Taiwanese China Studies (CS) has developed into a rich, interdisciplinary research field shaped by the unique geopolitical position and long standing academic engagement with Mainland China. This study responds to the growing need to systematically revisit and reorganize decades of Taiwan based CS scholarship by proposing an AI assisted approach that transforms unstructured academic texts into structured, interactive knowledge representations. We apply generative AI (GAI) techniques and large language models (LLMs) to extract and standardize entity relation triples from 1,367 peer reviewed CS articles published between 1996 and 2019. These triples are then visualized through a lightweight D3.js based system, forming the foundation of a domain specific knowledge graph and vector database for the field. This infrastructure allows users to explore conceptual nodes and semantic relationships across the corpus, revealing previously uncharted intellectual trajectories, thematic clusters, and research gaps. By decomposing textual content into graph structured knowledge units, our system enables a paradigm shift from linear text consumption to network based knowledge navigation. In doing so, it enhances scholarly access to CS literature while offering a scalable, data driven alternative to traditional ontology construction. This work not only demonstrates how generative AI can augment area studies and digital humanities but also highlights its potential to support a reimagined scholarly infrastructure for regional knowledge systems.

Define a building blocks set to be a collection of n cubes (each with six sides) where each side is assigned one letter and one color from a palette of m colors. We propose a novel problem of assigning letters and colors to each face so as to maximize the number of words one can spell from a chosen dataset that are either mono words, all letters have the same color, or rainbow words, all letters have unique colors. We explore this problem considering a chosen set of English words, up to six letters long, from a typical vocabulary of a US American 14 year old and explore the problem when n = 6 and m = 6, with the added restriction that each color appears exactly once on the cube. The problem is intractable, as the size of the solution space makes a brute force approach computationally infeasible. Therefore we aim to solve this problem using random search, simulated annealing, two distinct tree search approaches (greedy and best-first), and a genetic algorithm. To address this, we explore a range of optimization techniques: random search, simulated annealing, two distinct tree search methods (greedy and best-first), and a genetic algorithm. Additionally, we attempted to implement a reinforcement learning approach; however, the model failed to converge to viable solutions within the problem's constraints. Among these methods, the genetic algorithm delivered the best performance, achieving a total of 2846 mono and rainbow words.

Many cognitive models posit mental representations based on discrete substructures. Even connectionist models whose processing involves manipulation of real-valued activations typically represent objects as patterns of 0s and 1s across a set of units (Noelle, Cottrell, and Wilms, 1997). Often, individual units are taken to represent specific features of the objects and two representations will share features to the degree to which the two objects are similar. While this arrangement is intuitively appealing, it can be difficult to construct the features to be used in such a model. Using random feature assignments clouds the relationship between the model and the objects it is intended to represent, diminishing the model's value. As Clouse and Cottrell (1996) point out, hand-crafted representations are tedious to construct and it can be difficult to precisely justify (or even articulate) the principles that guided their design. These difficulties effectively limit the number of objects that can be encoded, constraining modeling efforts to small examples. In this paper, we investigate methods for automatically synthesizing feature-based representations directly from the pairwise object similarities that the model is intended to respect.

Originally developed for imputing missing entries in low rank, or approximately low rank matrices, matrix completion has proven widely effective in many problems where there is no reason to assume low-dimensional linear structure in the underlying matrix, as would be imposed by rank constraints. In this manuscript, we build some theoretical intuition for this behavior. We consider matrices which are not necessarily low-rank, but lie in a low-dimensional non-linear manifold. We show that nuclear-norm penalization is still effective for recovering these matrices when observations are missing completely at random. In particular, we give upper bounds on the rate of convergence as a function of the number of rows, columns, and observed entries in the matrix, as well as the smoothness and dimension of the non-linear embedding. We additionally give a minimax lower bound: This lower bound agrees with our upper bound (up to a logarithmic factor), which shows that nuclear-norm penalization is (up to log terms) minimax rate optimal for these problems.

