In this paper we describe eBird, a citizen-science project that takes advantage of human observational capacity and machine learning methods to explore the synergies between human computation and mechanical computation. We call this model a Human/Computer Learning Network, whose core is an active learning feedback loop between humans and machines that dramatically improves the quality of both, and thereby continually improves the effectiveness of the network as a whole. Human/Computer Learning Networks leverage the contributions of a broad recruitment of human observers and processes their contributed data with Artificial Intelligence algorithms leading to a computational power that far exceeds the sum of the individual parts.

Experience using computational perception within the context of art and performance is reported. Four different types of pedagogical projects are presented: a new non-majors introductory computing course, an upper-level course covering computer vision and graphics inan integrated manner, an interactive dance piece, and a peer-led tele-workshop outreach series.

This paper suggests some teaching strategies for Algorithms and AI courses. These courses can have a common goal of teaching complex problem-solving techniques. Based on my experience teaching undergraduates in a small liberal-arts college, the paper offers concrete ideas for working toward this goal. These ideas are supported by relevant studies in cognitive science and education. Together, they provide a plan for structuring lessons and assignments to help student become better problem-solvers.

In this paper, we study the problem of large-scale Kernel Logistic Regression (KLR). A straightforward approach is to apply stochastic approximation to KLR. We refer to this approach as non-conservative online learning algorithm because it updates the kernel classifier after every received training example, leading to a dense classifier. To improve the sparsity of the KLR classifier, we propose two conservative online learning algorithms that update the classifier in a stochastic manner and generate sparse solutions. With appropriately designed updating strategies, our analysis shows that the two conservative algorithms enjoy similar theoretical guarantee as that of the non-conservative algorithm. Empirical studies on several benchmark data sets demonstrate that compared to batch-mode algorithms for KLR, the proposed conservative online learning algorithms are able to produce sparse KLR classifiers, and achieve similar classification accuracy but with significantly shorter training time. Furthermore, both the sparsity and classification accuracy of our methods are comparable to those of the online kernel SVM.

In this paper, we investigate belief revision in possibilistic logic, which is a weighted logic proposed to deal with incomplete and uncertain information. Existing revision operators in possibilistic logic are restricted in the sense that the input information can only be a formula instead of a possibilistic knowledge base which is a set of weighted formulas. To break this restriction, we consider weighted prime implicants of a possibilistic knowledge base and use them to define novel revision operators in possibilistic logic. Intuitively, a weighted prime implicant of a possibilistic knowledge base is a logically weakest possibilistic term (i.e., a set of weighted literals) that can entail the knowledge base. We first show that the existing definition of a weighted prime implicant is problematic and need a modification. To define a revision operator using weighted prime implicants, we face two problems. The first problem is that we need to define the notion of a conflict set between two weighted prime implicants of two possibilistic knowledge bases to achieve minimal change. The second problem is that we need to define the disjunction of possibilistic terms. We solve these problems and define two conflict-based revision operators in possibilistic logic. We then adapt the well-known postulates for revision proposed by Katsuno and Mendelzon and show that our revision operators satisfy four of the basic adapted postulates and satisfy two others in some special cases.

Saliency detection has been a desirable way for robotic vision to find the most noticeable objects in a scene. In this paper, a robust manifold-based saliency estimation method has been developed to help capture the most salient objects in front of robotic eyes, namely cameras. In the proposed approach, an image is considered as a manifold of visual signals (stimuli) spreading over a connected grid, and local visual stimuli are compared against the global image variation to model the visual saliency. With this model, manifold learning is then applied to minimize the local variation while keeping the global contrast, and turns the RGB image into a multi-channel image. After the projection through manifold learning, histogram-based contrast is then computed for saliency modeling of all channels of the projected images, and mutual information is introduced to evaluate each single-channel saliency map against prior knowledge to provide cues for the fusion of multiple channels. In the last step, the fusion procedure combines all single-channel saliency maps according to their mutual information score, and generates the final saliency map. In our experiment, the proposed method is evaluated using one of the largest publicly available image datasets. The experimental results demonstrate that our algorithm consistently outperforms the state-of-the-art unsupervised saliency detection methods, yielding higher precision and better recall rates. Furthermore, the proposed method is tested on a video-type test dataset where a moving camera is trying to catch up with the walking person---a salient object in the video sequence. Our experimental results show that the proposed approach can successful accomplish this task, revealing its potential use for similar robotic applications.

A large number of images with ground truth object bounding boxes are critical for learning object detectors, which is a fundamental task in compute vision. In this paper, we study strategies to crowd-source bounding box annotations. The core challenge of building such a system is to effectively control the data quality with minimal cost. Our key observation is that drawing a bounding box is significantly more difficult and time consuming than giving answers to multiple choice questions. Thus quality control through additional verification tasks is more cost effective than consensus based algorithms. In particular, we present a system that consists of three simple sub-tasks --- a drawing task, a quality verification task and a coverage verification task. Experimental results demonstrate that our system is scalable, accurate, and cost-effective.

To ensure quality results from crowdsourced tasks requesters often aggregate worker responses and use one of a plethora of strategies for the process of inferring the correct answer from the set of noisy responses. However, all current models assume prior knowledge of all possible outcomes of the task. While not an unreasonable assumption for tasks that can be posited as multiple-choice questions (e.g. n-ary classification), we observe that many tasks do not naturally fit this paradigm, but instead demand a free-response, generalized, formulation where the outcome space is of infinite size (e.g. audio transcription). We call these tasks open questions. We model open questions with a novel probabilistic graphical model, and design and implement LazySusan, a decision-theoretic controller that dynamically requests responses as necessary in order to infer answers to these tasks. Live experiments on Amazon Mechanical Turk demonstrate the superiority of LazySusan at solving SAT Math questions, eliminating 83.2% of the error and achieving greater net utility compared to the state-of-the-art strategy, majority voting.

Reaching for a target requires estimating the spatial position of the target and to convert such a position in a suitable arm-motor command. In the proposed framework, the location of the target is represented implicitly by the gaze direction of the robot and by the distance of the target. The NAO robot is provided with two cameras, one to look ahead and one to look down, which constitute two independent head-centered coordinate systems. These head-centered frames of reference are converted into reaching commands by two neural networks. The weights of networks are learned by moving the arm while gazing the hand, using an on-line learning algorithm that maintains the covariance matrix of weights. This work adapts a previously proposed model that worked on a full humanoid robot torso, to work with the NAO and is a step toward a more generic framework for the implicit representation of the peripersonal space in humanoid robots.

The Model AI Assignments session seeks to gather and disseminate the best assignment designs of the Artificial Intelligence (AI) Education community. Recognizing that assignments form the core of student learning experience, we here present abstracts of three AI assignments from the 2012 session that are easily adoptable, playfully engaging, and flexible for a variety of instructor needs.