Large language model-based artificial conversational agents (like ChatGPT) give answers to all kinds of questions, and often enough these answers are correct. Just on the basis of that capacity alone, we may attribute knowledge to them. But do these models use this knowledge as a basis for their own conversational behaviour? I argue this is not the case, and I will refer to this failure as a `disconnect'. I further argue this disconnect is fundamental in the sense that with more data and more training of the LLM on which a conversational chatbot is based, it will not disappear. The reason is, as I will claim, that the core technique used to train LLMs does not allow for the establishment of the connection we are after. The disconnect reflects a fundamental limitation on the capacities of LLMs, and explains the source of hallucinations. I will furthermore consider the ethical version of the disconnect (ethical conversational knowledge not being aligned with ethical conversational behaviour), since in this domain researchers have come up with several additional techniques to influence a chatbot's behaviour. I will discuss how these techniques do nothing to solve the disconnect and can make it worse.

Fault diagnosis of mechanical equipment involves data collection, feature extraction, and pattern recognition but is often hindered by the imbalanced nature of industrial data, introducing significant uncertainty and reducing diagnostic reliability. To address these challenges, this study proposes the Uncertainty-Aware Bayesian Meta-Learning Framework (UBMF), which integrates four key modules: data perturbation injection for enhancing feature robustness, cross-task self-supervised feature extraction for improving transferability, uncertainty-based sample filtering for robust out-of-domain generalization, and Bayesian meta-knowledge integration for fine-grained classification. Experimental results on ten open-source datasets under various imbalanced conditions, including cross-task, small-sample, and unseen-sample scenarios, demonstrate the superiority of UBMF, achieving an average improvement of 42.22% across ten Any-way 1-5-shot diagnostic tasks. This integrated framework effectively enhances diagnostic accuracy, generalization, and adaptability, providing a reliable solution for complex industrial fault diagnosis.

Ensuring data quality in large tabular datasets is a critical challenge, typically addressed through data wrangling tasks. Traditional statistical methods, though efficient, cannot often understand the semantic context and deep learning approaches are resource-intensive, requiring task and dataset-specific training. To overcome these shortcomings, we present an automated system that utilizes large language models to generate executable code for tasks like missing value imputation, error detection, and error correction. Our system aims to identify inherent patterns in the data while leveraging external knowledge, effectively addressing both memory-dependent and memory-independent tasks.

Recent progress in Learning by Reading and Machine Reading systems has significantly increased the capacity of knowledge-based systems to learn new facts. In this work, we discuss the problem of selecting a set of learning requests for these knowledge-based systems which would lead to maximum Q/A performance. To understand the dynamics of this problem, we simulate the properties of a learning strategy, which sends learning requests to an external knowledge source. We show that choosing an optimal set of facts for these learning systems is similar to a coordination game, and use reinforcement learning to solve this problem. Experiments show that such an approach can significantly improve Q/A performance.

The development of generative large language models (G-LLM) opened up new opportunities for the development of new types of knowledge-based systems similar to ChatGPT, Bing, or Gemini. Fine-tuning (FN) and Retrieval-Augmented Generation (RAG) are the techniques that can be used to implement domain adaptation for the development of G-LLM-based knowledge systems. In our study, using ROUGE, BLEU, METEOR scores, and cosine similarity, we compare and examine the performance of RAG and FN for the GPT-J-6B, OPT-6.7B, LlaMA, LlaMA-2 language models. Based on measurements shown on different datasets, we demonstrate that RAG-based constructions are more efficient than models produced with FN. We point out that connecting RAG and FN is not trivial, because connecting FN models with RAG can cause a decrease in performance. Furthermore, we outline a simple RAG-based architecture which, on average, outperforms the FN models by 16% in terms of the ROGUE score, 15% in the case of the BLEU score, and 53% based on the cosine similarity. This shows the significant advantage of RAG over FN in terms of hallucination, which is not offset by the fact that the average 8% better METEOR score of FN models indicates greater creativity compared to RAG.

