Expressive Power Research Articles

Quantum tangent kernel

The quantum kernel method is one of the key approaches to quantum machine learning, which has the advantage of not requiring optimization and its theoretical simplicity. By virtue of these properties, several experimental demonstrations and discussions of the potential advantages have been developed so far. However, as is the case in classical machine learning, not all quantum machine learning models could be regarded as kernel methods. In this work, we explore a quantum machine learning model with a deep parametrized quantum circuit and aim to go beyond the conventional quantum kernel method. In this case, the expressive power and performance are expected to be enhanced, while the training process might be a bottleneck because of the barren plateaus. Moreover, the high computational cost of gradient-based optimization and the large search space of the gradient-free optimization directly make the training intractable. However, we find that parameters of a deep enough quantum circuit do not move much from their initial values during training, allowing for a first-order expansion with respect to the parameters. This behavior is similar to that of the neural tangent kernel in classical machine learning, and such a quantum machine learning with deep variational quantum circuits can be described by another emergent kernel, the . We show that the proposed quantum tangent kernel has the potential to outperform the conventional quantum kernel method by performing a classification task on an ansatz-generated dataset. This work provides a different direction beyond the conventional quantum kernel method and explores the potential power of quantum machine learning with deep parametrized quantum circuits. Published by the American Physical Society 2024

Sound Borrow-Checking for Rust via Symbolic Semantics

The Rust programming language continues to rise in popularity, and as such, warrants the close attention of the programming languages community. In this work, we present a new foundational contribution towards the theoretical understanding of Rust’s semantics. We prove that LLBC, a high-level, borrow-centric model previously proposed for Rust’s semantics and execution, is sound with regards to a low-level pointer-based language à la CompCert. Specifically, we prove the following: that LLBC is a correct view over a traditional model of execution; that LLBC’s symbolic semantics are a correct abstraction of LLBC programs; and that LLBC’s symbolic semantics act as a borrow-checker for LLBC, i.e. that symbolically-checked LLBC programs do not get stuck when executed on a heap-and-addresses model of execution. To prove these results, we introduce a new proof style that considerably simplifies our proofs of simulation, which relies on a notion of hybrid states. Equipped with this reasoning framework, we show that a new addition to LLBC’s symbolic semantics, namely a join operation, preserves the abstraction and borrow-checking properties. This in turn allows us to add support for loops to the Aeneas framework; we show, using a series of examples and case studies, that this unlocks new expressive power for Aeneas.

Defect detection of zipper tape based on lightweight deep learning network

Zipper tapes are essential in the garment industry, with defects significantly impacting the appearance of fabric products. Current methods for inspecting zipper tapes suffer from low detection accuracy. This paper proposes a lightweight, deep learning-based defect detection method using YOLOv5. The method includes a newly designed C3-CM module that integrates the Convolutional Block Attention Module (CBAM) into the backbone network, enhancing defect attention and feature extraction capabilities. Additionally, the lightweight GSConv convolution reduces parameter count while maintaining accuracy. The VoV-GSCSP module constructs deep-level feature fusion to boost the network’s expressive power. Using the Content-Aware Reassembly of Features (CARAFE), the method leverages underlying semantic information to predict and reorganize kernels, thereby enhancing upsampling effectiveness. Experimental results indicate that this method significantly improves accuracy compared to traditional approaches and outperforms current state-of-the-art algorithms in both accuracy and speed.

Neural-Symbolic Methods for Knowledge Graph Reasoning: A Survey

Neural symbolic knowledge graph (KG) reasoning offers a promising approach that combines the expressive power of symbolic reasoning with the learning capabilities inherent in neural networks. This survey provides a comprehensive overview of advancements, techniques, and challenges in the field of neural symbolic KG reasoning. The survey introduces the fundamental concepts of KGs and symbolic logic, followed by an exploration of three significant KG reasoning tasks: knowledge graph completion, complex query answering, and logical rule learning. For each task, we thoroughly discuss three distinct categories of methods: pure symbolic methods, pure neural approaches, and the integration of neural networks and symbolic reasoning methods known as neural-symbolic. We carefully analyze and compare the strengths and limitations of each category of methods to provide a comprehensive understanding. By synthesizing recent research contributions and identifying open research directions, this survey aims to equip researchers and practitioners with a comprehensive understanding of the state-of-the-art in neural symbolic KG reasoning, fostering future advancements in this interdisciplinary domain.

