Deep Learning models have experienced exponential growth in complexity and resource demands in recent years. Accelerating these models for efficient execution on resource-constrained devices has become more crucial than ever. Two notable techniques employed to achieve this goal are Hardware-aware Neural Architecture Search (HW-NAS) and Automatic Code Optimization (ACO). HW-NAS automatically designs accurate yet hardware-friendly neural networks, while ACO involves searching for the best compiler optimizations to apply on neural networks for efficient mapping and inference on the target hardware. This survey explores recent works that combine these two techniques within a single framework. We present the fundamental principles of both domains and demonstrate their sub-optimality when performed independently. We then investigate their integration into a joint optimization process that we call Hardware Aware-Neural Architecture and Compiler Optimizations co-Search (NACOS).

Background: The accuracy of spelling in Electronic Health Records (EHRs) is a critical factor for efficient clinical care, research, and ensuring patient safety. The Persian language, with its abundant vocabulary and complex characteristics, poses unique challenges for real-word error correction. This research aimed to develop an innovative approach for detecting and correcting spelling errors in Persian clinical text. Methods: Our strategy employs a state-of-the-art pre-trained model that has been meticulously fine-tuned specifically for the task of spelling correction in the Persian clinical domain. This model is complemented by an innovative orthographic similarity matching algorithm, PERTO, which uses visual similarity of characters for ranking correction candidates. Results: The evaluation of our approach demonstrated its robustness and precision in detecting and rectifying word errors in Persian clinical text. In terms of non-word error correction, our model achieved an F1-Score of 90.0% when the PERTO algorithm was employed. For real-word error detection, our model demonstrated its highest performance, achieving an F1-Score of 90.6%. Furthermore, the model reached its highest F1-Score of 91.5% for real-word error correction when the PERTO algorithm was employed. Conclusions: Despite certain limitations, our method represents a substantial advancement in the field of spelling error detection and correction for Persian clinical text. By effectively addressing the unique challenges posed by the Persian language, our approach paves the way for more accurate and efficient clinical documentation, contributing to improved patient care and safety. Future research could explore its use in other areas of the Persian medical domain, enhancing its impact and utility.

Bayesian Last Layer (BLL) models focus solely on uncertainty in the output layer of neural networks, demonstrating comparable performance to more complex Bayesian models. However, the use of Gaussian priors for last layer weights in Bayesian Last Layer (BLL) models limits their expressive capacity when faced with non-Gaussian, outlier-rich, or high-dimensional datasets. To address this shortfall, we introduce a novel approach that combines diffusion techniques and implicit priors for variational learning of Bayesian last layer weights. This method leverages implicit distributions for modeling weight priors in BLL, coupled with diffusion samplers for approximating true posterior predictions, thereby establishing a comprehensive Bayesian prior and posterior estimation strategy. By delivering an explicit and computationally efficient variational lower bound, our method aims to augment the expressive abilities of BLL models, enhancing model accuracy, calibration, and out-of-distribution detection proficiency. Through detailed exploration and experimental validation, We showcase the method's potential for improving predictive accuracy and uncertainty quantification while ensuring computational efficiency.

This paper introduces a novel approach Counterfactual Shapley Values (CSV), which enhances explainability in reinforcement learning (RL) by integrating counterfactual analysis with Shapley Values. The approach aims to quantify and compare the contributions of different state dimensions to various action choices. To more accurately analyze these impacts, we introduce new characteristic value functions, the ``Counterfactual Difference Characteristic Value" and the ``Average Counterfactual Difference Characteristic Value." These functions help calculate the Shapley values to evaluate the differences in contributions between optimal and non-optimal actions. Experiments across several RL domains, such as GridWorld, FrozenLake, and Taxi, demonstrate the effectiveness of the CSV method. The results show that this method not only improves transparency in complex RL systems but also quantifies the differences across various decisions.

Diffusion models (DMs) have achieved state-of-the-art performance on various generative tasks such as image synthesis, text-to-image, and text-guided image-to-image generation. However, the more powerful the DMs, the more harmful they potentially are. Recent studies have shown that DMs are prone to a wide range of attacks, including adversarial attacks, membership inference, backdoor injection, and various multi-modal threats. Since numerous pre-trained DMs are published widely on the Internet, potential threats from these attacks are especially detrimental to the society, making DM-related security a worth investigating topic. Therefore, in this paper, we conduct a comprehensive survey on the security aspect of DMs, focusing on various attack and defense methods for DMs. First, we present crucial knowledge of DMs with five main types of DMs, including denoising diffusion probabilistic models, denoising diffusion implicit models, noise conditioned score networks, stochastic differential equations, and multi-modal conditional DMs. We further survey a variety of recent studies investigating different types of attacks that exploit the vulnerabilities of DMs. Then, we thoroughly review potential countermeasures to mitigate each of the presented threats. Finally, we discuss open challenges of DM-related security and envision certain research directions for this topic.

