Henry Kautz

Since its birth in the 1940s, the field of artificial intelligence has been divided into two camps, one focused on artificial neural networks and the other on reasoning with symbolic representations of knowledge. The symbolic representational approach firmly dominated the field until 2012, when a neural network named ‘AlexNet’handily won an algorithm competition for recognizing objects in images (Krizhevsky et al., 2012). Further convincing successes of neural network algorithms for speech recognition, the game of Go (Silver et al., 2017), and other problems that had long eluded the KR approach soon followed. Today, neural networks, under the banner of ‘deep learning’, where ‘deep’refers to the fact that the artificial neurons are arranged in many layers, dominate research and commercial applications. Most students studying AI learn little about knowledge representation, and the approach is rarely mentioned in …

This article summarizes the author's Robert S. Englemore Memorial Lecture presented at the Thirty-Fourth AAAI Conference on Artificial Intelligence on February 10, 2020. It explores recurring themes in the history of AI, real and imagined dangers from AI, and the future of the field.

In the work developed in Bassolas et al. 1, we studied the structure of cities and their impact in city livability using a highly aggregated mobility dataset. In order to protect privacy, random noise was added using an automated Laplace mechanism (ε, δ)-differential privacy, with ε= 0.66 and δ= 2.1× 10− 29. Where ε sets the noise intensity and δ stands for the deviation from pure ε-privacy.To illustrate the protection provided by a layer of (ε, δ)-differential privacy, with ε= 0.66 and δ= 2.1× 10− 29, we note that an attacker can improve their certainty about an individual’s presence or absence in the dataset by at most 16%. This observation holds even if the attacker knows every individual’s data, including that of the target, via some side channel. An attack model like this is known as membership inference with perfect

ResultsUsing Bassolas et al.’s attack model on a real-world mobility dataset, we show the empirical risk to be higher than the 16% bound as soon as the victim took more than three unique trips over any week (p 3 (u)= 70.5%). Figure 1 reports the accuracy of the membership attack, p k (u), the likelihood that an attacker can test if u is in the aggregated data knowing k trips from their trajectory. The average number of trips per user in Bassolas et al.’s dataset is not reported but, looking at the Google Maps Timeline 2 of one of us, the 39 trips taken over a typical week with 32 of them being unique would give an attacker a 95.4% certainty that he is in the dataset.

Intimate partner violence is a public health problem with increasing prevalence and harmful influence to both individuals and society. Automated screening for intimate partner violence is still an unsolved problem in academic research and practical applications. Current detection methods use self-reporting scales and in-person interviews, which are laborious, expensive, and often lack precision and sensitivity, making it essential to develop new approaches. This paper proposes a scalable and lightweight ubiquitous screening technique, validated via ground truth data collected through self assessment survey, for detecting signs of intimate partner violence by analyzing individual-level Google search histories. Initial analysis shows that there are temporal, textual, contextual differences in search behavior between individuals who have/haven't experienced intimate partner violence. Using these differentiating signals …

Objective We developed a digital scribe for automatic medical documentation by utilizing elements of patient-centered communication. Excessive time spent on medical documentation may contribute to physician burnout. Patient-centered communication may improve patient satisfaction, reduce malpractice rates, and decrease diagnostic testing expenses. We demonstrate that patient-centered communication may allow providers to simultaneously talk to patients and efficiently document relevant information. Materials and Methods We utilized two elements of patient-centered communication to document patient history. One element was summarizing, which involved providers recapping information to confirm an accurate understanding of the patient. Another element was signposting, which involved providers using transition questions and statements to guide the conversation …

We present a simple yet highly generalizable method for explaining interacting parts within a neural network's reasoning process. First, we design an algorithm based on cross derivatives for computing statistical interaction effects between individual features, which is generalized to both 2-way and higher-order (3-way or more) interactions. We present results side by side with a weight-based attribution technique, corroborating that cross derivatives are a superior metric for both 2-way and higher-order interaction detection. Moreover, we extend the use of cross derivatives as an explanatory device in neural networks to the computer vision setting by expanding Grad-CAM, a popular gradient-based explanatory tool for CNNs, to the higher order. While Grad-CAM can only explain the importance of individual objects in images, our method, which we call Taylor-CAM, can explain a neural network's relational reasoning across multiple objects. We show the success of our explanations both qualitatively and quantitatively, including with a user study. We will release all code as a tool package to facilitate explainable deep learning.