The Hexi Corridor Elements in Traditional Music and Contemporary Innovation and Application

This article explores the characteristics of the Hexi Corridor elements in traditional music and their innovation and application in contemporary times. The research background includes a review of the cultural and musical history of the ancient geographical region of Hexi Corridor, analyzing its unique elements in traditional music such as melody, rhythm, and instruments. The research method adopts a combination of literature analysis and field research, collecting and analyzing relevant music materials to explore the core elements of music in the Hexi Corridor. The research results indicate that the musical elements of the Hexi Corridor have been innovatively applied in modern music creation, such as integrating electronic music, modern stage art, etc., enriching the expression forms of contemporary music. This article argues that the innovative application of traditional music elements in the Hexi Corridor not only broadens the expressive power of traditional music, but also provides new inspiration and materials for modern music creation. Research is of great significance in promoting the inheritance and innovation of traditional culture, and promoting the development of cultural diversity.

Disorder-Invariant Implicit Neural Representation.

Implicit neural representation (INR) characterizes the attributes of a signal as a function of corresponding coordinates which emerges as a sharp weapon for solving inverse problems. However, the expressive power of INR is limited by the spectral bias in the network training. In this paper, we find that such a frequency-related problem could be greatly solved by re-arranging the coordinates of the input signal, for which we propose the disorder-invariant implicit neural representation (DINER) by augmenting a hash-table to a traditional INR backbone. Given discrete signals sharing the same histogram of attributes and different arrangement orders, the hash-table could project the coordinates into the same distribution for which the mapped signal can be better modeled using the subsequent INR network, leading to significantly alleviated spectral bias. Furthermore, the expressive power of the DINER is determined by the width of the hash-table. Different width corresponds to different geometrical elements in the attribute space, e.g., 1D curve, 2D curved-plane and 3D curved-volume when the width is set as 1, 2 and 3, respectively. More covered areas of the geometrical elements result in stronger expressive power. Experiments not only reveal the generalization of the DINER for different INR backbones (MLP versus SIREN) and various tasks (image/video representation, phase retrieval, refractive index recovery, and neural radiance field optimization) but also show the superiority over the state-of-the-art algorithms both in quality and speed.

How to Formalize Different Types of Norms in Multi-agent Systems: A Methodology Focused on the T-Norm Model

In a world where many activities are carried out digitally, it is increasingly urgent to be able to formally represent the norms, policies, and contracts that regulate these activities in order to make them understandable and processable by machine. In multi-agent systems, the process to be followed by a person to choose a formal model of norms and transform a norm written in a natural language into a formal one by using the selected model is a demanding task. In this paper, we introduce a methodology to be followed by people to understand the fundamental elements that they should consider for this transformation. We will focus mainly on a methodology for formalizing norms using the T-Norm model, this is because it allows us to express a rich set of different types of norms. Nevertheless, the proposed methodology is general enough to also be used, in some of its steps, to formalize norms using other formal languages. In the definition of the methodology, we will explicitly state which types of norms can be expressed with a given model and which cannot. Since there is not yet a set of different types of norms that is sufficiently expressive and is recognized as valid by the Normative Mutiagent Systems (NorMAS) community, another goal of this paper is to propose and discuss a rich set of norms types that could be used to study the expressive power of different formal models of norms, to compare them, and to translate norms formalized with one language into norms written in another language.

ES-dRNN: A Hybrid Exponential Smoothing and Dilated Recurrent Neural Network Model for Short-Term Load Forecasting.

Short-term load forecasting (STLF) is challenging due to complex time series (TS) which express three seasonal patterns and a nonlinear trend. This article proposes a novel hybrid hierarchical deep-learning (DL) model that deals with multiple seasonality and produces both point forecasts and predictive intervals (PIs). It combines exponential smoothing (ES) and a recurrent neural network (RNN). ES extracts dynamically the main components of each individual TS and enables on-the-fly deseasonalization, which is particularly useful when operating on a relatively small dataset. A multilayer RNN is equipped with a new type of dilated recurrent cell designed to efficiently model both short and long-term dependencies in TS. To improve the internal TS representation and thus the model's performance, RNN learns simultaneously both the ES parameters and the main mapping function transforming inputs into forecasts. We compare our approach against several baseline methods, including classical statistical methods and machine learning (ML) approaches, on STLF problems for 35 European countries. The empirical study clearly shows that the proposed model has high expressive power to solve nonlinear stochastic forecasting problems with TS including multiple seasonality and significant random fluctuations. In fact, it outperforms both statistical and state-of-the-art ML models in terms of accuracy.

