教学课程资源库 更多>>

关键词： Artificial intelligence applications   Computer science   Health sciences   Medicine  

摘要： Deep learning holds great promise in drug discovery, yet its application is hindered by high labeling costs and limited datasets. Developing algorithms that effectively learn from sparsely labeled data is crucial. Capsule networks (CapsNet), introduced in 2017, solve the spatial information loss in traditional neural networks and excel in handling small datasets by capturing spatial hierarchical relationships among features. This capability makes CapsNet particularly promising for drug discovery, where data scarcity is a common challenge. Various modified CapsNet architectures have been successfully applied to drug design and discovery tasks. This review provides a comprehensive analysis of CapsNet's theoretical foundations, its current applications in drug discovery, and its performance in addressing key challenges in the field. Additionally, the study highlights the limitations of CapsNet and outlines potential future research directions to further enhance its utility in drug discovery, offering valuable insights for researchers in both computational and pharmaceutical sciences. © 2025 The Author(s)

关键词： Physics   Neural networks   Computer science  

摘要： In this study, we explore the inherent trade-off between accuracy and robustness in neural networks, drawing an analogy to the uncertainty principle in quantum mechanics. We propose that neural networks are subject to an uncertainty relation, which manifests as a fundamental limitation in their ability to simultaneously achieve high accuracy and robustness against adversarial attacks. Through mathematical proofs and empirical evidence, we demonstrate that this trade-off is a natural consequence of the sharp boundaries formed between different class concepts during training. Our findings reveal that the complementarity principle, a cornerstone of quantum physics, applies to neural networks, imposing fundamental limits on their capabilities in simultaneous learning of conjugate features. Meanwhile, our work suggests that achieving human- level intelligence through a single-network architecture or massive datasets alone may be inherently limited. Our work provides new insights into the theoretical foundations of neural network vulnerability and opens up avenues for designing more robust neural network architectures.

关键词： Urban areas   Routing   Benchmark testing   Metaheuristics   Genetic algorithms   Vehicle routing   Surface waves   Standards   Heuristic algorithms   Computer science  

摘要： This study introduces the Transverse Waves Algorithm (TWA), a novel heuristic approach devised to address the Travelling Salesperson Problem (TSP) within a unique instance. Inspired by natural phenomena where energy disperses in waves from a central point and interacts with its environment, TWA is designed for areas structured in concentric circles and segmented into equal parts. The algorithm mimics wave behaviors, when disrupted by obstacles and reflected by surfaces, to optimize routing. It systematically calculates routes initiating from a central hub, extending along each circle’s circumference, visiting each location once, and progressing through strategically chosen adjacent points to minimize the total traveled distance. Experimental results indicate that TWA significantly enhances route optimization, outperforming traditional methods in specific instances. The findings underscore TWA’s potential contributions to the field of logistics and operational research.

关键词： Emotion recognition   Computational modeling   Weak supervision   Multilingual   Benchmark testing   Text recognition   Speech recognition   Context modeling   Computer science   Complexity theory  

摘要： Text-based emotion recognition plays a crucial role in various domains and applications due to its significance in understanding human behavior and improving communication systems. Although extensive research has been conducted for texts in English, only few studies deal with non-English languages. Especially for the German language, previous work is limited due to the focus on specific text domains and the usage of lexicon-based approaches, which lack the ability to consider contextual information. In this paper, an approach for emotion recognition on German text corpora is presented, which addresses these challenges with domain-generalized and context-sensitive methodologies. To achieve domain generalization, neural machine translation and weak supervision techniques are combined with multi-view learning, in which various data sources from different domains are utilized to improve the generalizability and to overcome the problem of lack of data. Using the BERT model as the primary architecture to capture contextual information, an overall F1-score of 65.5% and an accuracy of 68.1% are achieved while maintaining well-balanced results on the metrics over all considered domains and emotions. To ensure the legitimacy and reliability of the findings, further comprehensive evaluations and comparisons are conducted. Given the absence of an established benchmark specifically for emotion recognition on German text corpora, the used datasets, evaluations, and results can serve for benchmarking purposes.

关键词： Optics and photonics   Computer science   Machine learning  

摘要： Computer processors that exploit both electricity and light could improve the performance of artificial-intelligence systems while consuming less energy.

