Optimization of Edge Resources for Deep Learning Application with Batch and Model Management

In the past decade, we have witnessed a dramatically increasing volume of data collected from various sources. To maximize utilization, various machine and deep learning models have been developed to study data. While data-driven applications improve countless products, hyperparameter tuning for the models is still a time-consuming and resource-intensive process. Cloud computing provides infrastructure support for the training of deep learning applications. The cloud service providers create an isolated virtual environment for clients who share physical resources, e.g., CPU and memory. On the cloud, resource management schemes are implemented to enable better sharing among users and boost system-wide performance. However, general scheduling approaches, such as spread priority and balanced resource schedulers, do not work well with deep learning workloads. In this article, we propose SpeCon, a novel container scheduler optimized for short-lived deep learning applications. Based on virtualized containers, such as Kubernetes and Docker, SpeCon analyzes the typical characteristics of training processes. We design a suite of algorithms to monitor the training’s progress and speculatively migrate the slow-growing models to release resources for fast-growing ones. Specifically, the extensive experiments demonstrate that SpeCon improves an individual job’s completion time by up to 41.5%, 14.8% system-wide, and 24.7% in terms of makespan.

Edge AI systems are increasingly being adopted in a wide range of application domains. These systems typically deploy Convolutional Neural Network (CNN) models on edge devices to perform inference, while relying on the cloud for model training. This is due to the high computational and memory demands of conventional model training, which exceeds the capabilities of resource-constrained edge devices running on tight power budgets. The dependency on the cloud for training is not suitable in many applications, where new objects or environmental conditions different from the ones present during training, are frequently encountered. In such applications, continual learning of new knowledge on the edge device becomes a necessity to avoid performance bottlenecks due to round-trip communication delays, network connectivity, and the available bandwidth. In this thesis, we propose Field-Programmable Gate Array (FPGA) based accelerator architecture and optimization strategies for a new paradigm of machine learning algorithms that is capable of continual learning. The proposed methods will enable edge FPGA systems to perform on-device deep continual learning for object classification. Specifically, the proposed methods aim to achieve real-time learning on-device, while providing for a high degree of scalability to learn a large number of classes. We first propose a FPGA accelerator for a Self-Organizing Neural Network (SONN), that can perform class-incremental continual learning in a streaming manner when combined with a CNN. The SONN model performs unsupervised learning from embedding features extracted from the CNN model by dynamically growing neurons and connections. We introduce design optimization strategies and runtime scheduling techniques to optimize resource usage, latency, and energy consumption. Experimental results based on Core50 dataset for continuous object recognition from video sequences, demonstrated that the proposed FPGA architecture outperforms CPU and GPU based counterparts in terms of latency and power. However, the SONN model grows proportionally to the classes learnt, which limits its scalability to learn a large number of classes efficiently. Next, we propose a FPGA accelerator for a Streaming Linear Discriminant Analysis (SLDA) model to overcome the scalability limitations of SONN. Similar to the SONN, SLDA performs continual learning from embedding features extracted from a CNN in a streaming manner. SLDA is highly scalable for learning a large number of classes as the network does not grow dynamically to accommodate new knowledge. We propose several design and runtime optimizations to minimize resource usage, latency, and energy consumption. Additionally, we introduce a new variant of SLDA and discuss the accuracy-efficiency trade-offs using popular datasets for continual learning, CoRE50 and CUB200. The results demonstrate that the proposed SLDA accelerator outperforms CPU and GPU counterparts, in terms of latency and energy efficiency. Finally, we demonstrate a full on-chip deep continual learning pipeline on FPGA, by integrating the proposed SLDA accelerator with Xilinx DPU, a programmable CNN accelerator IP. The design is implemented on a Xilinx Zynq Ultrascale+ MPSoC. In order to overcome the large performance bottleneck due to the communication overhead between the ARM processing system (PS) and programmable logic (PL), we implemented a Linux device driver that facilitates efficient memory mapping between PS-PL. The experimental results based on CoRE50 dataset show that the proposed pipeline is capable of performing continual learning at nearly the same latency as the inference pipeline, with only a marginal increase in energy consumption. Our results clearly demonstrate the viability of deploying real-time deep continual learning on edge AI systems that are equipped with FPGA accelerators.

