检索结果-内蒙古大学图书馆

28th International Joint Conference on Artificial Intelligence

作者： Yang, Cheng Tang, Jian Sun, Maosong Cui, Ganqu Liu, Zhiyuan Tsinghua Univ Dept Comp Sci & Technol Beijing Peoples R China Tsinghua Univ Inst Artificial Intelligence Beijing Peoples R China Tsinghua Univ State Key Lab Intelligent Technol & Syst Beijing Peoples R China Mila Quebec Inst Learning Algorithms Montreal PQ Canada HEC Montreal Montreal PQ Canada Canadian Inst Adv Res CIFAR Toronto ON Canada

ISBN: (纸本)9780999241141

Information diffusion prediction is an important task which studies how information items spread among users. With the success of deep learning techniques, recurrent neural networks (RNNs) have shown their powerful capability in modeling information diffusion as sequential data. However, previous works focused on either microscopic diffusion prediction which aims at guessing the next influenced user or macroscopic diffusion prediction which estimates the total numbers of influenced users during the diffusion process. To the best of our knowledge, no previous works have suggested a unified model for both microscopic and macroscopic scales. In this paper, we propose a novel multi-scale diffusion prediction model based on reinforcement learning (RL). RL incorporates the macroscopic diffusion size information into the RNN-based microscopic diffusion model by addressing the non-differentiable problem. We also employ an effective structural context extraction strategy to utilize the underlying social graph information. Experimental results show that our proposed model outperforms state-of-the-art baseline models on both microscopic and macroscopic diffusion predictions on three real-world datasets.

关键词：

来源：评论

学校读者我要写书评

暂无评论

HOW TRANSFERABLE ARE FEATURES IN CONVOLUTIONAL NEURAL NETWORK ACOUSTIC MODELS ACROSS LANGUAGES? 44

HOW TRANSFERABLE ARE FEATURES IN CONVOLUTIONAL NEURAL NETWOR...

引用

44th IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)

作者： Thompson, Jessica A. F. Schoenwiesner, Marc Bengio, Yoshua Willett, Daniel Univ Montreal Int Lab Brain Mus & Sound Res BRAMS Montreal PQ Canada Quebec Inst Learning Algorithms Mila Montreal PQ Canada CRBLM Montreal PQ Canada Univ Leipzig Inst Biol Leipzig Germany Nuance Commun Aachen Germany

ISBN: (纸本)9781479981311

Characterization of the representations learned in intermediate layers of deep networks can provide valuable insight into the nature of a task and can guide the development of well-tailored learning strategies. Here we study convolutional neural network (CNN)-based acoustic models in the context of automatic speech recognition. Adapting a method proposed by [1], we measure the transferability of each layer between English, Dutch and German to assess their language-specificity. We observed three distinct regions of transferability: (1) the first two layers were entirely transferable between languages, (2) layers 2-8 were also highly transferable but we found some evidence of language specificity, (3) the subsequent fully connected layers were more language specific but could be successfully finetuned to the target language. To further probe the effect of weight freezing, we performed follow-up experiments using freeze-training [2]. Our results are consistent with the observation that CNNs converge 'bottom up' during training and demonstrate the benefit of freeze training, especially for transfer learning.

关键词： CNNs acoustic modeling interpretability transfer learning language-specificity freeze training

来源：评论

学校读者我要写书评

暂无评论

Artificial intelligence and open science in discovery of disease-modifying medicines for Alzheimer's disease

