Author: Aria Cook

Authors: Mohsin Raza、Ahsan Adeel Paper: https://arxiv.org/abs/2408.11019 An Overlooked Role of Context-Sensitive Dendrites: A Detailed Interpretive Blog Introduction Background and Problem Statement The study of dendrites, particularly in pyramidal two-point neurons (TPNs), has traditionally focused on the apical zone, which receives feedback (FB) connections from higher perceptual layers. This feedback is used for learning. However, recent advancements in cellular neurophysiology and computational neuroscience have revealed that the apical input, which includes feedback and lateral connections, is far more complex and diverse than previously understood. This multifaceted input, referred to as context, has significant implications for ongoing learning and processing in the…

Authors: Zijian Zhao、Tingwei Chen、Zhijie Cai、Hang Li、Xiaoyang Li、Qimei Chen、Guangxu Zhu Paper: https://arxiv.org/abs/2408.10919 Introduction In recent years, Wi-Fi sensing has emerged as a promising technology due to its advantages such as privacy protection, low cost, and penetration ability. This technology has been applied in various domains including gesture recognition, people identification, and fall detection. However, Wi-Fi sensing models often face challenges related to domain shift, where the model’s performance deteriorates in environments different from the training data. This issue is exacerbated by the limited availability of diverse Wi-Fi sensing datasets, leading to models that overfit to the training set and fail in…

Authors: Yongxin Deng、Xihe Qiu、Xiaoyu Tan、Jing Pan、Chen Jue、Zhijun Fang、Yinghui Xu、Wei Chu、Yuan Qi Paper: https://arxiv.org/abs/2408.10608 Introduction Large Language Models (LLMs) have revolutionized natural language processing by leveraging extensive text corpora to generate human-like text. However, these models often inherit biases present in their training data, leading to unfair and discriminatory outputs. This paper addresses the “implicit bias problem” in LLMs, where biases subtly influence model behavior across different demographic groups. The authors propose a novel framework, Bayesian-Theory based Bias Removal (BTBR), to identify and mitigate these biases using Bayesian inference. Related Work Previous research has highlighted the presence of biases in LLMs…

Authors: Zhiyang Qi、Michimasa Inaba Paper: https://arxiv.org/abs/2408.10516 Introduction Spoken Dialogue Systems (SDSs) have become a pivotal technology in artificial intelligence and speech processing, garnering significant attention from both academia and industry. Despite the advancements in large language models (LLMs), traditional SDSs remain a research focal point due to their superior control and interpretability. These systems are typically trained using data from human-to-human interactions, which exhibit varying speaking styles. This variability necessitates that human speakers adjust their dialogue strategies when engaging with different users, such as minors who often exhibit less clarity in their intentions and give ambiguous responses. However, adapting SDSs…

Authors: Arthur Cerveira、Frederico Kremer、Darling de Andrade Lourenço、Ulisses B Corrêa Paper: https://arxiv.org/abs/2408.10482 Introduction The field of drug discovery is undergoing a significant transformation with the advent of Artificial Intelligence (AI) techniques. These computational methods are increasingly being used to design and predict the properties of new therapeutic molecules. Traditional drug discovery methods often focus on single-target drugs, but this approach has limitations, especially for complex diseases like those affecting the central nervous system. Multi-target Drug Discovery (MTDD) aims to develop drugs that can modulate multiple targets simultaneously, offering potential advantages such as improved efficacy and reduced side effects. However, there is…

Authors: Yu Dian Lim、Hong Yu Li、Simon Chun Kiat Goh、Xiangyu Wang、Peng Zhao、Chuan Seng Tan Paper: https://arxiv.org/abs/2408.10287 Introduction Background Over the past decade, integrated silicon photonics (SiPh) gratings have been extensively developed for optical addressing in ion trap quantum computing. These gratings are crucial for guiding laser beams to trapped ion qubits, a fundamental component in quantum computing. However, accurately determining the heights at which beam profiles are located when viewed through infrared (IR) cameras remains a challenge. Problem Statement The difficulty in determining the corresponding heights of beam profiles from SiPh gratings when viewed through IR cameras poses a significant challenge.…

Authors: Andong Chen、Lianzhang Lou、Kehai Chen、Xuefeng Bai、Yang Xiang、Muyun Yang、Tiejun Zhao、Min Zhang Paper: https://arxiv.org/abs/2408.09945 Introduction The translation of classical Chinese poetry presents unique challenges due to its rich cultural and historical context, strict linguistic structure, and inherent aesthetic value. While large language models (LLMs) like ChatGPT have shown impressive performance in general translation tasks, the demand for translations that are not only adequate but also fluent and elegant has increased. This study introduces a benchmark specifically designed to evaluate the performance of LLMs in translating classical Chinese poetry into English, focusing on adequacy, fluency, and elegance. The study reveals that existing LLMs…

Authors: Kun Luo、Bowen Zheng、Shidong Lv、Jie Tao、Qiang Wei Paper: https://arxiv.org/abs/2408.09746 Introduction Prostate cancer is the second most common cancer and the fifth leading cause of cancer-related death among men worldwide. Early diagnosis is crucial for effective treatment and reducing mortality. Multiparametric magnetic resonance imaging (mpMRI) has become a popular non-invasive method for diagnosing prostate cancer, providing both anatomical and functional information. However, interpreting mpMRI requires significant expertise, highlighting the need for automated grading systems to assist radiologists. The study titled “Enhanced Cascade Prostate Cancer Classifier in mp-MRI Utilizing Recall Feedback Adaptive Loss and Prior Knowledge-Based Feature Extraction” addresses the challenges of…

Authors: Vamsi Krishna Pendyala、Hessam S. Sarjoughian、Bala Potineni、Edward J. Yellig Paper: https://arxiv.org/abs/2408.09307 Introduction The rapid advancements in high-computing devices have necessitated the development of smarter manufacturing factories, particularly in the semiconductor industry. Discrete-event models and simulators play a crucial role in designing, building, and operating semiconductor manufacturing processes. Machines such as diffusion, implantation, and lithography are integral to these processes, characterized by their complex feed-forward and feedback connectivity. The dataset derived from simulations of these factory models holds significant potential for generating valuable machine-learning models. These surrogate data-based models offer high efficiency compared to their physics-based counterparts. This research focuses on…

Authors: Angus Nicolson、Yarin Gal、J. Alison Noble Paper: https://arxiv.org/abs/2408.08652 TextCAVs: Debugging Vision Models Using Text Introduction Deep learning models are increasingly used in healthcare, where errors can have severe consequences. Interpretability, the ability to explain a model in human-understandable terms, is crucial for creating safer models. Concept-based interpretability methods, which use high-level human-interpretable concepts, are particularly useful. Traditional methods require labeled data for these concepts, which is expensive in medical domains. This paper introduces TextCAVs, a novel method that uses vision-language models like CLIP to create Concept Activation Vectors (CAVs) using text descriptions instead of image examples. This approach reduces the…