Nowadays, machine learning (ML) has attained a high level of achievement in many contexts. Considering the significance of ML in medical and bioinformatics owing to its accuracy, many investigators discussed multiple solutions for developing the function of medical and bioinformatics challenges using deep learning (DL) techniques. The importance of DL in Internet of Things (IoT)-based bio- and medical informatics lies in its ability to analyze and interpret large amounts of complex and diverse data in real time, providing insights that can improve healthcare outcomes and increase efficiency in the healthcare industry. Several applications of DL in IoT-based bio- and medical informatics include diagnosis, treatment recommendation, clinical decision support, image analysis, wearable monitoring, and drug discovery. The review aims to comprehensively evaluate and synthesize the existing body of the literature on applying deep learning in the intersection of the IoT with bio- and medical informatics. In this paper, we categorized the most cutting-edge DL solutions for medical and bioinformatics issues into five categories based on the DL technique utilized: convolutional neural network, recurrent neural network, generative adversarial network, multilayer perception, and hybrid methods. A systematic literature review was applied to study each one in terms of effective properties, like the main idea, benefits, drawbacks, methods, simulation environment, and datasets. After that, cutting-edge research on DL approaches and applications for bioinformatics concerns was emphasized. In addition, several challenges that contributed to DL implementation for medical and bioinformatics have been addressed, which are predicted to motivate more studies to develop medical and bioinformatics research progressively. According to the findings, most articles are evaluated using features like accuracy, sensitivity, specificity, F-score, latency, adaptability, and scalability.

It is a computational approach, which uses a deep learning model with an architecture similar to that of biological brain networks, that has been trained using vast amounts of data. Deep reinforcement learning (DRL) is another name for deep learning (DL). By eliminating the need for direct programming in the process, DL functions as a middleman between data collection and meaningful knowledge. It has outperformed the vast majority of classification algorithms and is capable of learning data representations for a broad range of functions by itself. Deep learning applications in cancer include classification, feature extraction, object identification, picture interpretation and translation, sensitively and appropriately, and image annotation and labeling. The goal of this chapter is to gain a better understanding of the possible function of DL and how it may be used more successfully in radiation oncology. With the expansion of DL, a wide range of studies that led to the improvement of radiation oncology were explored more thoroughly than before. This article discussed medical imaging, image segmentation utilizing computers to assist diagnosis, computer-aided detection, treatment planning and delivery, quality assurance, treatment response, and treatment delivery. The studies that utilized DL were classified and organized according to the kind of radiation treatment used. The most current scientific achievements were chosen, and the therapeutic value of their results was assessed. Therapists may profit from employing a deep learning model since it will provide them with more precise and accurate solutions to their problems. A statistical approach to cancer patient safety is obvious, but implementing these concepts would require social adjustments at both the academic and industrial levels, which will take time. The goal of this chapter was to make it as accessible as possible to both radiotherapy and deep learning in order to encourage new collaboration between the two groups in the development of specialized radiation technologies.