Leaders of the Air Force, Navy, Army and Marines are converging on a vision of the future military: connecting every asset on the global battlefield. That means everything from F-35 jets overhead to the destroyers on the sea to the armor of the tanks crawling over the land to the multiplying devices in every troops' pockets. Every weapon, vehicle, and device connected, sharing data, constantly aware of the presence and state of every other node in a truly global network. The effect: an unimaginably large cephapoloidal nervous system armed with the world's most sophisticated weaponry. In recent months, the Joint Chiefs of Staff put together the newest version of their National Military Strategy.

Like most learning algorithms, the multilayer perceptrons (MLP) is designed to learn a vector of parameters from data. However, in certain scenarios we are interested in learning structured parameters (predictions) in the form of symmetric positive definite matrices. Here, we introduce a variant of the MLP, referred to as the matrix MLP, that is specialized at learning symmetric positive definite matrices. We also present an application of the model within the context of the variational autoencoder (VAE). Our formulation of the VAE extends the vanilla formulation to the cases where the recognition and the generative networks can be from the parametric family of distributions with dense covariance matrices. Two specific examples are discussed in more detail: the dense covariance Gaussian and its generalization, the power exponential distribution. Our new developments are illustrated using both synthetic and real data.

Although it might be too early for a standard model of the mind (SMM), comparison between current cognitive architectures is a useful exercise. This article highlights some of the likely difficulties facing the development of a SMM – both empirical and theoretical. In particular, it follows Newell (1990) by arguing that a viable model of the mind must be constructed taking advantage of experimental constraints, based on comparisons of the model with (human or animal) data. We then describe our proposed methodology for ensuring a tight link between psychological data and a cognitive architecture. We also discuss CHREST, a cognitive model with a particular emphasis on modelling psychological results. CHREST has been applied in several domains, such as language acquisition and expertise. The article concludes by highlighting some of the features that distinguish CHREST from architectures such as Soar and ACT-R. Some of these differences are significant, creating challenges for a SMM.

Leaders of the Air Force, Navy, Army and Marines are converging on a vision of the future military: connecting every asset on the global battlefield. That means everything from F-35 jets overhead to the destroyers on the sea to the armor of the tanks crawling over the land to the multiplying devices in every troops' pockets. Every weapon, vehicle, and device connected, sharing data, constantly aware of the presence and state of every other node in a truly global network. The effect: an unimaginably large cephapoloidal nervous system armed with the world's most sophisticated weaponry. In recent months, the Joint Chiefs of Staff put together the newest version of their National Military Strategy.

Researchers have recognized the importance of classifying personality through discourse for many years. However, this line of research tends to focus almost exclusively on the personality categories known as the Big Five factors. Though this information is certainly valuable, it may also be useful to categorize personality based on the Leary’s Interpersonal Circumplex model which emphasizes a predictive function. In this paper we construct the data set for personality annotation among six dimensions (based on a coding scheme developed from Leary’s Interpersonal Circumplex) for players using a chat interaction in an epistemic game, Land Science. Our results indicate that overall personality annotation is reliable (Average Kappa = 0.65) with the highest reliability for the competitive dimension and the lowest reliability for the leading dimension.

If the promise of computational modeling is to be fully realized in higherlevel cognitivedomains such as language processing, principled methods must be developed to construct the semantic representations used in such models. In this paper, we propose the use of an established formalism from mathematical psychology, additive clustering, as a means of automatically constructingbinary representations for objects using only pairwise similarity data. However, existing methods for the unsupervised learning of additive clustering models do not scale well to large problems. Wepresent a new algorithm for additive clustering, based on a novel heuristic technique for combinatorial optimization. The algorithm is simpler than previous formulations and makes fewer independence assumptions. Extensiveempirical tests on both human and synthetic data suggest that it is more effective than previous methods and that it also scales better to larger problems. By making additive clustering practical, we take a significant step toward scaling connectionist models beyond hand-coded examples.