关键词： Embedded systems   Computational modeling   Hardware   Aerospace electronics   Software   Real-time systems   Systems modeling   Costs   Computer science   Proposals  

摘要： One of the main challenges of embedded system design lies in the natural heterogeneity of these systems. We can say that embedded systems are electronic systems designed and programmed to tackle a specific application. Each application has its requirements, although embedded systems often combine many domain-specific subsystems. Considering this context, the design of embedded systems can be extremely challenging, including system modeling, simulation, formal verification, and the synthesis to a correct implementation. To manage the complexity of such systems, the design should start at higher levels of abstraction, based on formal models, without considering the low-level characteristics of the underlying software or hardware. These high-level formal meta-models, named models of computation (MoC), define a set of rules that dictate how computation should be performed and how they should communicate with each other, along with other information such as the notion of time. In this paper, we present as the main contribution a set of rules and interfaces that enable the proper mixing of different MoC domains in a framework for complex embedded system design, thus allowing a heterogeneous system composition at a high abstraction level, including the synchronous reactive, synchronous dataflow, and scenario-aware dataflow MoCs. We model both part of an avionic system and a reconfigurable RISC-V processor using these MoCs and the proposed interfaces as a case study showing the applicability brought by our proposal.

关键词： Project management   Software   Organizations   Systematic literature review   Interviews   Cultural differences   Costs   Computer science   Technological innovation   Lead  

摘要： In current era of technological advancement, global software development (GSD) is expanding to an increasing extent. This rise is driven by the advantages of low-cost development, access to expert resources, proximity to markets and clients, as well as options for innovation and the exchange of best practices. However, the various key aspects of GSD, including geographical dispersion, work ethics, time zone differences and cultural variability make project management more complex in a GSD setting. This study harnesses the critical success factors (CSFs) approach to identify the model for successful management of GSD projects. Sixteen CSFs have been determined using literature review, expert judgement, and exhaustive interviews. The interrelationship among the identified CSFs has been modeled using interpretive structural modeling (ISM) and cross-impact matrix multiplication applied to classification (MICMAC) analysis. The proposed model has been validated using detailed interviews, conducted with twelve professionals from industry and academia. The expert participants were carefully chosen based on criteria which include working experience, roles, and participation in GSD projects. This research computes CSFs of software project management in GSD by assessing their driving and relative strengths. Furthermore, these CSFs are categorized using MICMAC analysis. The previous research studies lack in exploring the mutual influence of CSFs and their hierarchical relationships. With the application of ISM and MICMAC analysis, the proposed study offers understanding of these interdependencies, providing great insights into their driving and dependent function. These insights enhance knowledge in GSD project management by allowing practitioners to prioritize key criteria and formulate potent management strategies.

关键词： Text summarization   Generators   Long short term memory   Encoding   Training   Reinforcement learning   Feature extraction   Computer science   Bidirectional control   Accuracy  

摘要： Text summarization is crucial in various sectors, such as engineering and healthcare, because it enhances efficiency in terms of time and costs. Current extractive text summarization methods struggle with challenges such as greedy selection, model generalization limitations, and high computational demands. To solve these problems, this research introduces a novel extractive text summarization method that uniquely integrates a Generative Adversarial Network (GAN), Transductive Long Short-Term Memory (TLSTM), and DistilBERT for sentence embedding. Our technique uses GANs, which include generator and discriminator components, with the core design based on TLSTM. TLSTM utilizes transductive learning to improve accuracy by focusing on samples geographically closer to the test data. In our model, the generator considers whether to include a sentence in the summary while the discriminator critically reviews the generated summary. This GAN model reduces greedy sentence selection, enhancing summary coherence and quality. We implement a Reinforcement Learning (RL)-based strategy to address an imbalance caused by more fake than real samples in the discriminator. This RL approach, novel in the context of GANs for summarization, views training as a sequence of interconnected decisions, treating each sample as a unique scenario. The network, acting as the decision-making agent, assigns greater rewards or penalties to the minority class to correct the imbalance. The effectiveness of our model was evaluated using the well-regarded CNN/Daily Mail dataset, achieving ROUGE-1, ROUGE-2, and ROUGE-L scores of 52.45, 26.46, and 44.85, respectively. Compared to existing methods, our results demonstrate a significant improvement in summarization quality and operational efficiency, as measured by the ROUGE metric.

关键词： capital punishment   death penalty   deterrence   homicide   murder  

摘要： Australian data encompassing 1910-2022, by year and state, were analyzed to estimate the effect of capital punishment on homicide rates. Our estimates showed that capital punishment had a negative and significant effect on homicides. In some specifications, the estimates implied that an execution was associated with 12.68 fewer homicides;whereas in other specifications, each execution reduced the number of homicides by less than one. The results are stable across different model specifications and subsamples. However, we cannot reject the hypothesis that the deterrent effect of capital punishment being legal is the same as that of mandatory life sentences with mandatory minimum non-parole periods. Thus, our results imply lengthy sentences serve as just as strong a deterrent as capital punishment.

关键词： Computer science   Machine learning   Policy  

摘要： Many firms are misusing the ‘open source’ label. The scientific community, which relies on transparency and replicability, must resist this trend.