T. Takagi

Bio: T. Takagi is an academic researcher from Tokyo Institute of Technology. The author has contributed to research in topics: Computer science & Fuzzy classification. The author has an hindex of 1, co-authored 1 publications receiving 17632 citations.

Fuzzy identification of systems and its applications to modeling and control

Abstract: A mathematical tool to build a fuzzy model of a system where fuzzy implications and reasoning are used is presented. The premise of an implication is the description of fuzzy subspace of inputs and its consequence is a linear input-output relation. The method of identification of a system using its input-output data is then shown. Two applications of the method to industrial processes are also discussed: a water cleaning process and a converter in a steel-making process.

Personalized Fashion Sequential Recommendation with Visual Feature Based on Conditional Hierarchical VAE

Abstract: With the increase of online shopping services, there has been much research on fashion item recommendation. Unlike standard recommendation systems, a recommendation for fashion items needs to take into account the context of the item IDs in the user behavior and that of the fashion-specific visual features such as color and design. In this study, we propose the conditional hierarchical variational auto-encoder (CHVAE) for extracting fashion-specific visual features, and construct a fashion item recommendation system based on it. CHVAE is an extension of VAE to enable conditional and hierarchical learning. It can capture the continuous latent space of color and design using item images and labels, and extract visual features for fashion recommendations. In our experiments, we show that the proposed method outperforms an extensive list of state-of-the-art sequential recommendation models and achieves the same or better performance as human stylists.

Conceptual Attention in StyleGAN

Abstract: Attention is an important function in human cognition. Since the human brain can only process a limited amount of information at a time, attention selects and focuses on just the important information among all the perceived information. Recent years have seen the advent of methods that imitate the human attention mechanism by means of deep learning, one of which is the multi-head attention proposed for Transformer. Humans can consider a single object from multiple perspectives, so multi-head attention linearly maps the input to multiple latent spaces and computes the attention for each of them. However, when humans pay attention to a single object from various aspects, there is an explicit context in the brain (e.g., a concept), which they pay attention to and accordingly perceive in a top-down manner—and multi-head attention cannot do this. We have therefore developed Conceptual Attention (CA), which can more explicitly compute the attention for each concept. The aim of CA is to achieve the same concept-by-concept attentional mechanism as the human brain by using style vectors learned by StyleGAN as concepts. Our experiments demonstrate that introducing CA into the StyleGAN2 discriminator and then fine-tuning it improves the quality of the generated images for large, small, and noisy data. We also visualize the results of attention to show that the proposed method can capture the concepts and qualitatively clarify how the concepts are reflected in the generated images.

Exploratory Inference Chain: Exploratorily Chaining Multi-hop Inferences with Large Language Models for Question-Answering

Abstract: Successful few-shot question-answering with large language models (LLMs) has been reported for a variety of tasks. In the usual approach, an answer is generated by a single call to an LLM, but it has been pointed out that the performance of multi-hop inference by LLMs is not sufficient. Thus, an LLM is unable to perform the complex processing necessary to get an answer, which leads to poor performance. Moreover, the inference process is opaque. Against this, approaches that call an LLM multiple times have been proposed, but many of these approaches can only be used for a limited number of effective tasks, and LLMs essentially require complex processing.To address these problems, we propose the Exploratory Inference Chain (EIC) framework that combines the implicit processing of LLMs with explicit inference chains, and this is based on the dual process theory of human cognitive processes. The EIC framework first generates the information needed to answer a multi-hop question as keywords and then performs 1-hop inference for each keyword. If the inference is not sufficient, additional inferences are performed. This process is repeated, and when sufficient inferences are obtained, they are aggregated, and the final answer is generated. This makes the information per inference by LLM simplified, and logical inference is achieved through an explicit inference chain.We conducted experiments on two multi-hop QA datasets and confirmed through a quantitative evaluation that our EIC framework performed better than existing approaches. Moreover, a qualitative evaluation confirmed that our approach can effectively perform inference so as to get closer to the answer in question-answering tasks that require knowledge. In addition, compared with existing approaches, the EIC framework improves the interpretability of the output.

