Generative AI and transfer learning fields have experienced remarkable advancements in recent years especially in the domain of Natural Language Processing (NLP). Transformers were at the heart of these advancements where the cutting-edge transformer-based Language Models (LMs) enabled new state-of-the-art results in a wide spectrum of applications. While the number of research works involving neural LMs is exponentially increasing, their vast majority are high-level and far from self-contained. Consequently, a deep understanding of the literature in this area is a tough task especially at the absence of a unified mathematical framework explaining the main types of neural LMs. We address the aforementioned problem in this tutorial where the objective is to explain neural LMs in a detailed, simplified and unambiguous mathematical framework accompanied with clear graphical illustrations. Concrete examples on widely used models like BERT and GPT2 are explored. Finally, since transformers pretrained on language-modeling-like tasks have been widely adopted in computer vision and time series applications, we briefly explore some examples of such solutions in order to enable readers understand how transformers work in the aforementioned domains and compare this use with the original one in NLP.

In the dynamic and data-driven landscape of financial markets, this paper introduces MarketSenseAI, a novel AI-driven framework leveraging the advanced reasoning capabilities of GPT-4 for scalable stock selection. MarketSenseAI incorporates Chain of Thought and In-Context Learning methodologies to analyze a wide array of data sources, including market price dynamics, financial news, company fundamentals, and macroeconomic reports emulating the decision making process of prominent financial investment teams. The development, implementation, and empirical validation of MarketSenseAI are detailed, with a focus on its ability to provide actionable investment signals (buy, hold, sell) backed by cogent explanations. A notable aspect of this study is the use of GPT-4 not only as a predictive tool but also as an evaluator, revealing the significant impact of the AI-generated explanations on the reliability and acceptance of the suggested investment signals. In an extensive empirical evaluation with S&P 100 stocks, MarketSenseAI outperformed the benchmark index by 13%, achieving returns up to 40%, while maintaining a risk profile comparable to the market. These results demonstrate the efficacy of Large Language Models in complex financial decision-making and mark a significant advancement in the integration of AI into financial analysis and investment strategies. This research contributes to the financial AI field, presenting an innovative approach and underscoring the transformative potential of AI in revolutionizing traditional financial analysis investment methodologies.

Thyroid cancer, the most prevalent endocrine cancer, has gained significant global attention due to its impact on public health. Extensive research efforts have been dedicated to leveraging artificial intelligence (AI) methods for the early detection of this disease, aiming to reduce its morbidity rates. However, a comprehensive understanding of the structured organization of research applications in this particular field remains elusive. To address this knowledge gap, we conducted a systematic review and developed a comprehensive taxonomy of machine learning-based applications in thyroid cancer pathogenesis, diagnosis, and prognosis. Our primary objective was to facilitate the research community's ability to stay abreast of technological advancements and potentially lead the emerging trends in this field. This survey presents a coherent literature review framework for interpreting the advanced techniques used in thyroid cancer research. A total of 758 related studies were identified and scrutinized. To the best of our knowledge, this is the first review that provides an in-depth analysis of the various aspects of AI applications employed in the context of thyroid cancer. Furthermore, we highlight key challenges encountered in this domain and propose future research opportunities for those interested in studying the latest trends or exploring less-investigated aspects of thyroid cancer research. By presenting this comprehensive review and taxonomy, we contribute to the existing knowledge in the field, while providing valuable insights for researchers, clinicians, and stakeholders in advancing the understanding and management of this disease.

Time-series data exists in every corner of real-world systems and services, ranging from satellites in the sky to wearable devices on human bodies. Learning representations by extracting and inferring valuable information from these time series is crucial for understanding the complex dynamics of particular phenomena and enabling informed decisions. With the learned representations, we can perform numerous downstream analyses more effectively. Among several approaches, deep learning has demonstrated remarkable performance in extracting hidden patterns and features from time-series data without manual feature engineering. This survey first presents a novel taxonomy based on three fundamental elements in designing state-of-the-art universal representation learning methods for time series. According to the proposed taxonomy, we comprehensively review existing studies and discuss their intuitions and insights into how these methods enhance the quality of learned representations. Finally, as a guideline for future studies, we summarize commonly used experimental setups and datasets and discuss several promising research directions. An up-to-date corresponding resource is available at https://github.com/itouchz/awesome-deep-time-series-representations.