In this paper, we propose a fuzzy adaptive loss function for enhancing deep learning performance in classification tasks. Specifically, we redefine the cross-entropy loss to effectively address class-level noise conditions, including the challenging problem of class imbalance. Our approach introduces aggregation operators, leveraging the power of fuzzy logic to improve classification accuracy. The rationale behind our proposed method lies in the iterative up-weighting of class-level components within the loss function, focusing on those with larger errors. To achieve this, we employ the ordered weighted average (OWA) operator and combine it with an adaptive scheme for gradient-based learning. Through extensive experimentation, our method outperforms other commonly used loss functions, such as the standard cross-entropy or focal loss, across various binary and multiclass classification tasks. Furthermore, we explore the influence of hyperparameters associated with the OWA operators and present a default configuration that performs well across different experimental settings.

Peng Zhao Abstract In order to cope with the task allocation in national economic mobilization, a task allocation planning method based on Hierarchical Task Network (HTN) for national economic mobilization is proposed. An HTN planning algorithm is designed to solve and optimize task allocation, and a method is explored to deal with the resource shortage. Finally, based on a real task allocation case in national economic mobilization, an experimental study verifies the effectiveness of the proposed method.

AI Researcher, Cognitive Technologist Inventor - AI Thinking, Think Chain Innovator - AIOT, XAI, Autonomous Cars, IIOT Founder Fisheyebox Spatial Computing Savant, Transformative Leader, Industry X.0 Practitioner What's the difference between a knowledge based system and an expert system? KBS/ES Knowledge Bases Automated reasoning engines (Inference engines, theorem provers, classifiers), - "expert system" refers to the type of task the system is trying to assist with – to replace or aid a human expert in a complex task requiring expert knowledge; - "knowledge-based system" refers to the architecture of the system – that it represents knowledge explicitly, rather than as procedural code; While the earliest knowledge-based systems were almost all expert systems, the same tools and architectures can and have since been used for a whole host of other types of systems. Virtually all expert systems are knowledge-based systems, but many knowledge-based systems are not expert systems. Expert systems is going as a computer system emulating the decision-making ability of a human expert, solve complex problems by reasoning through bodies of knowledge, represented mainly as if-then rules rather than through conventional procedural code. The knowledge base represents facts and rules about the world, via KRR formalisms, as ontologies, frames, conceptual graphs or logical assertions.

The most completed list of Artificial Intelligence terms as a dictionary is here for you. Artificial intelligence is already all around us. As AI becomes increasingly prevalent in the workplace, it's more important than ever to keep up with the newest words and use types. Leaders in the field of artificial intelligence are well aware that it is revolutionizing business. So, how much do you know about it? You'll discover concise definitions for automation tools and phrases below. It's no surprise that the world is moving ahead quickly thanks to artificial intelligence's wonders. Technology has introduced new values and creativity to our personal and professional lives. While frightening at times, the rapid evolution has been complemented by artificial intelligence (AI) technology with new aspects. It has provided us with new phrases to add to our everyday vocab that we have never heard of before.

MetaShare is a knowledge-based system that supports the creation of data management plans and provides the functionality to support researchers as they implement those plans. MetaShare is a community-based, user-driven system that is being designed around the parallels of the scientific data life cycle and the development cycle of knowledge-based systems. MetaShare will provide recommendations and guidance to researchers based on the practices and decisions of similar projects. Using formal knowledge representation in the form of ontologies and rules, the system will be able to generate data collection, dissemination, and management tools to facilitate tasks with respect to using and sharing scientific data. MetaShare, which is initially targeting the research community at the University of Texas at El Paso, is being developed on a Web platform, using Semantic Web technologies. This paper presents a roadmap for the development of MetaShare, justifying the functionality and implementation decisions. In addition, the paper presents an argument concerning the return on investment for researchers and the planned evaluation for the system.