We propose a technique of training models for feature extraction using prior expectation of regions of importance in an instrument's timbre. Over a dataset of training examples, we extract significant spectral peaks, calculate their ratio to fundamental frequency, and use $k$-means clustering to identify a set of windows of spectral prominence for each instrument. These windows are used to extract amplitude values from training data to use as features in classification tasks. We test this approach on two databases of 17 instruments, cross evaluate between datasets, and compare with MFCC features.

Social media systems rely on user feedback and rating mechanisms for personalization, ranking, and content filtering. However, when users evaluate content contributed by fellow users (e.g., by liking a post or voting on a comment), these evaluations create complex social feedback effects. This paper investigates how ratings on a piece of content affect its author's future behavior. By studying four large comment-based news communities, we find that negative feedback leads to significant behavioral changes that are detrimental to the community. Not only do authors of negatively-evaluated content contribute more, but also their future posts are of lower quality, and are perceived by the community as such. Moreover, these authors are more likely to subsequently evaluate their fellow users negatively, percolating these effects through the community. In contrast, positive feedback does not carry similar effects, and neither encourages rewarded authors to write more, nor improves the quality of their posts. Interestingly, the authors that receive no feedback are most likely to leave a community. Furthermore, a structural analysis of the voter network reveals that evaluations polarize the community the most when positive and negative votes are equally split.

In this paper, we explore different ways to extend a recurrent neural network (RNN) to a \textit{deep} RNN. We start by arguing that the concept of depth in an RNN is not as clear as it is in feedforward neural networks. By carefully analyzing and understanding the architecture of an RNN, however, we find three points of an RNN which may be made deeper; (1) input-to-hidden function, (2) hidden-to-hidden transition and (3) hidden-to-output function. Based on this observation, we propose two novel architectures of a deep RNN which are orthogonal to an earlier attempt of stacking multiple recurrent layers to build a deep RNN (Schmidhuber, 1992; El Hihi and Bengio, 1996). We provide an alternative interpretation of these deep RNNs using a novel framework based on neural operators. The proposed deep RNNs are empirically evaluated on the tasks of polyphonic music prediction and language modeling. The experimental result supports our claim that the proposed deep RNNs benefit from the depth and outperform the conventional, shallow RNNs.

In this paper, we propose an efficient and scalable low rank matrix completion algorithm. The key idea is to extend orthogonal matching pursuit method from the vector case to the matrix case. We further propose an economic version of our algorithm by introducing a novel weight updating rule to reduce the time and storage complexity. Both versions are computationally inexpensive for each matrix pursuit iteration, and find satisfactory results in a few iterations. Another advantage of our proposed algorithm is that it has only one tunable parameter, which is the rank. It is easy to understand and to use by the user. This becomes especially important in large-scale learning problems. In addition, we rigorously show that both versions achieve a linear convergence rate, which is significantly better than the previous known results. We also empirically compare the proposed algorithms with several state-of-the-art matrix completion algorithms on many real-world datasets, including the large-scale recommendation dataset Netflix as well as the MovieLens datasets. Numerical results show that our proposed algorithm is more efficient than competing algorithms while achieving similar or better prediction performance.

Representations in the auditory cortex might be based on mechanisms similar to the visual ventral stream; modules for building invariance to transformations and multiple layers for compositionality and selectivity. In this paper we propose the use of such computational modules for extracting invariant and discriminative audio representations. Building on a theory of invariance in hierarchical architectures, we propose a novel, mid-level representation for acoustical signals, using the empirical distributions of projections on a set of templates and their transformations. Under the assumption that, by construction, this dictionary of templates is composed from similar classes, and samples the orbit of variance-inducing signal transformations (such as shift and scale), the resulting signature is theoretically guaranteed to be unique, invariant to transformations and stable to deformations. Modules of projection and pooling can then constitute layers of deep networks, for learning composite representations. We present the main theoretical and computational aspects of a framework for unsupervised learning of invariant audio representations, empirically evaluated on music genre classification.