ANFIS: adaptive-network-based fuzzy inference system

Abstract: The architecture and learning procedure underlying ANFIS (adaptive-network-based fuzzy inference system) is presented, which is a fuzzy inference system implemented in the framework of adaptive networks. By using a hybrid learning procedure, the proposed ANFIS can construct an input-output mapping based on both human knowledge (in the form of fuzzy if-then rules) and stipulated input-output data pairs. In the simulation, the ANFIS architecture is employed to model nonlinear functions, identify nonlinear components on-line in a control system, and predict a chaotic time series, all yielding remarkable results. Comparisons with artificial neural networks and earlier work on fuzzy modeling are listed and discussed. Other extensions of the proposed ANFIS and promising applications to automatic control and signal processing are also suggested. >

Fuzzy logic in control systems: fuzzy logic controller. II

Abstract: For pt.I see ibid., vol.20, no.2, p.404-18, 1990. The basic aspects of the FLC (fuzzy logic controller) decision-making logic are examined. Several issues, including the definitions of a fuzzy implication, compositional operators, the interpretations of the sentence connectives 'and' and 'also', and fuzzy inference mechanisms, are investigated. Defuzzification strategies, are discussed. Some of the representative applications of the FLC, from laboratory level to industrial process control, are briefly reported. Some unsolved problems are described, and further challenges in this field are discussed. >

Robust Model-Based Fault Diagnosis for Dynamic Systems

Abstract: There is an increasing demand for dynamic systems to become safer and more reliable This requirement extends beyond the normally accepted safety-critical systems such as nuclear reactors and aircraft, where safety is of paramount importance, to systems such as autonomous vehicles and process control systems where the system availability is vital It is clear that fault diagnosis is becoming an important subject in modern control theory and practice Robust Model-Based Fault Diagnosis for Dynamic Systems presents the subject of model-based fault diagnosis in a unified framework It contains many important topics and methods; however, total coverage and completeness is not the primary concern The book focuses on fundamental issues such as basic definitions, residual generation methods and the importance of robustness in model-based fault diagnosis approaches In this book, fault diagnosis concepts and methods are illustrated by either simple academic examples or practical applications The first two chapters are of tutorial value and provide a starting point for newcomers to this field The rest of the book presents the state of the art in model-based fault diagnosis by discussing many important robust approaches and their applications This will certainly appeal to experts in this field Robust Model-Based Fault Diagnosis for Dynamic Systems targets both newcomers who want to get into this subject, and experts who are concerned with fundamental issues and are also looking for inspiration for future research The book is useful for both researchers in academia and professional engineers in industry because both theory and applications are discussed Although this is a research monograph, it will be an important text for postgraduate research students world-wide The largest market, however, will be academics, libraries and practicing engineers and scientists throughout the world

Fuzzy Control Systems Design and Analysis: A Linear Matrix Inequality Approach

Abstract: From the Publisher: A comprehensive treatment of model-based fuzzy control systems This volume offers full coverage of the systematic framework for the stability and design of nonlinear fuzzy control systems. Building on the Takagi-Sugeno fuzzy model, authors Tanaka and Wang address a number of important issues in fuzzy control systems, including stability analysis, systematic design procedures, incorporation of performance specifications, numerical implementations, and practical applications. Issues that have not been fully treated in existing texts, such as stability analysis, systematic design, and performance analysis, are crucial to the validity and applicability of fuzzy control methodology. Fuzzy Control Systems Design and Analysis addresses these issues in the framework of parallel distributed compensation, a controller structure devised in accordance with the fuzzy model. This balanced treatment features an overview of fuzzy control, modeling, and stability analysis, as well as a section on the use of linear matrix inequalities (LMI) as an approach to fuzzy design and control. It also covers advanced topics in model-based fuzzy control systems, including modeling and control of chaotic systems. Later sections offer practical examples in the form of detailed theoretical and experimental studies of fuzzy control in robotic systems and a discussion of future directions in the field. Fuzzy Control Systems Design and Analysis offers an advanced treatment of fuzzy control that makes a useful reference for researchers and a reliable text for advanced graduate students in the field.

Fuzzy Model Identification Based on Cluster Estimation

Abstract: We present an efficient method for estimating cluster centers of numerical data. This method can be used to determine the number of clusters and their initial values for initializing iterative optimization-based clustering algorithms such as fuzzy C-means. Here we use the cluster estimation method as the basis of a fast and robust algorithm for identifying fuzzy models. A benchmark problem involving the prediction of a chaotic time series shows this model identification method compares favorably with other, more computationally intensive methods. We also illustrate an application of this method in modeling the relationship between automobile trips and demographic factors.