The performance of modern wireless communications systems depends critically on the quality of the available channel state information (CSI) at the transmitter and receiver. Several previous works have proposed concepts and algorithms that help maintain high quality CSI even in the presence of high mobility and channel aging, such as temporal prediction schemes that employ neural networks. However, it is still unclear which neural network-based scheme provides the best performance in terms of prediction quality, training complexity and practical feasibility. To investigate such a question, this paper first provides an overview of state-of-the-art neural networks applicable to channel prediction and compares their performance in terms of prediction quality. Next, a new comparative analysis is proposed for four promising neural networks with different prediction horizons. The well-known tapped delay channel model recommended by the Third Generation Partnership Program is used for a standardized comparison among the neural networks. Based on this comparative evaluation, the advantages and disadvantages of each neural network are discussed and guidelines for selecting the best-suited neural network in channel prediction applications are given.

Deep learning-based disease diagnosis applications are essential for accurate diagnosis at various disease stages. However, using personal data exposes traditional centralized learning systems to privacy concerns. On the other hand, by positioning processing resources closer to the device and enabling more effective data analyses, a distributed computing paradigm has the potential to revolutionize disease diagnosis. Scalable architectures for data analytics are also crucial in healthcare, where data analytics results must have low latency and high dependability and reliability. This study proposes a microservices-based approach for IoT data analytics systems to satisfy privacy and performance requirements by arranging entities into fine-grained, loosely connected, and reusable collections. Our approach relies on federated learning, which can increase disease diagnosis accuracy while protecting data privacy. Additionally, we employ transfer learning to obtain more efficient models. Using more than 5800 chest X-ray images for pneumonia detection from a publicly available dataset, we ran experiments to assess the effectiveness of our approach. Our experiments reveal that our approach performs better in identifying pneumonia than other cutting-edge technologies, demonstrating our approach's promising potential detection performance.

Evolutionary algorithms (EA), a class of stochastic search methods based on the principles of natural evolution, have received widespread acclaim for their exceptional performance in various real-world optimization problems. While researchers worldwide have proposed a wide variety of EAs, certain limitations remain, such as slow convergence speed and poor generalization capabilities. Consequently, numerous scholars actively explore improvements to algorithmic structures, operators, search patterns, etc., to enhance their optimization performance. Reinforcement learning (RL) integrated as a component in the EA framework has demonstrated superior performance in recent years. This paper presents a comprehensive survey on integrating reinforcement learning into the evolutionary algorithm, referred to as reinforcement learning-assisted evolutionary algorithm (RL-EA). We begin with the conceptual outlines of reinforcement learning and the evolutionary algorithm. We then provide a taxonomy of RL-EA. Subsequently, we discuss the RL-EA integration method, the RL-assisted strategy adopted by RL-EA, and its applications according to the existing literature. The RL-assisted procedure is divided according to the implemented functions including solution generation, learnable objective function, algorithm/operator/sub-population selection, parameter adaptation, and other strategies. Finally, we analyze potential directions for future research. This survey serves as a rich resource for researchers interested in RL-EA as it overviews the current state-of-the-art and highlights the associated challenges. By leveraging this survey, readers can swiftly gain insights into RL-EA to develop efficient algorithms, thereby fostering further advancements in this emerging field.

This article provides a comprehensive synthesis of the recent developments in synthetic data generation via deep generative models, focusing on tabular datasets. We specifically outline the importance of synthetic data generation in the context of privacy-sensitive data. Additionally, we highlight the advantages of using deep generative models over other methods and provide a detailed explanation of the underlying concepts, including unsupervised learning, neural networks, and generative models. The paper covers the challenges and considerations involved in using deep generative models for tabular datasets, such as data normalization, privacy concerns, and model evaluation. This review provides a valuable resource for researchers and practitioners interested in synthetic data generation and its applications.

In our pursuit of advancing multi-modal AI assistants capable of guiding users to achieve complex multi-step goals, we propose the task of "Visual Planning for Assistance (VPA)". Given a succinct natural language goal, e.g., "make a shelf", and a video of the user's progress so far, the aim of VPA is to devise a plan, i.e., a sequence of actions such as "sand shelf", "paint shelf", etc. to realize the specified goal. This requires assessing the user's progress from the (untrimmed) video, and relating it to the requirements of natural language goal, i.e., which actions to select and in what order? Consequently, this requires handling long video history and arbitrarily complex action dependencies. To address these challenges, we decompose VPA into video action segmentation and forecasting. Importantly, we experiment by formulating the forecasting step as a multi-modal sequence modeling problem, allowing us to leverage the strength of pre-trained LMs (as the sequence model). This novel approach, which we call Visual Language Model based Planner (VLaMP), outperforms baselines across a suite of metrics that gauge the quality of the generated plans. Furthermore, through comprehensive ablations, we also isolate the value of each component--language pre-training, visual observations, and goal information. We have open-sourced all the data, model checkpoints, and training code.

