journals, and publications. Computer science occupations are anticipated to be in high demand not just in 2023, but also for the foreseeable future. It's not surprising that the number of computer science students at universities is growing and will continue to grow. The enormous increase in student enrolment in many subdisciplines of computers has presented some distinct issues. If computer science is to be incorporated into the K-12 curriculum, it is vital that K-12 educators are competent. But one of the biggest problems with this plan is that there aren't enough trained computer science professors. Numerous new fields and applications, for instance, are being introduced to computer science. In addition, it is difficult for schools to recruit skilled computer science instructors for a variety of reasons including low salary issue. Utilizing the K-12 teachers who are already in the schools, have a love for teaching, and consider teaching as a vocation is therefore the most effective strategy to improve or fix this issue. So, if we want teachers to quickly grasp computer science topics, we need to give them an easy way to learn about computer science. To simplify and expedite the study of computer science, we must acquaint school-treachers with the terminology associated with computer science concepts so they can know which things they need to learn according to their profile. If we want to make it easier for schoolteachers to comprehend computer science concepts, it would be ideal if we could provide them with a tree of words and phrases from which they could determine where the phrases originated and which phrases are connected to them so that they can be effectively learned. To find a good concept word or phrase, we must first identify concepts and then establish their connections or linkages. As computer science is a fast developing field, its nomenclature is also expanding at a frenetic rate. Therefore, adding all concepts and terms to the knowledge graph would be a challenging endeavor. Cre- ating a system that automatically adds all computer science domain terms to the knowledge graph would be a straightforward solution to the issue. We have identified knowledge graph use cases for the schoolteacher training program, which motivates the development of a knowledge graph. We have analyzed the knowledge graph's use case and the knowledge graph's ideal characteristics. We have designed a webbased system for adding, editing, and removing words from a knowledge graph. In addition, a term or phrase can be represented with its children list, parent list, and synonym list for enhanced comprehension. We' ve developed an automated system for extracting words and phrases that can extract computer science idea phrases from any supplied text, therefore enriching the knowledge graph. Therefore, we have designed the knowledge graph for use in teacher education so that school-teachers can educate K-12 students computer science topicses effectively.
  • Thumbnail Image
    Item
    Deep Image Processing with Spatial Adaptation and Boosted Efficiency & Supervision for Accurate Human Keypoint Detection and Movement Dynamics Tracking
    (2023-05) Dai, Chao Yang; Zhang, Qingxue; King, Brian S.; Fang, Shiaofen
    This thesis aims to design and develop the spatial adaptation approach through spatial transformers to improve the accuracy of human keypoint recognition models. We have studied different model types and design choices to gain an accuracy increase over models without spatial transformers and analyzed how spatial transformers increase the accuracy of predictions. A neural network called Widenet has been leveraged as a specialized network for providing the parameters for the spatial transformer. Further, we have evaluated methods to reduce the model parameters, as well as the strategy to enhance the learning supervision for further improving the performance of the model. Our experiments and results have shown that the proposed deep learning framework can effectively detect the human key points, compared with the baseline methods. Also, we have reduced the model size without significantly impacting the performance, and the enhanced supervision has improved the performance. This study is expected to greatly advance the deep learning of human key points and movement dynamics.
  • Thumbnail Image
    Item
    Deep Learning Based Methods for Automatic Extraction of Syntactic Patterns and their Application for Knowledge Discovery
    (2023-12-28) Kabir, Md. Ahsanul; Hasan, Mohammad Al; Mukhopadhyay, Snehasis; Tuceryan, Mihran; Fang, Shiaofen
    Semantic pairs, which consist of related entities or concepts, serve as the foundation for comprehending the meaning of language in both written and spoken forms. These pairs enable to grasp the nuances of relationships between words, phrases, or ideas, forming the basis for more advanced language tasks like entity recognition, sentiment analysis, machine translation, and question answering. They allow to infer causality, identify hierarchies, and connect ideas within a text, ultimately enhancing the depth and accuracy of automated language processing. Nevertheless, the task of extracting semantic pairs from sentences poses a significant challenge, necessitating the relevance of syntactic dependency patterns (SDPs). Thankfully, semantic relationships exhibit adherence to distinct SDPs when connecting pairs of entities. Recognizing this fact underscores the critical importance of extracting these SDPs, particularly for specific semantic relationships like hyponym-hypernym, meronym-holonym, and cause-effect associations. The automated extraction of such SDPs carries substantial advantages for various downstream applications, including entity extraction, ontology development, and question answering. Unfortunately, this pivotal facet of pattern extraction has remained relatively overlooked by researchers in the domains of natural language processing (NLP) and information retrieval. To address this gap, I introduce an attention-based supervised deep learning model, ASPER. ASPER is designed to extract SDPs that denote semantic relationships between entities within a given sentential context. I rigorously evaluate the performance of ASPER across three distinct semantic relations: hyponym-hypernym, cause-effect, and meronym-holonym, utilizing six datasets. My experimental findings demonstrate ASPER's ability to automatically identify an array of SDPs that mirror the presence of these semantic relationships within sentences, outperforming existing pattern extraction methods by a substantial margin. Second, I want to use the SDPs to extract semantic pairs from sentences. I choose to extract cause-effect entities from medical literature. This task is instrumental in compiling various causality relationships, such as those between diseases and symptoms, medications and side effects, and genes and diseases. Existing solutions excel in sentences where cause and effect phrases are straightforward, such as named entities, single-word nouns, or short noun phrases. However, in the complex landscape of medical literature, cause and effect expressions often extend over several words, stumping existing methods, resulting in incomplete extractions that provide low-quality, non-informative, and at times, conflicting information. To overcome this challenge, I introduce an innovative unsupervised method for extracting cause and effect phrases, PatternCausality