The lack of reliable data in developing countries is a major obstacle to sustainable development, food security, and disaster relief. Poverty data, for example, is typically scarce, sparse in coverage, and labor-intensive to obtain. Remote sensing data such as high-resolution satellite imagery, on the other hand, is becoming increasingly available and inexpensive. Unfortunately, such data is highly unstructured and currently no techniques exist to automatically extract useful insights to inform policy decisions and help direct humanitarian efforts. We propose a novel machine learning approach to extract large-scale socioeconomic indicators from high-resolution satellite imagery. The main challenge is that training data is very scarce, making it difficult to apply modern techniques such as Convolutional Neural Networks (CNN). We therefore propose a transfer learning approach where nighttime light intensities are used as a data-rich proxy. We train a fully convolutional CNN model to predict nighttime lights from daytime imagery, simultaneously learning features that are useful for poverty prediction. The model learns filters identifying different terrains and man-made structures, including roads, buildings, and farmlands, without any supervision beyond nighttime lights. We demonstrate that these learned features are highly informative for poverty mapping, even approaching the predictive performance of survey data collected in the field.

Due to the decentralized nature of the Semantic Web, the same real-world entity may be described in various data sources with different ontologies and assigned syntactically distinct identifiers. In order to facilitate data utilization and consumption in the Semantic Web, without compromising the freedom of people to publish their data, one critical problem is to appropriately interlink such heterogeneous data. This interlinking process is sometimes referred to as Entity Coreference, i.e., finding which identifiers refer to the same real-world entity. In this paper, we first summarize state-of-the-art algorithms in detecting such coreference relationships between ontology instances. We then discuss various techniques in scaling entity coreference to large-scale datasets. Finally, we present well-adopted evaluation datasets and metrics, and compare the performance of the state-of-the-art algorithms on such datasets.

In this paper we expand the standard Hotelling-Downs model of spatial competition to a setting where clients do not necessarily choose their closest candidate (retail product or political). Specifically, we consider a setting where clients may disavow all candidates if there is no candidate that is sufficiently close to the client preferences. Moreover, if there are multiple candidates that are sufficiently close, the client may choose amongst them at random. We show the existence of Nash Equilibria for some such models, and study the price of anarchy and stability in such scenarios.

We consider the following problem in which a given number of items has to be chosen from a predefined set. Each item is described by a vector of attributes and for each attribute there is a desired distribution that the selected set should fit. We look for a set that fits as much as possible the desired distributions on all attributes. Examples of applications include choosing members of a representative committee, where candidates are described by attributes such as sex, age and profession, and where we look for a committee that for each attribute offers a certain representation, i.e., a single committee that contains a certain number of young and old people, certain number of men and women, certain number of people with different professions, etc. With a single attribute the problem boils down to the apportionment problem for party-list proportional representation systems (in such case the value of the single attribute is the political affiliation of a candidate). We study some properties of the associated subset selection rules, and address their computation.

Bribery in elections is an important problem in computational social choice theory. We introduce and study two important special cases of the bribery problem, namely, FRUGAL-BRIBERY and FRUGAL-$BRIBERY where the briber is frugal in nature. By this, we mean that the briber is only able to influence voters who benefit from the suggestion of the briber. More formally, a voter is vulnerable if the outcome of the election improves according to her own preference when she accepts the suggestion of the briber. In the FRUGAL-BRIBERY problem, the goal is to make a certain candidate win the election by changing only the vulnerable votes. In the FRUGAL-$BRIBERY problem, the vulnerable votes have prices and the goal is to make a certain candidate win the election by changing only the vulnerable votes, subject to a budget constraint. We show that both the FRUGAL-BRIBERY and the FRUGAL-$BRIBERY problems are intractable for many commonly used voting rules for weighted as well as unweighted elections. These intractability results demonstrate that bribery is a hard computational problem, in the sense that several special cases of this problem continue to be computationally intractable. This strengthens the view that bribery, although a possible attack on an election in principle, may be infeasible in practice.

In Supreme Court parlance and the political science literature, an ideal point positions a justice in a continuous space and can be interpreted as a quantification of the justice's policy preferences. We present an automated approach to infer such ideal points for justices of the US Supreme Court. This approach combines topic modeling over case opinions with the voting (and endorsing) behavior of justices. Furthermore, given a topic of interest, say the Fourth Amendment, the topic model can be optionally seeded with supervised information to steer the inference of ideal points. Application of this methodology over five years of cases provides interesting perspectives into the leaning of justices on crucial issues, coalitions underlying specific topics, and the role of swing justices in deciding the outcomes of cases.

While Hierarchical Task Networks are frequently cited as flexible and powerful planning models, they are often ignored due to the intensive labor cost for experts/programmers, due to the need to create and refine the model by hand. While recent work has begun to address this issue by working towards learning aspects of an HTN model from demonstration, or even the whole framework, the focus so far has been on simple domains, which lack many of the challenges faced in the real world such as imperfect information and real-time environments. I plan to extend this work using the domain of real-time strategy (RTS) games, which have gained recent popularity as a challenging and complex domain for AI research.

Artificial Intelligence is all over the news these days with companies like Google, Facebook and Apple investing heavily, but it can be hard for individual salespeople and entrepreneurs to know which services they can use without the need of a large IT staff or a corporate approval process. These services offer something unique like helping to find the right prospect to follow-up with, scheduling a meeting or finding insight on a customer. In each case, these services do not require any IT knowledge for setup, management, or maintenance. How many times have you engaged a prospect, but it took a large number of emails back and forth to schedule that next meeting? Instead you can use X.ai's assistant'Amy' who connects to your calendar and emails your contact on your behalf. She proposes free times and will send out calendar invites once an agreement on time and place has been met.

Today's security systems usually fall into one of two categories: human or machine. So-called "analyst-driven solutions" rely on rules created by living experts and therefore miss any attacks that don't match the rules. Meanwhile, today's machine-learning approaches rely on "anomaly detection," which tends to trigger false positives that both create distrust of the system and end up having to be investigated by humans, anyway. But what if there were a solution that could merge those two worlds? What would it look like?

"Today's security systems usually fall into one of two categories: man or machine," Adam Conner-Simon from MIT's Computer Science and Artificial Intelligence Laboratory (CSAIL) wrote in a post on the MIT News site. "So-called'analyst-driven solutions' rely on rules created by human experts and therefore miss any attacks that don't match the rules," he said. "Meanwhile, today's machine-learning approaches rely on'anomaly detection,' which tends to trigger false positives that both create distrust of the system and end up having to be investigated by humans, anyway." The MIT and PatternEx platform attempts to merge those two approaches. AI2 predicts attacks by combing through data and detecting suspicious activity by clustering it into meaningful patterns using unsupervised machine learning, according to researchers at MIT.