With the development of information and technology, especially with the boom in big data, healthcare support systems are becoming much better. Patient data can be collected, retrieved, and stored in real time. These data are valuable and meaningful for monitoring, diagnosing, and further applications in data analysis and decision-making. Essentially, the data can be divided into three types, namely, statistical, image-based, and sequential data. Each type has a different method of retrieval, processing, and deployment. Additionally, the application of machine learning (ML) and deep learning (DL) in healthcare support systems is growing more rapidly than ever. Numerous high-performance architectures are proposed to optimize decision-making. As reliability and stability are the most important factors in the healthcare support system, enhancing the predicted performance and maintaining the stability of the model are always the top priority. The main idea of our study comes from ensemble techniques. Numerous studies and data science competitions show that by combining several weak models into one, ensemble models can attain outstanding performance and reliability. We propose three deep ensemble learning (DEL) approaches, each with stable and reliable performance, that are workable on the above-mentioned data types. These are deep-stacked generalization ensemble learning, gradient deep learning boosting, and deep aggregation learning. The experiment results show that our proposed approaches achieve more vigorous and reliable performance than traditional ML and DL techniques on statistical, image-based, and sequential benchmark datasets. In particular, on the Heart Disease UCI dataset, representing the statistical type, the gradient deep learning boosting approach dominates the others with accuracy, recall, F1-score, Matthews correlation coefficient, and area under the curve values of 0.87, 0.81, 0.83, 0.73, and 0.91, respectively. On the X-ray dataset, representing the image-based type, the deep aggregation learning approach shows the highest performance with values of 0.91, 0.97, 0.93, 0.80, and 0.94, respectively. On the Depresjon dataset, representing the sequence type, the deep-stacked generalization ensemble learning approach outperforms the others with values of 0.91, 0.84, 0.86, 0.8, and 0.94, respectively. Overall, we conclude that applying DL models using our proposed approaches is a promising method for the healthcare support system to enhance prediction and diagnosis performance. Furthermore, our study reveals that these approaches are flexible and easy to apply to achieve optimal performance.

Deep learning has been successfully explored in addressing different multimedia topics recent years, ranging from object detection, semantic classification, entity annotation, to multimedia captioning, multimedia question answering and storytelling. Open source libraries and platforms such as Tensorflow, Caffe, MXnet significantly help promote the wide deployment of deep learning in solving real-world applications. On one hand, deep learning practitioners, while not necessary to understand the involved math behind, are able to set up and make use of a complex deep network. One recent deep learning tool based on Keras even provides the graphical interface to enable straightforward 'drag and drop' operation for deep learning programming. On the other hand, however, some general theoretical problems of learning such as the interpretation and generalization, have only achieved limited progress. Most deep learning papers published these days follow the pipeline of designing/modifying network structures - tuning parameters - reporting performance improvement in specific applications. We have even seen many deep learning application papers without one single equation. Theoretical interpretation and the science behind the study are largely ignored. While excited about the successful application of deep learning in classical and novel problems, we multimedia researchers are responsible to think and solve the fundamental topics in deep learning science. Prof. Guanrong Chen recently wrote an editorial note titled 'Science and Technology, not SciTech' [1]. This panel falls into similar discussion and aims to invite prestigious multimedia researchers and active deep learning practitioners to discuss the positioning of deep learning research now and in the future. Specifically, each panelist is asked to present their opinions on the following five questions: 1)How do you think the current phenomenon that deep learning applications are explosively growing, while the general theoretical problems remain slow progress? 2)Do you agree that deployment of deep learning techniques is getting easy (with a low barrier), while deep learning research is difficult (with a high barrier) 3)What do you think are the core problems for deep learning techniques? 4)What do you think are the core problems for deep learning science? 5)What's your suggestion on the multimedia research in the post-deep learning era?

Few-shot learning aims to obtain a better deep learning model through training with a smaller amount of data. In recent years, with the development and application of deep learning, deep learning has faced the problem of few-shot in many scenarios. Therefore, the study of few-shot learning will promote the application and deployment of deep learning in the industrial field. First of all, this survey specifically introduces two few-shot learning implementation methods: based on data augmentation and based on transfer learning. Then, this survey lists actual cases to illustrate the application of few-shot learning in industry. One case is about Few-shot parts surface defect detection based on metric learning. Another case is about poultry egg detection in few-shot based on meta learning. Finally, this survey summarizes the research achievements and research value of few-shot learning. Survey summarizes the problems and challenges faced by few-shot learning and the future development direction of few-shot learning.KeywordsFew-shot learningData augmentationTransfer learningMetric learningMeta learning