引用

CELL REPORTS MEDICINE 2024年第2期5卷 101379-101379页

作者： Cheng, Feixiong Wang, Fei Tang, Jian Zhou, Yadi Fu, Zhimin Zhang, Pengyue Haines, Jonathan L. Leverenz, James B. Gan, Li Hu, Jianying Rosen-Zvi, Michal Pieper, Andrew A. Cummings, Jeffrey Cleveland Clin Genom Med Inst Lerner Res Inst Cleveland OH 44195 USA Cleveland Clin Lerner Res Inst Genome Ctr Cleveland OH 44195 USA Case Western Reserve Univ Cleveland Clin Dept Mol Med Lerner Coll Med Cleveland OH 44195 USA Cornell Univ Dept Populat Hlth Sci Weill Cornell Med Coll New York NY 10065 USA HEC Montreal Mila Quebec Inst Learning Algorithms Montreal PQ H3T 2A7 Canada HEC Montreal CIFAR AI Res Chair Montreal PQ H3T 2A7 Canada Northeast Ohio Med Univ Coll Pharm Rootstown OH 44272 USA Indiana Univ Dept Biostat & Hlth Data Sci Indianapolis IN 46037 USA Case Western Reserve Univ Cleveland Inst Computat Biol Cleveland OH 44106 USA Case Western Reserve Univ Dept Populat & Quantitat Hlth Sci Cleveland OH 44106 USA Cleveland Clin Neurol Inst Lou Ruvo Ctr Brain Hlth Cleveland OH 44195 USA Weill Cornell Med Helen & Robert Appel Alzheimers Dis Res Inst Brain & Mind Res Inst New York NY 10021 USA IBM Res Yorktown Hts NY 10598 USA IBM Res Labs AI Accelerated Healthcare & Life Sci Discovery IL-3498825 Haifa Israel Hebrew Univ Jerusalem Fac Med IL-9190500 Jerusalem Israel Univ Hosp Cleveland Harrington Discovery Inst Brain Hlth Med Ctr Med Ctr Cleveland OH 44106 USA Case Western Reserve Univ Dept Psychiat Cleveland OH 44106 USA Louis Stokes Cleveland VA Med Ctr Geriatr Psychiat GRECC Cleveland OH 44106 USA Case Western Reserve Univ Sch Med Inst Transformat Mol Med Cleveland OH 44106 USA Case Western Reserve Univ Sch Med Dept Pathol Cleveland OH 44106 USA Case Western Reserve Univ Sch Med Dept Neurosci Cleveland OH 44106 USA UNLV Sch Integrated Hlth Sci Dept Brain Hlth Chambers Grundy Ctr Transformat Neurosci Las Vegas NV 89154 USA

The high failure rate of clinical trials in Alzheimer's disease (AD) and AD-related dementia (ADRD) is due to a lack of understanding of the pathophysiology of disease, and this deficit may be addressed by applying artificial intelligence (AI) to ''big data'' to rapidly and effectively expand therapeutic development efforts. Recent accelerations in computing power and availability of big data, including electronic health records and multiomics profiles, have converged to provide opportunities for scientific discovery and treatment development. Here, we review the potential utility of applying AI approaches to big data for discovery of disease-modifying medicines for AD/ADRD. We illustrate how AI tools can be applied to the AD/ADRD drug development pipeline through collaborative efforts among neurologists, gerontologists, geneticists, pharmacologists, medicinal chemists, and computational scientists. AI and open data science expedite drug discovery and development of disease-modifying therapeutics for AD/ADRD and other neurodegenerative diseases.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Mutual Information Neural Estimation 35

Mutual Information Neural Estimation

引用

35th International Conference on Machine learning (ICML)

作者： Belghazi, Mohamed Ishmael Baratin, Aristide Rajeswar, Sai Ozair, Sherjil Bengio, Yoshua Courville, Aaron Hjelm, R. Devon Univ Montreal Montreal Inst Learning Algorithms MILA Montreal PQ Canada McGill Univ Dept Math & Stat Montreal PQ Canada Canadian Inst Adv Res CIFAR Toronto ON Canada Inst Data Valorizat IVADO Montreal PQ Canada

ISBN: (纸本)9781510867963

We argue that the estimation of mutual information between high dimensional continuous random variables can be achieved by gradient descent over neural networks. We present a Mutual Information Neural Estimator (MINE) that is linearly scalable in dimensionality as well as in sample size, trainable through back-prop, and strongly consistent. We present a handful of applications on which MINE can be used to minimize or maximize mutual information. We apply MINE to improve adversarially trained generative models. We also use MINE to implement the Information Bottleneck, applying it to supervised classification;our results demonstrate substantial improvement in flexibility and performance in these settings.

关键词： Classification (of information)

来源：评论

学校读者我要写书评

暂无评论

Scaling behavior in measured keystroke time series from patients with Parkinson's disease

引用

EUROPEAN PHYSICAL JOURNAL B 2020年第7期93卷 126-126页

作者： Madanchi, Ata Taghavi-Shahri, Fatemeh Taghavi-Shahri, Seyed Mahmood Tabar, Mohammed Reza Rahimi McGill Univ Dept Phys Montreal PQ H3A 2T8 Canada Montreal Inst Learning Algorithms MILA Montreal PQ H2S 3H1 Canada Ferdowsi Univ Mashhad Dept Phys POB 1436 Mashhad Razavi Khorasan Iran Isfahan Univ Med Sci Sch Publ Hlth Dept Epidemiol & Biostat Esfahan Iran Sharif Univ Technol Dept Phys Tehran 111559161 Iran Carl von Ossietzky Univ Oldenburg Inst Phys D-26111 Oldenburg Germany Carl von Ossietzky Univ Oldenburg ForWind D-26111 Oldenburg Germany