The Artistic Impact of Computer-Aided Design on Building Façade in Nigeria

The visual landscape of our cities is ever- evolving, shaped by the architectural and embedded computer aided design marvels that adorn the urban fabric. Among the myriad elements that contribute to the allure of a building, the artistic impact on its facade holds a distinct significance. The facade, as the external face of a structure, acts as a canvas where artistry and design converge, manifesting an artistic expression that resonates with its surroundings and captivates the human eye. The interplay between art, computer and architecture has been a topic of fascination for centuries, as artists, computer aided design and architects have sought to transcend mere functionality and transform buildings into visually striking works of art. From ancient civilizations to modern metropolises, the artistic impact on building facades has been an enduring reflection of cultural heritage, societal values, and creative ingenuity. This journal aims to delve into the multifaceted aspects of artistic and computerization impact on building facades, exploring the diverse factors that shape this phenomenon and the profound influence it has on our built environment. By delving into the intricate interplay of aesthetics, functionality, and cultural context, we seek to unravel the power of artistic and automation expression in transforming buildings into iconic landmarks. Understanding the artistic and embedded system impact on building facades necessitates an exploration of various dimensions. Examining the influence of cultural context, as different regions and communities in Nigeria imbue their buildings with distinct artistic computerization styles, motifs, and themes rooted in their heritage and traditions. Additionally, architectural coupled with automation system style plays a pivotal role, as different design paradigms demand specific artistic elements and materials to achieve harmony and coherence between form and function. Furthermore, this journal will investigate the impact of the urban environment on artistic automation system expression. The surrounding cityscape, with its diverse architectural and computerization styles, urban planning principles, and contextual demands, serves as a backdrop against which building facades make their artistic and automation statements.

Interactive Invigoration: Volumetric Modeling of Trees with Strands

Generating realistic models of trees and plants is a complex problem because of the vast variety of shapes trees can form. Procedural modeling algorithms are popular for defining branching structures and steadily increasing their expressive power by considering more biological findings. Most existing methods focus on defining the branching structure of trees based on skeletal graphs, while the surface mesh of branches is most commonly defined as simple cylinders. One critical open problem is defining and controlling the complex details observed in real trees. This paper aims to advance tree modeling by proposing a strand-based volumetric representation for tree models. Strands are fixed-size volumetric pipes that define the branching structure. By leveraging strands, our approach captures the lateral development of trees. We combine the strands with a novel branch development formulation that allows us to locally inject vigor and reshape the tree model. Moreover, we define a set of editing operators for tree primary and lateral development that enables users to interactively generate complex tree models with unprecedented detail with minimal effort.

Automatic and User-Assisted Sphere-Mesh Construction.

A sphere-mesh is a class of geometric proxies defined as the volume swept by spheres with linearly interpolated centers and radii, potentially striking a good balance between conciseness of representation, simplicity of spatial queries, and expressive power. We investigate the semiautomatic generation of sphere-meshes from standard triangular meshes. We improve one known automatic construction algorithm, based on iterative local coarsening operation, by introducing a mechanism to prevent operations that would result in spheres exceeding the target shape; then, we propose a 3-D interface designed to permit users to easily and intuitively modify the automatically generated sphere-meshes. The two phases, an improved automatic algorithm and a novel interactive tool, used in cascade, constitute a viable semiautomatic way to produce high-quality sphere-meshes. We test our method on several inputs tri-meshes, assess their quality, and finally exemplify the usability of our results by testing them in a few downstream applications.

Mapping Petri Nets onto a Calculus of Context-Aware Ambients

Petri nets are a graphical notation for describing a class of discrete event dynamic systems whose behaviours are characterised by concurrency, synchronisation, mutual exclusion and conflict. They have been used over the years for the modelling of various distributed systems applications. With the advent of pervasive systems and the Internet of Things, the Calculus of Context-aware Ambients (CCA) has emerged as a suitable formal notation for analysing the behaviours of these systems. In this paper, we are interested in comparing the expressive power of Petri nets to that of CCA. That is, can the class of systems represented by Petri nets be modelled in CCA? To answer this question, an algorithm is proposed that maps any Petri net onto a CCA process. We prove that a Petri net and its corresponding CCA process are behavioural equivalent. It follows that CCA is at least as expressive as Petri nets, i.e., any system that can be specified in Petri nets can also be specified in CCA. Moreover, tools developed for CCA can also be used to analyse the behaviours of Petri nets.