Large language models are ubiquitous in natural language processing because they can adapt to new tasks without retraining. However, their sheer scale and complexity present unique challenges and opportunities, prompting researchers and practitioners to explore novel model training, optimization, and deployment methods. This literature review focuses on various techniques for reducing resource requirements and compressing large language models, including quantization, pruning, knowledge distillation, and architectural optimizations. The primary objective is to explore each method in-depth and highlight its unique challenges and practical applications. The discussed methods are categorized into a taxonomy that presents an overview of the optimization landscape and helps navigate it to understand the research trajectory better.

This study explores the integration of real-world machine learning (ML) projects using human-computer interfaces (HCI) datasets in college-level courses to enhance both teaching and learning experiences. Employing a comprehensive literature review, course websites analysis, and a detailed case study, the research identifies best practices for incorporating HCI datasets into project-based ML education. Key findings demonstrate increased student engagement, motivation, and skill development through hands-on projects, while instructors benefit from effective tools for teaching complex concepts. The study also addresses challenges such as data complexity and resource allocation, offering recommendations for future improvements. These insights provide a valuable framework for educators aiming to bridge the gap between theoretical knowledge and practical application in ML education.

We give a nonexhaustive Within the landscape of linguistic capabilities that overview of the phenomena of those two have been studied and analyzed in Large Language subdomains and the methods traditionally used to Models (LLMs), a considerable amount of research analyze them. We subsequently consider the resulting has focused on phenomena on the level of morphology heterogeneous set of phenomena and methods and syntax (Marvin and Linzen, 2018; as a starting point for our survey of work on discourse Hu et al., 2020). Here, the community seems to pragmatics and interactional pragmatics in have agreed on benchmarks and phenomena that an the context of LLMs. LLM should be capable of (e.g.

Artificial Intelligence (AI) technologies have profoundly transformed the field of remote sensing, revolutionizing data collection, processing, and analysis. Traditionally reliant on manual interpretation and task-specific models, remote sensing has been significantly enhanced by the advent of foundation models--large-scale, pre-trained AI models capable of performing a wide array of tasks with unprecedented accuracy and efficiency. This paper provides a comprehensive survey of foundation models in the remote sensing domain, covering models released between June 2021 and June 2024. We categorize these models based on their applications in computer vision and domain-specific tasks, offering insights into their architectures, pre-training datasets, and methodologies. Through detailed performance comparisons, we highlight emerging trends and the significant advancements achieved by these foundation models. Additionally, we discuss the technical challenges, practical implications, and future research directions, addressing the need for high-quality data, computational resources, and improved model generalization. Our research also finds that pre-training methods, particularly self-supervised learning techniques like contrastive learning and masked autoencoders, significantly enhance the performance and robustness of foundation models in remote sensing tasks such as scene classification, object detection, and other applications. This survey aims to serve as a resource for researchers and practitioners by providing a panorama of advances and promising pathways for continued development and application of foundation models in remote sensing.

Machine learning (ML) has revolutionized medical prognostics by integrating advanced algorithms with clinical data to enhance disease prediction, risk assessment, and patient outcome forecasting. This comprehensive review critically examines the application of various ML techniques in medical prognostics, focusing on their efficacy, challenges, and future directions. The methodologies discussed include Random Forest (RF) for sepsis prediction, logistic regression for cardiovascular risk assessment, Convolutional Neural Networks (CNNs) for cancer detection, and Long Short-Term Memory (LSTM) networks for predicting clinical deterioration. RF models demonstrate robust performance in handling high-dimensional data and capturing non-linear relationships, making them particularly effective for sepsis prediction. Logistic regression remains valuable for its interpretability and ease of use in cardiovascular risk assessment. CNNs have shown exceptional accuracy in cancer detection, leveraging their ability to learn complex visual patterns from medical imaging. LSTM networks excel in analyzing temporal data, providing accurate predictions of clinical deterioration. The review highlights the strengths and limitations of each technique, the importance of model interpretability, and the challenges of data quality and privacy. Future research directions include the integration of multi-modal data sources, the application of transfer learning, and the development of continuous learning systems. These advancements aim to enhance the predictive power and clinical applicability of ML models, ultimately improving patient outcomes in healthcare settings.