Large Language Models (LLMs) have demonstrated considerable proficiency in general natural language processing (NLP) tasks. Instruction tuning, a successful paradigm, enhances the ability of LLMs to follow natural language instructions and exhibit robust generalization across a wide range of tasks. However, these models often encounter performance limitations across multiple tasks due to constrained model capacity. Expanding this capacity during the instruction tuning phase poses significant challenges. To address this issue, we introduce a novel approach, Parameter-Efficient Sparsity Crafting (PESC), which transitions dense models to sparse models using a Mixture of Experts (MoE) architecture. PESC integrates adapters into the MoE layers of sparse models, differentiating experts without altering the individual weights within these layers. This method significantly reduces computational costs and GPU memory requirements, facilitating model capacity expansion through a minimal increase in parameters via the inserted adapters. Our empirical evaluation demonstrates the effectiveness of the PESC method. Using PESC during instruction tuning, our sparse models, dubbed Camelidae outperform all other opensource sparse models and exhibit superior general capabilities compared to GPT3.5.

As Large Language Models (LLMs) continue to advance in their ability to write human-like text, a key challenge remains around their tendency to hallucinate generating content that appears factual but is ungrounded. This issue of hallucination is arguably the biggest hindrance to safely deploying these powerful LLMs into real-world production systems that impact people's lives. The journey toward widespread adoption of LLMs in practical settings heavily relies on addressing and mitigating hallucinations. Unlike traditional AI systems focused on limited tasks, LLMs have been exposed to vast amounts of online text data during training. While this allows them to display impressive language fluency, it also means they are capable of extrapolating information from the biases in training data, misinterpreting ambiguous prompts, or modifying the information to align superficially with the input. This becomes hugely alarming when we rely on language generation capabilities for sensitive applications, such as summarizing medical records, financial analysis reports, etc. This paper presents a comprehensive survey of over 32 techniques developed to mitigate hallucination in LLMs. Notable among these are Retrieval Augmented Generation (Lewis et al, 2021), Knowledge Retrieval (Varshney et al,2023), CoNLI (Lei et al, 2023), and CoVe (Dhuliawala et al, 2023). Furthermore, we introduce a detailed taxonomy categorizing these methods based on various parameters, such as dataset utilization, common tasks, feedback mechanisms, and retriever types. This classification helps distinguish the diverse approaches specifically designed to tackle hallucination issues in LLMs. Additionally, we analyze the challenges and limitations inherent in these techniques, providing a solid foundation for future research in addressing hallucinations and related phenomena within the realm of LLMs.

With the rapid development of machine learning and a growing concern for data privacy, federated learning has become a focal point of attention. However, attacks on model parameters and a lack of incentive mechanisms hinder the effectiveness of federated learning. Therefore, we propose A Privacy Protected Blockchain-based Federated Learning Model (PPBFL) to enhance the security of federated learning and encourage active participation of nodes in model training. Blockchain technology ensures the integrity of model parameters stored in the InterPlanetary File System (IPFS), providing protection against tampering. Within the blockchain, we introduce a Proof of Training Work (PoTW) consensus algorithm tailored for federated learning, aiming to incentive training nodes. This algorithm rewards nodes with greater computational power, promoting increased participation and effort in the federated learning process. A novel adaptive differential privacy algorithm is simultaneously applied to local and global models. This safeguards the privacy of local data at training clients, preventing malicious nodes from launching inference attacks. Additionally, it enhances the security of the global model, preventing potential security degradation resulting from the combination of numerous local models. The possibility of security degradation is derived from the composition theorem. By introducing reverse noise in the global model, a zero-bias estimate of differential privacy noise between local and global models is achieved. Furthermore, we propose a new mix transactions mechanism utilizing ring signature technology to better protect the identity privacy of local training clients. Security analysis and experimental results demonstrate that PPBFL, compared to baseline methods, not only exhibits superior model performance but also achieves higher security.

