Recent progress on automatic generation of image captions has shown that it is possible to describe the most salient information conveyed by images with accurate and meaningful sentences. In this paper, we propose an image caption system that exploits the parallel structures between images and sentences. In our model, the process of generating the next word, given the previously generated ones, is aligned with the visual perception experience where the attention shifting among the visual regions imposes a thread of visual ordering. This alignment characterizes the flow of "abstract meaning", encoding what is semantically shared by both the visual scene and the text description. Our system also makes another novel modeling contribution by introducing scene-specific contexts that capture higher-level semantic information encoded in an image. The contexts adapt language models for word generation to specific scene types. We benchmark our system and contrast to published results on several popular datasets. We show that using either region-based attention or scene-specific contexts improves systems without those components. Furthermore, combining these two modeling ingredients attains the state-of-the-art performance.

We study the fundamental limits on learning latent community structure in dynamic networks. Specifically, we study dynamic stochastic block models where nodes change their community membership over time, but where edges are generated independently at each time step. In this setting (which is a special case of several existing models), we are able to derive the detectability threshold exactly, as a function of the rate of change and the strength of the communities. Below this threshold, we claim that no algorithm can identify the communities better than chance. We then give two algorithms that are optimal in the sense that they succeed all the way down to this limit. The first uses belief propagation (BP), which gives asymptotically optimal accuracy, and the second is a fast spectral clustering algorithm, based on linearizing the BP equations. We verify our analytic and algorithmic results via numerical simulation, and close with a brief discussion of extensions and open questions.

We present an approach to Intelligent Tutoring Systems which adaptively personalizes sequences of learning activities to maximize skills acquired by students, taking into account the limited time and motivational resources. At a given point in time, the system proposes to the students the activity which makes them progress faster. We introduce two algorithms that rely on the empirical estimation of the learning progress, RiARiT that uses information about the difficulty of each exercise and ZPDES that uses much less knowledge about the problem. The system is based on the combination of three approaches. First, it leverages recent models of intrinsically motivated learning by transposing them to active teaching, relying on empirical estimation of learning progress provided by specific activities to particular students. Second, it uses state-of-the-art Multi-Arm Bandit (MAB) techniques to efficiently manage the exploration/exploitation challenge of this optimization process. Third, it leverages expert knowledge to constrain and bootstrap initial exploration of the MAB, while requiring only coarse guidance information of the expert and allowing the system to deal with didactic gaps in its knowledge. The system is evaluated in a scenario where 7-8 year old schoolchildren learn how to decompose numbers while manipulating money. Systematic experiments are presented with simulated students, followed by results of a user study across a population of 400 school children.

Previously, we proposed a physically inspired rule to organize the data points in a sparse yet effective structure, called the in-tree (IT) graph, which is able to capture a wide class of underlying cluster structures in the datasets, especially for the density-based datasets. Although there are some redundant edges or lines between clusters requiring to be removed by computer, this IT graph has a big advantage compared with the k-nearest-neighborhood (k-NN) or the minimal spanning tree (MST) graph, in that the redundant edges in the IT graph are much more distinguishable and thus can be easily determined by several methods previously proposed by us. In this paper, we propose a general framework to re-construct the IT graph, based on an initial neighborhood graph, such as the k-NN or MST, etc, and the corresponding graph distances. For this general framework, our previous way of constructing the IT graph turns out to be a special case of it. This general framework 1) can make the IT graph capture a wider class of underlying cluster structures in the datasets, especially for the manifolds, and 2) should be more effective to cluster the sparse or graph-based datasets.

Many real-world phenomena can be described in tems of pairwise relationships between entities. When learning pairwise relations, symmetry and anti-symmetry are two types of prior knowledge constraints that commonly appear when both of the objects in a pair belong to the same domain. A typical example of an application where relationships are often assumed to be symmetric is the prediction of protein-protein interactions: if protein A interacts with protein B, then conversely it also holds that B interacts with A. Typical example of an anti-symmetric relation would be a preference relation: if A is preferred over B, then conversely B is not preferred over A. Commonly used symmetric pairwise kernels include the symmetrized Kronecker [Ben-Hur and Noble, 2005] and Cartesian [Kashima et al., 2009], as well as the metric learning [Vert et al., 2007] kernels. Such kernels are analyzed in more detail by Brunner et al. [2012]. Typical examples of anti-symmetric kernels are the transitive kernel of [Herbrich et al., 2000] used for learning to rank, and the anti-symmetric Kronecker product kernel [Pahikkala et al., 2010] for learning intransitive preference relations.