In today’s complex and ever-changing world, Supply Chain Management (SCM) is increasingly becoming a cornerstone to any company to reckon with in this global era for all industries. The rapidly growing interest in the application of Deep Learning (a class of machine learning algorithms) in SCM, has urged the need for an up-to-date systematic review on the research development. The main purpose of this study is to provide a comprehensive vision by reviewing a set of 43 papers about applications of Deep Learning (DL) methods to the SCM, as well as the trends, perspectives, and potential research gaps. This review uses content analysis to answer three research questions namely: 1- What SCM problems have been solved by the use of DL techniques? 2- What DL algorithms have been used to solve these problems? 3- What alternative algorithms have been used to tackle the same problems? And do DL outperform these methods and through which evaluation metrics? This review also responds to this call by developing a conceptual framework in a value-adding perspective that provides a full picture of areas on where and how DL can be applied within the SCM context. This makes it easier to identify potential applications to corporations, in addition to potential future research areas to science. It might also provide businesses a competitive advantage over their competitors by allowing them to add value to their data by analyzing it quickly and precisely.

Deep Learning (DL) applications in the Internet of Things (IoT) have garnered significant attention, with numerous studies exploring various models and implementations. Concurrently, the emerging field of the Internet of Behaviors (IoB) has captured broad interest, extending the capabilities of IoT through the synergy of DL. This transformative approach presents novel possibilities across diverse domains (e.g. healthcare, business, education, and insurance). In this survey, we uniquely contribute by elucidating the synergistic potential of integrating IoB with DL. Our literature review provides a state-of-the-art analysis of DL implementations within the IoB ecosystem, highlighting architectures, features, and advantages over traditional machine learning methods. Through a meticulous examination of findings, we reveal specific insights gained from the survey, and we discuss issues, challenges, and future research directions in applying DL in IoB applications. Our survey stands as a testament to achievements in this dynamic intersection and serves as a call to action for exploring uncharted territories.

Path planning refers to that the mobile robot can obtain the surrounding environment information and its own state information through the sensor carried by itself, which can avoid obstacles and move towards the target point. Deep reinforcement learning consists of two parts: reinforcement learning and deep learning, mainly used to deal with perception and decision-making problems, has become an important research branch in the field of artificial intelligence. This paper first introduces the basic knowledge of deep learning and reinforcement learning. Then, the research status of deep reinforcement learning algorithm based on value function and strategy gradient in path planning is described, and the application research of deep reinforcement learning in computer game, video game and autonomous navigation is described. Finally, I made a brief summary and outlook on the algorithms and applications of deep reinforcement learning.

This study is conducted in response to the increasingly prominent climate crisis in contemporary society. It aims to contribute to the growing body of research on the application of deep learning (DL) in environmental sciences and to provide practical guidance for model selection in similar predictive tasks. To this end, the study focuses on carbon dioxide (CO2) emissions prediction, employing Multilayer Perceptron (MLP) models to analyze multi-country panel data. By integrating MLP with explainable artificial intelligence (XAI) techniques, this research not only investigates the underlying mechanisms of various factors influencing CO2 emissions but also quantifies and visualizes the contribution of different driving factors to the prediction outcomes, providing decision support for climate governance strategies. Through an analysis of global panel data, we construct a model incorporating 14 driving factors spanning multiple dimensions, including economic, social, environmental, energy, and technology aspects. To optimize the MLP model, we employ a fivedimensional hyperparameter space comprising hidden layer structure, learning rate, batch size, dropout rate, and training epochs and apply Grid Search for parameter tuning. Experimental results indicate that the MLP model achieves R2 of 0.9951, demonstrating its strong capability in highprecision nonlinear fitting under complex policy scenarios. To further enhance the interpretability of neural networks in CO2 emissions prediction, we introduce SHapley Additive exPlanations (SHAP) to quantify the marginal contributions of different driving factors. This analysis reveals that energy-related features play a dominant role in emission predictions, laying the foundation for scenario analysis and emission reduction policy evaluation. Furthermore, this study incorporates scenario analysis to simulate potential trajectories of CO2 emissions under different policy scenarios, providing a quantitative reference for future emission reduction strategies and environmental governance policies.