Given the rapid recent trend of urbanization, a better understanding of how urban infrastructure mediates socioeconomic interactions and economic systems is of vital importance. While the accessibility of location-enabled devices as well as large-scale datasets of human activities, has fueled significant advances in our understanding, there is little agreement on the linkage between socioeconomic status and its influence on movement patterns, in particular, the role of inequality. Here, we analyze a heavily aggregated and anonymized summary of global mobility and investigate the relationships between socioeconomic status and mobility across a hundred cities in the US and Brazil. We uncover two types of relationships, finding either a clear connection or little-to-no interdependencies. The former tend to be characterized by low levels of public transportation usage, inequitable access to basic amenities and …

Mental health problems among the global population are worsened during the coronavirus disease (COVID-19). How individuals engage with online platforms such as Google Search and YouTube undergoes drastic shifts due to pandemic and subsequent lockdowns. Such ubiquitous daily behaviors on online platforms have the potential to capture and correlate with clinically alarming deteriorations in mental health profiles in a non-invasive manner. The goal of this study is to examine, among college students, the relationship between deteriorating mental health conditions and changes in user behaviors when engaging with Google Search and YouTube during COVID-19. This study recruited a cohort of 49 students from a U.S. college campus during January 2020 (prior to the pandemic) and measured the anxiety and depression levels of each participant. This study followed up with the same cohort during May 2020 (during the pandemic), and the anxiety and depression levels were assessed again. The longitudinal Google Search and YouTube history data were anonymized and collected. From individual-level Google Search and YouTube histories, we developed 5 signals that can quantify shifts in online behaviors during the pandemic. We then assessed the differences between groups with and without deteriorating mental health profiles in terms of these features. Significant features included late-night online activities, continuous usages, and time away from the internet, porn consumptions, and keywords associated with negative emotions, social activities, and personal affairs. Though further studies are required, our results demonstrated …

Nighttime lights satellite imagery has been used for decades as a uniform, global source of data for studying a wide range of socioeconomic factors. Recently, another more terrestrial source is producing data with similarly uniform global coverage: anonymous and aggregated smart phone location. This data, which measures the movement patterns of people and populations rather than the light they produce, could prove just as valuable in decades to come. In fact, since human mobility is far more directly related to the socioeconomic variables being predicted, it has an even greater potential. Additionally, since cell phone locations can be aggregated in real time while preserving individual user privacy, it will be possible to conduct studies that would previously have been impossible because they require data from the present. Of course, it will take quite some time to establish the new techniques necessary to apply human mobility data to problems traditionally studied with satellite imagery and to conceptualize and develop new real time applications. In this study we demonstrate that it is possible to accelerate this process by inferring artificial nighttime satellite imagery from human mobility data, while maintaining a strong differential privacy guarantee. We also show that these artificial maps can be used to infer socioeconomic variables, often with greater accuracy than using actual satellite imagery. Along the way, we find that the relationship between mobility and light emissions is both nonlinear and varies considerably around the globe. Finally, we show that models based on human mobility can significantly improve our understanding of society …

This paper describes the SemEval-2020 shared task "Assessing Humor in Edited News Headlines." The task's dataset contains news headlines in which short edits were applied to make them funny, and the funniness of these edited headlines was rated using crowdsourcing. This task includes two subtasks, the first of which is to estimate the funniness of headlines on a humor scale in the interval 0-3. The second subtask is to predict, for a pair of edited versions of the same original headline, which is the funnier version. To date, this task is the most popular shared computational humor task, attracting 48 teams for the first subtask and 31 teams for the second.