What lies between `\emph{sensing}' and `\emph{sensibility}'? In other words, what kind of cognitive processes mediate sensing capability, and the formation of sensible impressions ---e.g., abstractions, analogies, hypotheses and theory formation, beliefs and their revision, argument formation--- in domain-specific problem solving, or in regular activities of everyday living, working and simply going around in the environment? How can knowledge and reasoning about such capabilities, as exhibited by humans in particular problem contexts, be used as a model and benchmark for the development of collaborative cognitive (interaction) systems concerned with human assistance, assurance, and empowerment? We pose these questions in the context of a range of assistive technologies concerned with \emph{visuo-spatial perception and cognition} tasks encompassing aspects such as commonsense, creativity, and the application of specialist domain knowledge and problem-solving thought processes. Assistive technologies being considered include: (a) human activity interpretation; (b) high-level cognitive rovotics; (c) people-centred creative design in domains such as architecture & digital media creation, and (d) qualitative analyses geographic information systems. Computational narratives not only provide a rich cognitive basis, but they also serve as a benchmark of functional performance in our development of computational cognitive assistance systems. We posit that computational narrativisation pertaining to space, actions, and change provides a useful model of \emph{visual} and \emph{spatio-temporal thinking} within a wide-range of problem-solving tasks and application areas where collaborative cognitive systems could serve an assistive and empowering function.

Discovering and characterizing the large-scale topological features in empirical networks are crucial steps in understanding how complex systems function. However, most existing methods used to obtain the modular structure of networks suffer from serious problems, such as being oblivious to the statistical evidence supporting the discovered patterns, which results in the inability to separate actual structure from noise. In addition to this, one also observes a resolution limit on the size of communities, where smaller but well-defined clusters are not detectable when the network becomes large. This phenomenon occurs not only for the very popular approach of modularity optimization, which lacks built-in statistical validation, but also for more principled methods based on statistical inference and model selection, which do incorporate statistical validation in a formally correct way. Here we construct a nested generative model that, through a complete description of the entire network hierarchy at multiple scales, is capable of avoiding this limitation, and enables the detection of modular structure at levels far beyond those possible with current approaches. Even with this increased resolution, the method is based on the principle of parsimony, and is capable of separating signal from noise, and thus will not lead to the identification of spurious modules even on sparse networks. Furthermore, it fully generalizes other approaches in that it is not restricted to purely assortative mixing patterns, directed or undirected graphs, and ad hoc hierarchical structures such as binary trees. Despite its general character, the approach is tractable, and can be combined with advanced techniques of community detection to yield an efficient algorithm that scales well for very large networks.

This work investigates summarizing the conversations that occur in the comments section of the UK newspaper the Guardian. In the comment summarization task comments are clustered and ranked within the cluster. The top comments from each cluster are used to give an overview of that cluster. It was found that topic model clustering gave the most agreement when evaluated against a human gold standard. This approach is compared to cosine distance clustering and k-means clustering. PageRank was found to be the prefered ranking system when compared with TF-IDF, Mutual Information gain and Maximal Marginal Relevance and evaluated against sets of comments summarized by a journalist for the Guardian letters page.

In this paper, we consider a popular model for collaborative filtering in recommender systems where some users of a website rate some items, such as movies, and the goal is to recover the ratings of some or all of the unrated items of each user. In particular, we consider both the clustering model, where only users (or items) are clustered, and the co-clustering model, where both users and items are clustered, and further, we assume that some users rate many items (information-rich users) and some users rate only a few items (information-sparse users). When users (or items) are clustered, our algorithm can recover the rating matrix with $\omega(MK \log M)$ noisy entries while $MK$ entries are necessary, where $K$ is the number of clusters and $M$ is the number of items. In the case of co-clustering, we prove that $K^2$ entries are necessary for recovering the rating matrix, and our algorithm achieves this lower bound within a logarithmic factor when $K$ is sufficiently large. We compare our algorithms with a well-known algorithms called alternating minimization (AM), and a similarity score-based algorithm known as the popularity-among-friends (PAF) algorithm by applying all three to the MovieLens and Netflix data sets. Our co-clustering algorithm and AM have similar overall error rates when recovering the rating matrix, both of which are lower than the error rate under PAF. But more importantly, the error rate of our co-clustering algorithm is significantly lower than AM and PAF in the scenarios of interest in recommender systems: when recommending a few items to each user or when recommending items to users who only rated a few items (these users are the majority of the total user population). The performance difference increases even more when noise is added to the datasets.

We apply the OSCAR (octagonal selection and clustering algorithms for regression) in recovering group-sparse matrices (two-dimensional---2D---arrays) from compressive measurements. We propose a 2D version of OSCAR (2OSCAR) consisting of the $\ell_1$ norm and the pair-wise $\ell_{\infty}$ norm, which is convex but non-differentiable. We show that the proximity operator of 2OSCAR can be computed based on that of OSCAR. The 2OSCAR problem can thus be efficiently solved by state-of-the-art proximal splitting algorithms. Experiments on group-sparse 2D array recovery show that 2OSCAR regularization solved by the SpaRSA algorithm is the fastest choice, while the PADMM algorithm (with debiasing) yields the most accurate results.