MİLAN KUNDERA – “GÜLMƏLİ MƏHƏBBƏTLƏR” HEKAYƏSİNDƏ MƏHƏBBƏT İDEYASI

Milan Kundera – The Idea of Love in the Story "Laughable Loves" Summary Born in Brno, Czechoslovakia, Milan Kundera was a student when the Czech communist regime was established in 1948, and later worked as a laborer, jazz musician and professor at the Institute for Advanced Cinematographic Studies in Prague. His books were banned after the Russian occupation in August 1968. She and her husband settled in France in 1975, and in 1981 became French citizens. He is the author of the novels "Joke", "Life is Elsewhere", "Goodbye Waltz", "Book of Laughter and Forgetfulness", "The Unbearable Lightness of Being" and "Immortality" and a collection of short stories "Laughable Loves" – all originally in Czech. His most recent novels, Slowness, Personality, and Ignorance, as well as his non-fiction works, Roman Art and Betrayed Will, were first written in French. The core of the themes that the author will work on in his later novels, as well as the original and innovative narrative methods in the development of these themes can be found in Kundera's "Laughable Loves", written with the greatest pleasure and delight. It can be said that the story book, which took ten years to write, is very different in terms of both content and form. In Kundera's stories, men persecute women with their "erotic passions." Married, single, old and young men face social difficulties, accept the loss of time and economic difficulties and try to attract women. Kundera beautifully reflects the universal challenges they face during this marathon. "Laughable Loves" is about raising the power of expression and aesthetics, as well as the successful depiction of this universal event – with humor.

LEGITIMACY OF THE COERCIVE MEASURE OF CIVIL DETENTION IN THE EXECUTION OF SENTENCES WITHIN THE FRAMEWORK OF CIVIL PROCEEDINGS

Article 53 of the Code of Civil Procedure regulates coercive measures, specifically, numeral 2 of said article empowers the judge to order the detention for 24 hours of anyone who resists his order without justification. This regulation generates controversy as it is considered unconstitutional because it would violate article 2 numeral 24 literal c) of the Political Constitution of the State, in the understanding that there is no imprisonment for debt, even the terminology of detention would correspond to be used in criminal matters. Furthermore, it is questioned whether the civil judge can order detention. In this context, this article analyzes the positions against and in favor of civil detention, concluding that several Latin American countries maintain its application specifically for certain cases, whether in civil or criminal normative bodies, as a sanction for non-compliance with a civil obligation, therefore it is necessary to regulate in the Code of Civil Procedure as an express power of the judge, the civil arrest, to enforce its decisions. Emphasizing that the appropriate terminology is that of arrest for up to 24 hours, which can be dictated by the civil judge.

DPGCL: Dual pass filtering based graph contrastive learning

Graph Contrastive Learning (GCL), which learns node or graph representation from supervision signals derived from the graph data itself, has recently attracted extensive research attention and achieved great success. Remarkably, most of the existing GCL encoders essentially perform low-frequency filtering on graph, which however limits their expressive power on heterophilous graphs where dissimilar nodes tend to be connected. This raises an interesting question: can high frequency be informative for GCL? In this work, we experimentally study the influence of high-frequency signals on GCL and find that adding some high-frequency signals in contrasting is beneficial for improving GCL performance. That motivates us to design a more general GCL framework beyond low-pass filtering, which simultaneously performs low-pass and high-pass signal contrasts, so as to capture both low and high-frequency information in general graphs. Furthermore, to enable the representation learning to be aware of neighbor diversity in heterophilic graphs, we propose a novel graph contrastive loss, termed Adap-infoNCE, which can automatically decide the weights of negative samples based on feature representations of neighboring nodes. Here two types of neighbors are considered, i.e., spatial neighbors and featural neighbors, whose effectiveness is verified using empirical study on synthetic datasets. Extensive experiments demonstrate that our method brings significant and consistent improvements over the base GCL approach and exceeds multiple state-of-the-art results on several unsupervised benchmarks, even surpassing the performance of supervised benchmarks.

Finitely ambiguous and finitely sequential weighted automata over fields

Expressive power of finitely ambiguous and finitely sequential weighted automata over fields is examined. Rational series realised by such automata can be classified into infinite hierarchies according to ambiguity and sequentiality degrees of realising automata – it is shown that both these hierarchies are strict already over unary alphabets in case the field under consideration is not locally finite. Moreover, the expressive power of finitely sequential, finitely ambiguous, and polynomially ambiguous weighted automata is compared over different fields, both for unary and arbitrary finite alphabets, drawing a complete picture of the relations between corresponding classes of formal power series.

