Models for recommender systems use latent factors to explain the preferences and behaviors of users with respect to a set of items (e.g., movies, books, academic papers). Typically, the latent factors are assumed to be static and, given these factors, the observed preferences and behaviors of users are assumed to be generated without order. These assumptions limit the explorative and predictive capabilities of such models, since users' interests and item popularity may evolve over time. To address this, we propose dPF, a dynamic matrix factorization model based on the recent Poisson factorization model for recommendations. dPF models the time evolving latent factors with a Kalman filter and the actions with Poisson distributions. We derive a scalable variational inference algorithm to infer the latent factors. Finally, we demonstrate dPF on 10 years of user click data from arXiv.org, one of the largest repository of scientific papers and a formidable source of information about the behavior of scientists. Empirically we show performance improvement over both static and, more recently proposed, dynamic recommendation models. We also provide a thorough exploration of the inferred posteriors over the latent variables.

In sentence modeling and classification, convolutional neural network approaches have recently achieved state-of-the-art results, but all such efforts process word vectors sequentially and neglect long-distance dependencies. To combine deep learning with linguistic structures, we propose a dependency-based convolution approach, making use of tree-based n-grams rather than surface ones, thus utlizing nonlocal interactions between words. Our model improves sequential baselines on all four sentiment and question classification tasks, and achieves the highest published accuracy on TREC.

We present a new convolutional neural network-based time-series model. Typical convolutional neural network (CNN) architectures rely on the use of max-pooling operators in between layers, which leads to reduced resolution at the top layers. Instead, in this work we consider a fully convolutional network (FCN) architecture that uses causal filtering operations, and allows for the rate of the output signal to be the same as that of the input signal. We furthermore propose an undecimated version of the FCN, which we refer to as the undecimated fully convolutional neural network (UFCNN), and is motivated by the undecimated wavelet transform. Our experimental results verify that using the undecimated version of the FCN is necessary in order to allow for effective time-series modeling. The UFCNN has several advantages compared to other time-series models such as the recurrent neural network (RNN) and long short-term memory (LSTM), since it does not suffer from either the vanishing or exploding gradients problems, and is therefore easier to train. Convolution operations can also be implemented more efficiently compared to the recursion that is involved in RNN-based models. We evaluate the performance of our model in a synthetic target tracking task using bearing only measurements generated from a state-space model, a probabilistic modeling of polyphonic music sequences problem, and a high frequency trading task using a time-series of ask/bid quotes and their corresponding volumes. Our experimental results using synthetic and real datasets verify the significant advantages of the UFCNN compared to the RNN and LSTM baselines.

To date, there have been massive Semi-Structured Documents (SSDs) during the evolution of the Internet. These SSDs contain both unstructured features (e.g., plain text) and metadata (e.g., tags). Most previous works focused on modeling the unstructured text, and recently, some other methods have been proposed to model the unstructured text with specific tags. To build a general model for SSDs remains an important problem in terms of both model fitness and efficiency. We propose a novel method to model the SSDs by a so-called Tag-Weighted Topic Model (TWTM). TWTM is a framework that leverages both the tags and words information, not only to learn the document-topic and topic-word distributions, but also to infer the tag-topic distributions for text mining tasks. We present an efficient variational inference method with an EM algorithm for estimating the model parameters. Meanwhile, we propose three large-scale solutions for our model under the MapReduce distributed computing platform for modeling large-scale SSDs. The experimental results show the effectiveness, efficiency and the robustness by comparing our model with the state-of-the-art methods in document modeling, tags prediction and text classification. We also show the performance of the three distributed solutions in terms of time and accuracy on document modeling.

Paragraph Vectors has been recently proposed as an unsupervised method for learning distributed representations for pieces of texts. In their work, the authors showed that the method can learn an embedding of movie review texts which can be leveraged for sentiment analysis. That proof of concept, while encouraging, was rather narrow. Here we consider tasks other than sentiment analysis, provide a more thorough comparison of Paragraph Vectors to other document modelling algorithms such as Latent Dirichlet Allocation, and evaluate performance of the method as we vary the dimensionality of the learned representation. We benchmarked the models on two document similarity data sets, one from Wikipedia, one from arXiv. We observe that the Paragraph Vector method performs significantly better than other methods, and propose a simple improvement to enhance embedding quality. Somewhat surprisingly, we also show that much like word embeddings, vector operations on Paragraph Vectors can perform useful semantic results.

This paper considers the kinds of AI systems we want involved in art and art practice. We explore this relationship from three perspectives: as artists interested in expanding and developing our own creative practice; as AI researchers interested in building new AI systems that contribute to the understanding and development of art and art practice; and as audience members interested in experiencing art. We examine the nature of both art practice and experiencing art to ask how AI can contribute. To do so, we review the history of work in intelligent agents which broadly speaking sits in two camps: autonomous agents (systems that can exhibit intelligent behaviour independently) in one, and multi-agent systems (systems which interact with other systems in communities of agents) in the other. In this context we consider the nature of the relationship between AI and Art and introduce two opposing concepts: that of “Heroic AI”, to describe the situation where the software takes on the role of the lone creative hero and “Collaborative AI” where the system supports, challenges and provokes the creative activity of humans. We then set out what we believe are the main challenges for AI research in understanding its potential relationship to art and art practice.

Personalization aims to tailor content to a person’s individual tastes. As a result, the tasks that benefit from personalization are inherently subjective. Many of the most robust approaches to personalization rely on large sets of other people’s preferences. However, existing preference data is not always available. In these cases, we propose leveraging online crowds to provide on-demand personalization. We introduce and evaluate two methods for personalized crowdsourcing: taste-matching for finding crowd workers who are similar to the requester, and taste-grokking , where crowd workers explicitly predict the requester’s tastes. Both approaches show improvement over a non-personalized baseline, with taste-grokking performing well in simpler tasks and taste-matching performing well with larger crowds and tasks with latent decision-making variables.

This demonstration presents a concatenative synthesis engine for the generation of musical accompaniments, based on chord progressions. The system takes a player's song recording as input, and generates the accompaniment for any other song, based on the input content. We show that working on accompaniment requires a special care about temporal deviations at the border of the sliced chunks, because they make most of the rhythmic groove. We address it by discriminating accidental deviations against intentional ones, in order to correct the first while keeping the second. We will provide a full demonstration of the system, from the recording process to the generation, in various conditions, inviting the audience to participate.

We propose an automatic music generation demo based on artificial neural networks, which integrates the ability of Long Short-Term Memory (LSTM) in memorizing and retrieving useful history information, together with the advantage of Restricted Boltzmann Machine (RBM) in high dimensional data modelling. Our model can generalize to different musical styles and generate polyphonic music better than previous models.

Recommender system has become an indispensable component in many e-commerce sites. One major challenge that largely remains open is the cold-start problem, which can be viewed as an ice barrier that keeps the cold-start users/items from the warm ones. In this paper, we propose a novel rating comparison strategy (RaPare) to break this ice barrier. The center-piece of  our RaPare is to provide a fine-grained calibration on the latent profiles of cold-start users/items by exploring the differences between cold-start and warm users/items. We instantiate our RaPare strategy on the prevalent method in recommender system, i.e., the matrix factorization based collaborative filtering. Experimental evaluations on two real data sets validate the superiority of our approach over the existing methods in cold-start scenarios.