Deep Learning (DL) has become a prominent machine learning technique due to the availability of efficient computational resources in the form of Graphics Processing Units (GPUs), large-scale datasets and a variety of models. The newer generation of GPUs are being designed with special emphasis on optimizing performance for DL applications. Also, the availability of easy-to-use DL frameworks—like PyTorch and TensorFlow— has enhanced productivity of domain experts to work on their custom DL applications from diverse domains. However, existing Deep Neural Network (DNN) training approaches may not fully utilize the newly emerging powerful GPUs like the NVIDIA A100—this is the primary issue that we address in this paper. Our motivating analyses show that the GPU utilization on NVIDIA A100 can be as low as 43% using traditional DNN training approaches for small-to-medium DL models and input data size. This paper proposes AccDP—a data-parallel distributed DNN training approach—to accelerate GPU-based DL applications. AccDP exploits the Message Passing Interface (MPI) communication library coupled with the NVIDIA’s Multi-Process Service (MPS) to increase the amount of work assigned to parallel GPUs resulting in higher utilization of compute resources. We evaluate our proposed design on different small-to-medium DL models and input sizes on the state-of-the-art HPC clusters. By injecting more parallelism into DNN training using our approach, the evaluation shows up to 58% improvement in training performance on a single GPU and up to 62% on 16 GPUs compared to regular DNN training. Furthermore, we conduct an in-depth characterization to determine the impact of several DNN training factors and best practices—including the batch size and the number of data loading workers— to optimally utilize GPU devices. To the best of our knowledge, this is the first work that explores the use of MPS and MPI to maximize the utilization of GPUs in distributed DNN training.

Deep learning is a complex machine learning algorithm that can learn the deep inner rules of a sample. In recent years, deep learning has achieved good results in the field of image processing. The essence of deep learning is to build a multi-layered machine learning architecture that trains on large-scale data. With the development of computer technology, deep learning has achieved good results in image recognition and natural language processing. Deep learning is also becoming more and more widely used in industry. This paper introduces the applications of deep learning in the industrial field, and finally discusses development and challenges of deep learning in industrial applications in the future.

Deep Learning Applications in Primary Education: A Systematic Literature Review of Emerging Trends, Challenges, and Opportunities. Objectives: Despite significant advances in healthcare and finance, Deep Learning (DL) remains underutilized in primary education, with only about 12% of AI-related studies focusing on K–6. Given the formative role of early schooling in cognitive and social development, this systematic review analyzed recent empirical studies to identify key trends, challenges, and opportunities in applying DL to primary education. Methods: Following the PRISMA 2020 guidelines, 21 studies published between 2021 and 2025 across 11 countries were analyzed using a structured coding sheet and further examined with bibliometric mapping, Microsoft Excel, and Python-based visualization tools. The review included diverse sources focusing on DL use cases across global primary education systems. Findings: The findings reveal a global increase in DL adoption, led by China and South Korea, with growing contributions from Indonesia, India, and the Philippines. Convolutional Neural Networks (CNNs), Recurrent Neural Networks (RNNs), Generative Adversarial Networks (GANs), and transformer-based models are among the most commonly applied architectures to tasks such as personalized learning, early detection of learning difficulties, assessment automation, and curriculum development. However, there are still problems in the context of ethical concerns, including data privacy, algorithmic bias, and equity of access. Technical barriers involve dataset complexity, model generalization, and resource limitations, while pedagogical issues center on aligning DL applications with developmental needs and classroom realities. Despite these obstacles, DL demonstrates significant potential to enhance personalization, foster engagement, and support holistic educational outcomes. Conclusion: This review contributes a strategic roadmap for integrating DL in primary education by balancing innovation with pedagogy and ethics. Future research should prioritize cross-disciplinary collaboration, greater geographic diversity, and improvements in scalability and interpretability to ensure DL supports equitable, future-ready learning. Keywords: deep learning, primary education, personalized learning, systematic literature review, educational technology.

The application of artificial intelligence is deep learning which is one of the current topics in the computer field as well as for the application of computer vision. With the continuous enhancement of deep learning, the algorithm performance is constantly updated. This review paper provides a brief overview of the basic concepts of computer vision and deep learning. Image classification, semantic segmentation and object detection are introduced in this paper followed by a description of their real world applications in various computer vision tasks, such as smart transportation and face recognition. Afterwards, the main applications of deep learning in the research field are demonstrated in this paper.