Current high-throughput data acquisition technologies probe dynamical systems with different imaging modalities, generating massive data sets at different spatial and temporal resolutions posing challenging problems in multimodal data fusion. A case in point is the attempt to parse out the brain structures and networks that underpin human cognitive processes by analysis of different neuroimaging modalities (functional MRI, EEG, NIRS etc.). We emphasize that the multimodal, multi-scale nature of neuroimaging data is well reflected by a multi-way (tensor) structure where the underlying processes can be summarized by a relatively small number of components or "atoms". We introduce Markov-Penrose diagrams - an integration of Bayesian DAG and tensor network notation in order to analyze these models. These diagrams not only clarify matrix and tensor EEG and fMRI time/frequency analysis and inverse problems, but also help understand multimodal fusion via Multiway Partial Least Squares and Coupled Matrix-Tensor Factorization. We show here, for the first time, that Granger causal analysis of brain networks is a tensor regression problem, thus allowing the atomic decomposition of brain networks. Analysis of EEG and fMRI recordings shows the potential of the methods and suggests their use in other scientific domains.

This paper considers the problem of representative selection: choosing a subset of data points from a dataset that best represents its overall set of elements. This subset needs to inherently reflect the type of information contained in the entire set, while minimizing redundancy. For such purposes, clustering may seem like a natural approach. However, existing clustering methods are not ideally suited for representative selection, especially when dealing with non-metric data, where only a pairwise similarity measure exists. In this paper we propose $\delta$-medoids, a novel approach that can be viewed as an extension to the $k$-medoids algorithm and is specifically suited for sample representative selection from non-metric data. We empirically validate $\delta$-medoids in two domains, namely music analysis and motion analysis. We also show some theoretical bounds on the performance of $\delta$-medoids and the hardness of representative selection in general.

Data-efficient learning in continuous state-action spaces using very high-dimensional observations remains a key challenge in developing fully autonomous systems. In this paper, we consider one instance of this challenge, the pixels to torques problem, where an agent must learn a closed-loop control policy from pixel information only. We introduce a data-efficient, model-based reinforcement learning algorithm that learns such a closed-loop policy directly from pixel information. The key ingredient is a deep dynamical model that uses deep auto-encoders to learn a low-dimensional embedding of images jointly with a predictive model in this low-dimensional feature space. Joint learning ensures that not only static but also dynamic properties of the data are accounted for. This is crucial for long-term predictions, which lie at the core of the adaptive model predictive control strategy that we use for closed-loop control. Compared to state-of-the-art reinforcement learning methods for continuous states and actions, our approach learns quickly, scales to high-dimensional state spaces and is an important step toward fully autonomous learning from pixels to torques.

Collaborative filtering (CF) is a successful approach commonly used by many recommender systems. Conventional CF-based methods use the ratings given to items by users as the sole source of information for learning to make recommendation. However, the ratings are often very sparse in many applications, causing CF-based methods to degrade significantly in their recommendation performance. To address this sparsity problem, auxiliary information such as item content information may be utilized. Collaborative topic regression (CTR) is an appealing recent method taking this approach which tightly couples the two components that learn from two different sources of information. Nevertheless, the latent representation learned by CTR may not be very effective when the auxiliary information is very sparse. To address this problem, we generalize recent advances in deep learning from i.i.d. input to non-i.i.d. (CF-based) input and propose in this paper a hierarchical Bayesian model called collaborative deep learning (CDL), which jointly performs deep representation learning for the content information and collaborative filtering for the ratings (feedback) matrix. Extensive experiments on three real-world datasets from different domains show that CDL can significantly advance the state of the art.

Many practical modeling problems involve discrete data that are best represented as draws from multinomial or categorical distributions. For example, nucleotides in a DNA sequence, children's names in a given state and year, and text documents are all commonly modeled with multinomial distributions. In all of these cases, we expect some form of dependency between the draws: the nucleotide at one position in the DNA strand may depend on the preceding nucleotides, children's names are highly correlated from year to year, and topics in text may be correlated and dynamic. These dependencies are not naturally captured by the typical Dirichlet-multinomial formulation. Here, we leverage a logistic stick-breaking representation and recent innovations in P\'olya-gamma augmentation to reformulate the multinomial distribution in terms of latent variables with jointly Gaussian likelihoods, enabling us to take advantage of a host of Bayesian inference techniques for Gaussian models with minimal overhead.