On June 4-6, 2019, the NSTC NITRD Program, in collaboration with NSTC’s MLAI Subcommittee, held a workshop to assess the research challenges and opportunities at the intersection of cybersecurity and artificial intelligence. The workshop brought together senior members of the government, academic, and industrial communities to discuss the current state of the art and future research needs, and to identify key research gaps.This report is a summary of those discussions,framed around research questions and possible topics for future research directions.

Anxiety disorder is one of the world's most prevalent mental health conditions, arising from complex interactions of biological and environmental factors and severely interfering one's ability to lead normal life activities. Current methods for detecting anxiety heavily rely on in-person interviews, which can be expensive, time-consuming, and blocked by social stigmas. In this work, we propose an alternative method to identify individuals with anxiety and further estimate their levels of anxiety using personal online activity histories from YouTube and the Google Search engine, platforms that are used by millions of people daily. We ran a longitudinal study and collected multiple rounds of anonymized YouTube and Google Search logs from volunteering participants, along with their clinically validated ground-truth anxiety assessment scores. We then developed explainable features that capture both the temporal and contextual aspects of online behaviors. Using those, we were able to train models that (i) identify individuals having anxiety disorder with an average F1 score of 0.83 and (ii) assess the level of anxiety by predicting the gold standard Generalized Anxiety Disorder 7-item scores (ranges from 0 to 21) with a mean square error of 1.87 based on the ubiquitous individual-level online engagement data. Our proposed anxiety assessment framework is cost-effective, time-saving, scalable, and opens the door for it to be deployed in real-world clinical settings, empowering care providers and therapists to learn about anxiety disorders of patients non-invasively at any moment in time.

Building datasets of creative text, such as humor, is quite challenging. We introduce FunLines, a competitive game where players edit news headlines to make them funny, and where they rate the funniness of headlines edited by others. FunLines makes the humor generation process fun, interactive, collaborative, rewarding and educational, keeping players engaged and providing humor data at a very low cost compared to traditional crowdsourcing approaches. FunLines offers useful performance feedback, assisting players in getting better over time at generating and assessing humor, as our analysis shows. This helps to further increase the quality of the generated dataset. We show the effectiveness of this data by training humor classification models that outperform a previous benchmark, and we release this dataset to the public.

Portmanteaus are new words formed by combining the sounds and meanings of two words. Given their sticky nature, portmanteaus are often used to create political and personal attacks by combining a target entity with derogatory terms, which can then be spread online for promoting hate speech and defamation. In this paper, we present a framework to decompose political portmanteaus used online into their component words. Using our annotated dataset of political portmanteaus, we train a system that correctly decomposes 76.2% of the political portmanteaus into their component words. Furthermore, for 93.4% of the political portmanteaus, our system finds the correct component words in its top ten results, suggesting that using better ranking methods can lead to stronger results. This work provides a framework for both understanding an intriguing linguistic phenomena and for building hate-speech filters that could catch novel words that would bypass traditional hate speech detection approaches.

Background: Depression and anxiety disorders among the global population have worsened during the COVID-19 pandemic. Yet, current methods for screening these two issues rely on in-person interviews, which can be expensive, time-consuming, and blocked by social stigma and quarantines. Meanwhile, how individuals engage with online platforms such as Google Search and YouTube has undergone drastic shifts due to COVID-19 and subsequent lockdowns. Such ubiquitous daily behaviors on online platforms have the potential to capture and correlate with clinically alarming deteriorations in depression and anxiety profiles of users in a noninvasive manner.Objective: The goal of this study is to examine, among college students in the United States, the relationships of deteriorating depression and anxiety conditions with the changes in user behaviors when engaging with Google Search and YouTube during COVID-19.Methods: This study recruited a cohort of undergraduate students (N= 49) from a US college campus during January 2020 (prior to the pandemic) and measured the anxiety and depression levels of each participant. The anxiety level was assessed via the General Anxiety Disorder-7 (GAD-7). The depression level was assessed via the Patient Health Questionnaire-9 (PHQ-9). This study followed up with the same cohort during May 2020 (during the pandemic), and the anxiety and depression levels were assessed again. The longitudinal Google Search and YouTube history data of all participants were anonymized and collected. From individual-level Google Search and YouTube histories, we developed 5 features that can …

