ArXiv Pub Date : 2024-02-15 DOI: 10.48550/arXiv.2402.09792

S. Shrivastava, A. Biswas, S. Chakrabarty, G. Dash, V. Saraswat, U. Ganguly

{"title":"System-level Impact of Non-Ideal Program-Time of Charge Trap Flash (CTF) on Deep Neural Network","authors":"S. Shrivastava, A. Biswas, S. Chakrabarty, G. Dash, V. Saraswat, U. Ganguly","doi":"10.48550/arXiv.2402.09792","DOIUrl":"https://doi.org/10.48550/arXiv.2402.09792","url":null,"abstract":"Learning of deep neural networks (DNN) using Resistive Processing Unit (RPU) architecture is energy-efficient as it utilizes dedicated neuromorphic hardware and stochastic computation of weight updates for in-memory computing. Charge Trap Flash (CTF) devices can implement RPU-based weight updates in DNNs. However, prior work has shown that the weight updates (V_T) in CTF-based RPU are impacted by the non-ideal program time of CTF. The non-ideal program time is affected by two factors of CTF. Firstly, the effects of the number of input pulses (N) or pulse width (pw), and secondly, the gap between successive update pulses (t_gap) used for the stochastic computation of weight updates. Therefore, the impact of this non-ideal program time must be studied for neural network training simulations. In this study, Firstly, we propose a pulse-train design compensation technique to reduce the total error caused by non-ideal program time of CTF and stochastic variance of a network. Secondly, we simulate RPU-based DNN with non-ideal program time of CTF on MNIST and Fashion-MNIST datasets. We find that for larger N (~1000), learning performance approaches the ideal (software-level) training level and, therefore, is not much impacted by the choice of t_gap used to implement RPU-based weight updates. However, for lower N (<500), learning performance depends on T_gap of the pulses. Finally, we also performed an ablation study to isolate the causal factor of the improved learning performance. We conclude that the lower noise level in the weight updates is the most likely significant factor to improve the learning performance of DNN. Thus, our study attempts to compensate for the error caused by non-ideal program time and standardize the pulse length (N) and pulse gap (t_gap) specifications for CTF-based RPUs for accurate system-level on-chip training.","PeriodicalId":8425,"journal":{"name":"ArXiv","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2024-02-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139962495","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

TOAD: Task-Oriented Automatic Dialogs with Diverse Response Styles TOAD：以任务为导向、响应风格多样的自动对话框

ArXiv Pub Date : 2024-02-15 DOI: 10.48550/arXiv.2402.10137

Yinhong Liu, Yimai Fang, David Vandyke, Nigel Collier

引用次数: 0

User Privacy Harms and Risks in Conversational AI: A Proposed Framework 人工智能对话中的用户隐私危害与风险：一个拟议框架

ArXiv Pub Date : 2024-02-15 DOI: 10.48550/arXiv.2402.09716

Ece Gumusel, Kyrie Zhixuan Zhou, M. Sanfilippo

引用次数: 0

A Systematic Evaluation of Evolving Highly Nonlinear Boolean Functions in Odd Sizes 对奇数大小高度非线性布尔函数进化的系统评估

ArXiv Pub Date : 2024-02-15 DOI: 10.48550/arXiv.2402.09937

C. Carlet, Marko Ðurasevic, D. Jakobović, S. Picek, L. Mariot

{"title":"A Systematic Evaluation of Evolving Highly Nonlinear Boolean Functions in Odd Sizes","authors":"C. Carlet, Marko Ðurasevic, D. Jakobović, S. Picek, L. Mariot","doi":"10.48550/arXiv.2402.09937","DOIUrl":"https://doi.org/10.48550/arXiv.2402.09937","url":null,"abstract":"Boolean functions are mathematical objects used in diverse applications. Different applications also have different requirements, making the research on Boolean functions very active. In the last 30 years, evolutionary algorithms have been shown to be a strong option for evolving Boolean functions in different sizes and with different properties. Still, most of those works consider similar settings and provide results that are mostly interesting from the evolutionary algorithm's perspective. This work considers the problem of evolving highly nonlinear Boolean functions in odd sizes. While the problem formulation sounds simple, the problem is remarkably difficult, and the related work is extremely scarce. We consider three solutions encodings and four Boolean function sizes and run a detailed experimental analysis. Our results show that the problem is challenging, and finding optimal solutions is impossible except for the smallest tested size. However, once we added local search to the evolutionary algorithm, we managed to find a Boolean function in nine inputs with nonlinearity 241, which, to our knowledge, had never been accomplished before with evolutionary algorithms.","PeriodicalId":8425,"journal":{"name":"ArXiv","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2024-02-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139962645","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Exploiting Alpha Transparency In Language And Vision-Based AI Systems 在基于语言和视觉的人工智能系统中利用阿尔法透明度