Over the past decade, deep learning models have exhibited considerable advancements, reaching or even exceeding human-level performance in a range of visual perception tasks. This remarkable progress has sparked interest in applying deep networks to real-world applications, such as autonomous vehicles, mobile devices, robotics, and edge computing. However, the challenge remains that state-of-the-art models usually demand significant computational resources, leading to impractical power consumption, latency, or carbon emissions in real-world scenarios. This trade-off between effectiveness and efficiency has catalyzed the emergence of a new research focus: computationally efficient deep learning, which strives to achieve satisfactory performance while minimizing the computational cost during inference. This review offers an extensive analysis of this rapidly evolving field by examining four key areas: 1) the development of static or dynamic light-weighted backbone models for the efficient extraction of discriminative deep representations; 2) the specialized network architectures or algorithms tailored for specific computer vision tasks; 3) the techniques employed for compressing deep learning models; and 4) the strategies for deploying efficient deep networks on hardware platforms. Additionally, we provide a systematic discussion on the critical challenges faced in this domain, such as network architecture design, training schemes, practical efficiency, and more realistic model compression approaches, as well as potential future research directions.

This thesis enhances the autonomy of the M4 (Multi-Modal Mobility Morphobot) robot, designed for Mars and rescue missions. The research enables the robot to autonomously select its locomotion mode and path in complex terrains. Focusing on walking and flying modes, a Gazebo simulation, and custom perception-navigations pipelines are developed. Leveraging deep learning, the robot determines optimal mode transitions based on a 2.5D map. Additionally, an energy efficient path planner based on 2.5D mapping is implemented and validated in simulations. The contributions demonstrate scalability for future mode integrations. The M4 robot showcases intelligent mode switching, efficient navigation, and reduced energy consumption, bringing us closer to fully autonomous multi-modal robots for exploration and rescue missions. This work paves the way for future advancements in autonomous robotics, with the ultimate vision of deploying the M4 robot for exploration and rescue tasks, making a significant impact in the quest for intelligent and versatile robotic systems.

One of the topics in machine learning that is becoming more and more relevant is multivariate time series classification. Current techniques concentrate on identifying the local important sequence segments or establishing the global long-range dependencies. They frequently disregard the merged data from both global and local features, though. Using dual attention, we explore a novel network (DA-Net) in this research to extract local and global features for multivariate time series classification. The two distinct layers that make up DA-Net are the Squeeze-Excitation Window Attention (SEWA) layer and the Sparse Self-Attention within Windows (SSAW) layer. DA- Net can mine essential local sequence fragments that are necessary for establishing global long-range dependencies based on the two expanded layers.

Computer vision and machine learning have brought revolutionary shifts in perception for researchers, scientists, and the general populace. Once thought to be unattainable, these technologies have achieved the seemingly impossible. Their exceptional applications in diverse fields like security, agriculture, and education are a testament to their impact. However, the full potential of computer vision remains untapped. This paper explores computer vision's potential in security and surveillance, presenting a novel approach to track motion in videos. By categorizing motion into Arcs, Lanes, Converging/Diverging, and Random/Block motions using Motion Information Images and Blockwise dominant motion data, the paper examines different optical flow techniques, CNN models, and machine learning models. Successfully achieving its objectives with promising accuracy, the results can train anomaly-detection models, provide behavioral insights based on motion, and enhance scene comprehension.

Memory is identified as a crucial human faculty that allows for the retention of visual and linguistic information within the hippocampus and neurons in the brain, which can subsequently be retrieved to address real-world challenges that arise through a lifetime of learning. The resolution of complex AI tasks through the application of acquired knowledge represents a stride toward the realization of artificial general intelligence. However, despite the prevalence of Large Language Models (LLMs) like GPT-3.5 and GPT-4 \cite{brown2020language, leiter2023chatgpt, zaitsu2023distinguishing, OpenAI2023GPT4TR} , which have displayed remarkable capabilities in language comprehension, generation, interaction, and reasoning, they are inhibited by constraints on context length that preclude the processing of extensive, continually evolving knowledge bases. This paper proposes that LLMs could be augmented through the selective integration of knowledge from external repositories, and in doing so, introduces a novel methodology for External Reasoning, exemplified by ChatPDF. Central to this approach is the establishment of a tiered policy for \textbf{External Reasoning based on Multiple LLM Interchange Assistance} in \cref{fig:overall}, where the level of support rendered is modulated across entry, intermediate, and advanced tiers based on the complexity of the query, with adjustments made in response to human feedback. A comprehensive evaluation of this methodology is conducted using multiple LLMs and the results indicate state-of-the-art performance in \cref{comparison} , surpassing existing solutions including ChatPDF.com. Moreover, the paper emphasizes that this approach is more efficient compared to the direct processing of full text by LLMs. The source code is publicly available at: \url{https://github.com/AkideLiu/ANLP}.