A Historical Approach to Understanding Differentiation of RYB vs RGB

This article defines the roles of colors and presents their historical development as a fundamental means of expression within artwork. It also introduces color theorists and practices, including the mixing of pigments, a necessary technique for artists-designers in creating tangible results. Modern artists-designers have used these theorists to express themselves in producing an aesthetic experience in the viewer through their artwork, starting with Sir Isaac Newton’s light-spectrum experiments using a glass prism and a beam of white light, and continuing through Johannes Itten’s color-wheel and creative color-matching exercises. This article objective defines the significance of color, its historical development on the basis of earlier perceptual theorists’ findings that color acquires dimension and meaning in response to cultural-historical context or psychological realities. As a result, this paper also explores how color affects our emotions, our psychic and spiritual manifestations. This psychic-spiritual manifestation is revealed through a process of visual perception and experimenting with color and its symbolic meaning. Artists such as Seurat, Munch, Kandinsky, Paul Klee, Josef Albers, Picasso, Joan Miro, or Mark Rothko demonstrated the expressive power of color-pigment. The authors hope that this paper will bring significant discussion, awareness, will assist general readers and academic researchers and truly advance knowledge.

From large language models to small logic programs: building global explanations from disagreeing local post-hoc explainers

The expressive power and effectiveness of large language models (LLMs) is going to increasingly push intelligent agents towards sub-symbolic models for natural language processing (NLP) tasks in human–agent interaction. However, LLMs are characterised by a performance vs. transparency trade-off that hinders their applicability to such sensitive scenarios. This is the main reason behind many approaches focusing on local post-hoc explanations, recently proposed by the XAI community in the NLP realm. However, to the best of our knowledge, a thorough comparison among available explainability techniques is currently missing, as well as approaches for constructing global post-hoc explanations leveraging the local information. This is why we propose a novel framework for comparing state-of-the-art local post-hoc explanation mechanisms and for extracting logic programs surrogating LLMs. Our experiments—over a wide variety of text classification tasks—show how most local post-hoc explainers are loosely correlated, highlighting substantial discrepancies in their results. By relying on the proposed novel framework, we also show how it is possible to extract faithful and efficient global explanations for the original LLM over multiple tasks, enabling explainable and resource-friendly AI techniques.

DyHANE: dynamic heterogeneous attributed network embedding through experience node replay

With real-world network systems typically comprising a large number of interactive components and inherently dynamic, Graph Continual Learning (GCL) has gained increasing popularity in recent years. Furthermore, most applications involve multiple entities and relationships with associated attributes, which has led to widely adopting Heterogeneous Information Networks (HINs) for capturing such rich structural and semantic meaning. In this context, we deal with the problem of learning multi-type node representations in a time evolving graph setting, harnessing the expressive power of Graph Neural Networks (GNNs). To this purpose, we propose a novel framework, named DyHANE—Dynamic Heterogeneous Attributed Network Embedding, which dynamically identifies a representative sample of multi-typed nodes as training set and updates the parameters of a GNN module, enabling the generation of up-to-date representations for all nodes in the network. We show the advantage of employing HINs on a data-incremental classification task. We compare the results obtained by DyHANE on a multi-step, incremental heterogeneous GAT model trained on a sample of changed and unchanged nodes, with the results obtained by either the same model trained from scratch or the same model trained solely on changed nodes. We demonstrate the effectiveness of the proposed approach in facing two major related challenges: (i) to avoid model re-train from scratch if only a subset of the network has been changed and (ii) to mitigate the risk of losing established patterns if the new nodes exhibit unseen properties. To the best of our knowledge, this is the first work that deals with the task of (deep) graph continual learning on HINs.

TransCell: In Silico Characterization of Genomic Landscape and Cellular Responses by Deep Transfer Learning.

Gene expression profiling of new or modified cell lines becomes routine today; however, obtaining comprehensive molecular characterization and cellular responses for a variety of cell lines, including those derived from underrepresented groups, is not trivial when resources are minimal. Using gene expression to predict other measurements has been actively explored; however, systematic investigation of its predictive power in various measurements has not been well studied. Here, we evaluated commonly used machine learning methods and presented TransCell, a two-step deep transfer learning framework that utilized the knowledge derived from pan-cancer tumor samples to predict molecular features and responses. Among these models, TransCell had the best performance in predicting metabolite, gene effect score (or genetic dependency), and drug sensitivity, and had comparable performance in predicting mutation, copy number variation, and protein expression. Notably, TransCell improved the performance by over 50% in drug sensitivity prediction and achieved a correlation of 0.7 in gene effect score prediction. Furthermore, predicted drug sensitivities revealed potential repurposing candidates for new 100 pediatric cancer cell lines, and predicted gene effect scores reflected BRAF resistance in melanoma cell lines. Together, we investigated the predictive power of gene expression in six molecular measurement types and developed a web portal (http://apps.octad.org/transcell/) that enables the prediction of 352,000 genomic and cellular response features solely from gene expression profiles.