This paper presents the conflict-driven clause-learning (CLDL) SAT solver CryptoMiniSat (CMS) augmented with the Stochastic Local Search (SLS)[11] solver WalkSAT v56 as submitted to SAT Competition 2020. CryptoMiniSat aims to be a modern, open source SAT solver using inprocessing techniques, optimized data structures and finely-tuned timeouts to have good control over both memory and time usage of inprocessing steps. CryptoMiniSat is authored by Mate Soos. WalkSAT [8] is a standard system to solve satisfiability problems using Stochastic Local Search. The version inside CryptoMiniSat is functionally equivalent to the “rnovelity” heuristic of WalkSAT v56 using an adaptive noise heuristic [6]. It behaves exactly as WalkSAT with the minor modification of performing early-abort in case the “lowbad” statistic (ie the quality indicator of the current best solution) indicates the solution is far. In these cases, we early abort, let the CDCL solver work longer to simplify the problem, and come back to WalkSAT later. The only major modification to WalkSAT has been to allow it to import variables and clauses directly from the main solver taking into account assumptions given by the user.

MIND | CiNii Research CiNii 国立情報学研究所 学術情報ナビゲータ[サイニィ] 詳細へ移動 検索 フォームへ移動 論文・データをさがす 大学図書館の本をさがす 日本の博士論文をさがす English 検索 タイトル 人物/団体名 所属機関 ISSN DOI 期間 ~ 本文リンク 本文リンクあり データソース JaLC IRDB Crossref DataCite NDL NDL-Digital RUDA JDCat NINJAL CiNii Articles CiNii Books CiNii Dissertations DBpedia Nikkei BP KAKEN Integbio MDR PubMed LSDB Archive 公共データ カタログ ムーンショット型研究開発事業 すべて 研究データ 論文 本 博士論文 プロジェクト [2023年 10月31日掲載]CiNii Dissertations及びCiNii BooksのCiNii Researchへの統合について MIND DOI Web Site 被引用文献1件 Anis Zaman Dept of Computer Science, University of Rochester, Rochester, NY Vincent Silenzio Dept of Urban-Global Public Health, Rutgers University, New Brunswick, NJ Henry Kautz Dept of Computer Science, University of Rochester, Rochester, …

Depressive disorder is one of the most prevalent mental illnesses among the global population. However, traditional screening methods require exacting in-person interviews and may fail to provide immediate interventions. In this work, we leverage ubiquitous personal longitudinal Google Search and YouTube engagement logs to detect individuals with depressive disorder. We collected Google Search and YouTube history data and clinical depression evaluation results from participants ( of them suffered from moderate to severe depressions). We then propose a personalized framework for classifying individuals with and without depression symptoms based on mutual-exciting point process that captures both the temporal and semantic aspects of online activities. Our best model achieved an average F1 score of and an AUC ROC of .

Routine experiences of daily living invoke particular patterns that can be detected in online activities. Every time an individual carries out any activity on the internet some kind of metadata, reflecting the user's preference, is created and stored. The generated metadata, a latent bi-product of high volume user interactions, is rich, has the potential to be mined for understanding one's current mental state. For example, Google logs every search query made on Google Search, Maps, and YouTube. Closely monitoring these experiences and events, along with the history of online activities, can inform systems to provide early diagnosis and detection of depression, anxiety, and related problems. A growing body of research focuses on using social media for identifying signals associated to various mental health phenomena. However, interventions based on such sources tend to have high false positive rates and may lead …