tailored explicitly for medical literature. PatternCausality employs a set of cause-effect dependency patterns as templates to identify the key terms within cause and effect phrases. It then utilizes a novel phrase extraction technique to produce comprehensive and meaningful cause and effect expressions from sentences. Experiments conducted on a dataset constructed from PubMed articles reveal that PatternCausality significantly outperforms existing methods, achieving a remarkable order of magnitude improvement in the F-score metric over the best-performing alternatives. I also develop various PatternCausality variants that utilize diverse phrase extraction methods, all of which surpass existing approaches. PatternCausality and its variants exhibit notable performance improvements in extracting cause and effect entities in a domain-neutral benchmark dataset, wherein cause and effect entities are confined to single-word nouns or noun phrases of one to two words. Nevertheless, PatternCausality operates within an unsupervised framework and relies heavily on SDPs, motivating me to explore the development of a supervised approach. Although SDPs play a pivotal role in semantic relation extraction, pattern-based methodologies remain unsupervised, and the multitude of potential patterns within a language can be overwhelming. Furthermore, patterns do not consistently capture the broader context of a sentence, leading to the extraction of false-positive semantic pairs. As an illustration, consider the hyponym-hypernym pattern the w of u which can correctly extract semantic pairs for a sentence like the village of Aasu but fails to do so for the phrase the moment of impact. The root cause of this limitation lies in the pattern's inability to capture the nuanced meaning of words and phrases in a sentence and their contextual significance. These observations have spurred my exploration of a third model, DepBERT which constitutes a dependency-aware supervised transformer model. DepBERT's primary contribution lies in introducing the underlying dependency structure of sentences to a language model with the aim of enhancing token classification performance. To achieve this, I must first reframe the task of semantic pair extraction as a token classification problem. The DepBERT model can harness both the tree-like structure of dependency patterns and the masked language architecture of transformers, marking a significant milestone, as most large language models (LLMs) predominantly focus on semantics and word co-occurrence while neglecting the crucial role of dependency architecture. In summary, my overarching contributions in this thesis are threefold. First, I validate the significance of the dependency architecture within various components of sentences and publish SDPs that incorporate these dependency relationships. Subsequently, I employ these SDPs in a practical medical domain to extract vital cause-effect pairs from sentences. Finally, my third contribution distinguishes this thesis by integrating dependency relations into a deep learning model, enhancing the understanding of language and the extraction of valuable semantic associations.
  • Thumbnail Image
    Item
    Deep Learning of Biomechanical Dynamics With Spatial Variability Mining and Model Sparsifiation
    (2024-08) Liu, Ming; Zhang, Qingxue; King, Brian S.; Ben-Miled, Zina; Xia, Yuni
    Deep learning of biomechanical dynamics is of great promise in smart health and data-driven precision medicine. Biomechanical dynamics are related to the movement patterns and gait characteristics of human people and may provide important insights if mined by deep learning models. However, efficient deep learning of biomechanical dynamics is still challenging, considering that there is a high diversity in the dynamics from different body locations, and the deep learning model may need to be lightweight enough to be able to be deployed in real-time. Targeting these challenges, we have firstly conducted studies on the spatial variability of biomechanical dynamics, aiming to evaluate and determine the optimal body location that is of great promise in robust physical activity type detection. Further, we have developed a framework for deep learning pruning, aiming to determine the optimal pruning schemes while maintaining acceptable performance. More specifically, the proposed approach first evaluates the layer importance of the deep learning model, and then leverages the probabilistic distribution-enabled threshold determination to optimize the pruning rate. The weighted random thresholding method is first investigated to further the understanding of the behavior of the pruning action for each layer. Afterwards, the Gaussian-based thresholding is designed to more effectively optimize the pruning strategies, which can find out the fine-grained pruning schemes with both emphasis and diversity regulation. Even further, we have enhanced and boosted the efficient deep learning framework, to co-optimize the accuracy and the continuity during the pruning process, with the latter metric – continuity meaning that the pruning locations in the weight matrices are encouraged to not cause too many noncontinuous non-pruned locations thereby achieving friendly model implementation. More specifically, the proposed framework leverages the significance scoring and the continuity scoring to quantize the characteristics of each of pruned convolutional filters, then leverages the clustering technique to group the pruned filters for each convolutional stage. Afterwards, the regularized ranking approach is designed to rank the pruned filters, through putting more emphasis on the continuity scores to encourage friendly implementation. In the end, a dual-thresholding strategy is leveraged to increase the diversity in this framework, during significance & continuity co-optimization. Experimental results have demonstrated promising findings, with enhanced understanding of the spatial variability of the biomechanical dynamics and best performance body location selection, with the effective deep learning model pruning framework that can reduce the model size significantly with performance maintained, and further, with the boosted framework that co-optimizes the accuracy and continuity to all consider the friendly implementation during the pruning process. Overall, this research will greatly advance the deep biomechanical mining towards efficient smart health.
  • Thumbnail Image
    Item
    Deep Learning with Go
    (2020-05) Stinson, Derek L.; Ben Miled, Zina; King, Brian; Rizkalla, Maher
    Current research in deep learning is primarily focused on using Python as a support language. Go, an emerging language, that has many benefits including native support for concurrency has seen a rise in adoption over the past few years. However, this language is not widely used to develop learning models due to the lack of supporting libraries and frameworks for model development. In this thesis, the use of Go for the development of neural network models in general and convolution neural networks is explored. The proposed study is based on a Go-CUDA implementation of neural network models called GoCuNets. This implementation is then compared to a Go-CPU deep learning implementation that takes advantage of Go's built in concurrency called ConvNetGo. A comparison of these two implementations shows a significant performance gain when using GoCuNets compared to ConvNetGo.