Parkinson has remained as one of the most difficult diseases to diagnose, as there are no biomarkers to be measured, and this requires one patient to do neurological and physical examinations. As Parkinson is a progressive disease, accurate detection of its symptoms is a crucial factor for therapeutic reasons. In this study, we perform Multifractal Detrended Fluctuation Analysis (MFDFA) on measured keystroke time series for three different categories of subjects: healthy, early-PD, and De-Novo patients. We have observed different scaling behavior in terms of multifractality of the measured time series, which can be used as a practical tool for diagnosis purposes. Additionally, the source of the multifractality has been studied which shows that in healthy and early-PD subjects, multifractality due to the long-range correlations is stronger than the influence of its probability distribution function (PDF) fatness, while in De-Novo patients, both shape of PDF and long-range correlations are contributing to observed multifractality.

关键词： Statistical and Nonlinear Physics

来源：评论

学校读者我要写书评

暂无评论

A Two-Engine interaction driven many-objective evolutionary algorithm with feasibility-aware adaptation

引用

APPLIED SOFT COMPUTING 2019年 82卷 105588-000页

作者： Ge, Hongwei Zhao, Mingde Zhang, Kai Hou, Yaqing Dalian Univ Technol Coll Comp Sci & Technol Dalian Liaoning Peoples R China Montreal Inst Learning Algorithms Mila Montreal PQ Canada McGill Univ Sch Comp Sci Montreal PQ Canada Washington Univ Dept Comp Sci & Engn St Louis MO 63110 USA Nanyang Technol Univ Sch Comp Sci & Engn Singapore Singapore

The infeasible parts of the objective space in many-objective optimization problems make evolutionary algorithms face difficulties in obtaining proximity and maintaining diversity simultaneously. This paper proposes a Two-Engine interaction driven many-objective Evolutionary Algorithm with feasibility-aware adaptation (TEEA) that adapts the reference vectors and evolves the population towards the true Pareto Front (PF). The two interacting engines make reference vectors always approximately evenly distributed within the current PF for providing appropriate guidance for selection. The current PF is tracked by maintaining an Individual Archive (IA) of undominated individuals, and the adaptation of reference vectors is conducted with the help of a Reference Archive (RA) that contains layers of reference vectors corresponding to different density. On CEC'2018 benchmark functions with competition standards, the experimental results of the proposed TEEA have demonstrated the expected characteristics and competitive performance. (C) 2019 Elsevier B.V. All rights reserved.

关键词： Many-objective optimization Reference vector Feasible objective space Interaction Adaptation

来源：评论

学校读者我要写书评

暂无评论

Deep generative molecular design reshapes drug discovery

引用

CELL REPORTS MEDICINE 2022年第12期3卷 100794-100794页

作者： Zeng, Xiangxiang Wang, Fei Luo, Yuan Kang, Seung-Gu Tang, Jian Lightstone, Felice C. Fang, Evandro F. Cornell, Wendy Nussinov, Ruth Cheng, Feixiong Hunan Univ Coll Comp Sci & Elect Engn Changsha 410082 Hunan Peoples R China Cornell Univ Weill Cornell Med Coll Dept Populat Hlth Sci New York NY 10065 USA Northwestern Univ Feinberg Sch Med Dept Prevent Med Div Hlth & Biomed Informat Chicago IL 60611 USA Ibm TJ Watson Res Ctr Healthcare & Life Sci Res 1101 Kitchawan Rd Yorktown Hts NY 10598 USA HEC Montreal Mila Quebec Inst Learning Algorithms Montreal PQ H3T 2A7 Canada HEC Montreal CIFAR AI Res Chair Montreal PQ H3T 2A7 Canada Lawrence Livermore Natl Lab Biosci & Biotechnol Div Phys & Life Sci Directorate Livermore CA 94550 USA Univ Oslo Dept Clin Mol Biol N-1478 Oslo Norway Akershus Univ Hosp N-1478 Oslo Norway Norwegian Ctr Hlth NO Ageing Age Oslo Norway NCI Computat Struct Biol Sect Frederick Natl Lab Canc Res Lab Canc Immunometab Frederick MD 21702 USA Tel Aviv Univ Sackler Sch Med Dept Human Mol Genet & Biochem IL-69978 Tel Aviv Israel Cleveland Clin Lerner Res Inst Genom Med Inst Cleveland OH 44195 USA Case Western Reserve Univ Cleveland Clin Dept Mol Med Lerner Coll Med Cleveland OH 44195 USA Case Western Reserve Univ Case Comprehens Canc Ctr Sch Med Cleveland OH 44106 USA