The prominent large language models (LLMs) of today differ from past language models not only in size, but also in the fact that they are trained on a combination of natural language and formal language (code). As a medium between humans and computers, code translates high-level goals into executable steps, featuring standard syntax, logical consistency, abstraction, and modularity. In this survey, we present an overview of the various benefits of integrating code into LLMs' training data. Specifically, beyond enhancing LLMs in code generation, we observe that these unique properties of code help (i) unlock the reasoning ability of LLMs, enabling their applications to a range of more complex natural language tasks; (ii) steer LLMs to produce structured and precise intermediate steps, which can then be connected to external execution ends through function calls; and (iii) take advantage of code compilation and execution environment, which also provides diverse feedback for model improvement. In addition, we trace how these profound capabilities of LLMs, brought by code, have led to their emergence as intelligent agents (IAs) in situations where the ability to understand instructions, decompose goals, plan and execute actions, and refine from feedback are crucial to their success on downstream tasks. Finally, we present several key challenges and future directions of empowering LLMs with code.

Driving Automation Systems (DAS) are subject to complex road environments and vehicle behaviors and increasingly rely on sophisticated sensors and Artificial Intelligence (AI). These properties give rise to unique safety faults stemming from specification insufficiencies and technological performance limitations, where sensors and AI introduce errors that vary in magnitude and temporal patterns, posing potential safety risks. The Safety of the Intended Functionality (SOTIF) standard emerges as a promising framework for addressing these concerns, focusing on scenario-based analysis to identify hazardous behaviors and their causes. Although the current standard provides a basic cause-and-effect model and high-level process guidance, it lacks concepts required to identify and evaluate hazardous errors, especially within the context of AI. This paper introduces two key contributions to bridge this gap. First, it defines the SOTIF Temporal Error and Failure Model (STEAM) as a refinement of the SOTIF cause-and-effect model, offering a comprehensive system-design perspective. STEAM refines error definitions, introduces error sequences, and classifies them as error sequence patterns, providing particular relevance to systems employing advanced sensors and AI. Second, this paper proposes the Model-based SOTIF Analysis of Failures and Errors (MoSAFE) method, which allows instantiating STEAM based on system-design models by deriving hazardous error sequence patterns at module level from hazardous behaviors at vehicle level via weakest precondition reasoning. Finally, the paper presents a case study centered on an automated speed-control feature, illustrating the practical applicability of the refined model and the MoSAFE method in addressing complex safety challenges in DAS.

In recent years, multi-objective optimization (MOO) emerges as a foundational problem underpinning many multi-agent multi-task learning applications. However, existing algorithms in MOO literature remain limited to centralized learning settings, which do not satisfy the distributed nature and data privacy needs of such multi-agent multi-task learning applications. This motivates us to propose a new federated multi-objective learning (FMOL) framework with multiple clients distributively and collaboratively solving an MOO problem while keeping their training data private. Notably, our FMOL framework allows a different set of objective functions across different clients to support a wide range of applications, which advances and generalizes the MOO formulation to the federated learning paradigm for the first time. For this FMOL framework, we propose two new federated multi-objective optimization (FMOO) algorithms called federated multi-gradient descent averaging (FMGDA) and federated stochastic multi-gradient descent averaging (FSMGDA). Both algorithms allow local updates to significantly reduce communication costs, while achieving the {\em same} convergence rates as those of their algorithmic counterparts in the single-objective federated learning. Our extensive experiments also corroborate the efficacy of our proposed FMOO algorithms.