ArXiv Pub Date : 2024-02-15 DOI: 10.48550/arXiv.2402.09671

David A. Noever, Forrest McKee

引用次数: 0

User Modeling and User Profiling: A Comprehensive Survey 用户建模和用户分析：全面调查

ArXiv Pub Date : 2024-02-15 DOI: 10.48550/arXiv.2402.09660

Erasmo Purificato, Ludovico Boratto, Ernesto William De Luca

{"title":"User Modeling and User Profiling: A Comprehensive Survey","authors":"Erasmo Purificato, Ludovico Boratto, Ernesto William De Luca","doi":"10.48550/arXiv.2402.09660","DOIUrl":"https://doi.org/10.48550/arXiv.2402.09660","url":null,"abstract":"The integration of artificial intelligence (AI) into daily life, particularly through information retrieval and recommender systems, has necessitated advanced user modeling and profiling techniques to deliver personalized experiences. These techniques aim to construct accurate user representations based on the rich amounts of data generated through interactions with these systems. This paper presents a comprehensive survey of the current state, evolution, and future directions of user modeling and profiling research. We provide a historical overview, tracing the development from early stereotype models to the latest deep learning techniques, and propose a novel taxonomy that encompasses all active topics in this research area, including recent trends. Our survey highlights the paradigm shifts towards more sophisticated user profiling methods, emphasizing implicit data collection, multi-behavior modeling, and the integration of graph data structures. We also address the critical need for privacy-preserving techniques and the push towards explainability and fairness in user modeling approaches. By examining the definitions of core terminology, we aim to clarify ambiguities and foster a clearer understanding of the field by proposing two novel encyclopedic definitions of the main terms. Furthermore, we explore the application of user modeling in various domains, such as fake news detection, cybersecurity, and personalized education. This survey serves as a comprehensive resource for researchers and practitioners, offering insights into the evolution of user modeling and profiling and guiding the development of more personalized, ethical, and effective AI systems.","PeriodicalId":8425,"journal":{"name":"ArXiv","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2024-02-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139962669","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Is Continual Learning Ready for Real-world Challenges? 持续学习能否应对现实世界的挑战？

ArXiv Pub Date : 2024-02-15 DOI: 10.48550/arXiv.2402.10130

Theodora Kontogianni, Yuanwen Yue, Siyu Tang, Konrad Schindler

引用次数: 0

Jack of All Trades, Master of Some, a Multi-Purpose Transformer Agent 多才多艺的变压器代理商

ArXiv Pub Date : 2024-02-15 DOI: 10.48550/arXiv.2402.09844

Quentin Gallou'edec, Edward Beeching, Cl'ement Romac, Emmanuel Dellandr'ea

引用次数: 0

Towards Reducing Diagnostic Errors with Interpretable Risk Prediction 通过可解释的风险预测减少诊断错误

ArXiv Pub Date : 2024-02-15 DOI: 10.48550/arXiv.2402.10109

Denis Jered McInerney, William Dickinson, Lucy Flynn, Andrea Young, Geoffrey Young, J.-W. van de Meent, Byron C. Wallace

{"title":"Towards Reducing Diagnostic Errors with Interpretable Risk Prediction","authors":"Denis Jered McInerney, William Dickinson, Lucy Flynn, Andrea Young, Geoffrey Young, J.-W. van de Meent, Byron C. Wallace","doi":"10.48550/arXiv.2402.10109","DOIUrl":"https://doi.org/10.48550/arXiv.2402.10109","url":null,"abstract":"Many diagnostic errors occur because clinicians cannot easily access relevant information in patient Electronic Health Records (EHRs). In this work we propose a method to use LLMs to identify pieces of evidence in patient EHR data that indicate increased or decreased risk of specific diagnoses; our ultimate aim is to increase access to evidence and reduce diagnostic errors. In particular, we propose a Neural Additive Model to make predictions backed by evidence with individualized risk estimates at time-points where clinicians are still uncertain, aiming to specifically mitigate delays in diagnosis and errors stemming from an incomplete differential. To train such a model, it is necessary to infer temporally fine-grained retrospective labels of eventual\"true\"diagnoses. We do so with LLMs, to ensure that the input text is from before a confident diagnosis can be made. We use an LLM to retrieve an initial pool of evidence, but then refine this set of evidence according to correlations learned by the model. We conduct an in-depth evaluation of the usefulness of our approach by simulating how it might be used by a clinician to decide between a pre-defined list of differential diagnoses.","PeriodicalId":8425,"journal":{"name":"ArXiv","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2024-02-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139962951","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Classification Diffusion Models 分类扩散模型

ArXiv Pub Date : 2024-02-15 DOI: 10.48550/arXiv.2402.10095

Shahar Yadin, Noam Elata, T. Michaeli

{"title":"Classification Diffusion Models","authors":"Shahar Yadin, Noam Elata, T. Michaeli","doi":"10.48550/arXiv.2402.10095","DOIUrl":"https://doi.org/10.48550/arXiv.2402.10095","url":null,"abstract":"A prominent family of methods for learning data distributions relies on density ratio estimation (DRE), where a model is trained to $textit{classify}$ between data samples and samples from some reference distribution. These techniques are successful in simple low-dimensional settings but fail to achieve good results on complex high-dimensional data, like images. A different family of methods for learning distributions is that of denoising diffusion models (DDMs), in which a model is trained to $textit{denoise}$ data samples. These approaches achieve state-of-the-art results in image, video, and audio generation. In this work, we present $textit{Classification Diffusion Models}$ (CDMs), a generative technique that adopts the denoising-based formalism of DDMs while making use of a classifier that predicts the amount of noise added to a clean signal, similarly to DRE methods. Our approach is based on the observation that an MSE-optimal denoiser for white Gaussian noise can be expressed in terms of the gradient of a cross-entropy-optimal classifier for predicting the noise level. As we illustrate, CDM achieves better denoising results compared to DDM, and leads to at least comparable FID in image generation. CDM is also capable of highly efficient one-step exact likelihood estimation, achieving state-of-the-art results among methods that use a single step. Code is available on the project's webpage in https://shaharYadin.github.io/CDM/ .","PeriodicalId":8425,"journal":{"name":"ArXiv","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2024-02-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139962999","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

ArXiv最新文献