Recent advances and accomplishments of artificial intelligence (AI) and deep generative models have established their usefulness in medicinal applications, especially in drug discovery and development. To correctly apply AI, the developer and user face questions such as which protocols to consider, which factors to scrutinize, and how the deep generative models can integrate the relevant disciplines. This review summarizes classical and newly developed AI approaches, providing an updated and accessible guide to the broad computational drug discovery and development community. We introduce deep generative models from different standpoints and describe the theoretical frameworks for representing chemical and biological structures and their applications. We discuss the data and technical challenges and highlight future directions of multimodal deep generative models for accelerating drug discovery.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Predictive Pattern Classification Can Distinguish Gender Identity Subtypes from Behavior and Brain Imaging

引用

CEREBRAL CORTEX 2020年第5期30卷 2755-2765页

作者： Clemens, Benjamin Derntl, Birgit Smith, Elke Junger, Jessica Neulen, Josef Mingoia, Gianluca Schneider, Frank Abel, Ted Bzdok, Danilo Habel, Ute Rhein Westfal TH Aachen Dept Psychiat Psychotherapy & Psychosomat Fac Med Pauwelsstr 30 D-52074 Aachen Germany JARA Inst Brain Struct Funct Relationship INM 10 Inst Neurosci & Med Wilhelm Johnen Str D-52425 Julich Germany Univ Tubingen Dept Psychiat & Psychotherapy D-72076 Tubingen Germany Univ Tubingen Werner Reichardt Ctr Integrat Neurosci CIN Otfried Muller Str 25 D-72076 Tubingen Germany LEAD Res Network Walter Simon Str 12 D-72072 Tubingen Germany Rhein Westfal TH Aachen Fac Med Dept Gynecol Endocrinol & Reprod Med D-52074 Aachen Germany Rhein Westfal TH Aachen Fac Med Interdisciplinary Ctr Clin Res IZKF Pauwelsstr 30 D-52074 Aachen Germany Univ Penn Dept Biol 433 South Univ Ave Philadelphia PA 19104 USA Univ Iowa Carver Coll Med Iowa Neurosci Inst Dept Neurosci & Pharmacol 51 Newton Rd 5-660 Bowen Sci Bldg Iowa City IA 52242 USA INRIA Neurospin Saclay Parietal Team 1 Rue Honore Estienne OrvesCampus Ecole Polytech F-91120 Palaiseau France McGill Univ Dept Biomed Engn Fac Med 3775 Rue Univ Montreal PQ H3A 2B4 Canada Montreal Inst Learning Algorithms MILA 6666 St Urbain 200 Montreal PQ H2S 3H1 Canada Heinrich Heine Univ Dusseldorf Univ Hosp Dusseldorf Moorenstr 5 D-40225 Dusseldorf Germany Univ Cologne Dept Psychol Biol Psychol Bernhard Feilchenfeld Str 11 D-50969 Cologne Germany

The exact neurobiological underpinnings of gender identity (i.e., the subjective perception of oneself belonging to a certain gender) still remain unknown. Combining both resting-state functional connectivity and behavioral data, we examined gender identity in cisgender and transgender persons using a data-driven machine learning strategy. Intrinsic functional connectivity and questionnaire data were obtained from cisgender (men/women) and transgender (trans men/trans women) individuals. Machine learning algorithms reliably detected gender identity with high prediction accuracy in each of the four groups based on connectivity signatures alone. The four normative gender groups were classified with accuracies ranging from 48% to 62% (exceeding chance level at 25%). These connectivity-based classification accuracies exceeded those obtained from a widely established behavioral instrument for gender identity. Using canonical correlation analyses, functional brain measurements and questionnaire data were then integrated to delineate nine canonical vectors (i.e., brain-gender axes), providing a multilevel window into the conventional sex dichotomy. Our dimensional gender perspective captures four distinguishable brain phenotypes for gender identity, advocating a biologically grounded reconceptualization of gender dimorphism. We hope to pave the way towards objective, data-driven diagnostic markers for gender identity and transgender, taking into account neurobiological and behavioral differences in an integrative modeling approach.

关键词： fMRI gender identity machine learning resting-state functional connectivity transgender

来源：评论

学校读者我要写书评

暂无评论

Guest Editorial: Deep learning in Computer Vision

引用

IET COMPUTER VISION 2017年第8期11卷 621-622页

作者： Hospedales, Timothy Romero, Adriana Vazquez, David Univ Edinburgh Image & Vis Comp Sch Informat Edinburgh Midlothian Scotland Queen Mary Univ London Sch Elect Engn & Comp Sci London England Univ Montreal Montreal Inst Learning Algorithms Montreal PQ Canada Comp Vis Ctr Barcelona CVC Barcelona Spain MILA Montreal PQ Canada Autonomous Univ Barcelona UAB Dept Comp Sci Barcelona Spain

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：