Dynamic Poisson Factorization
Posted on23/09/2015
Models for recommender systems use latent factors to explain the preferences and behaviors of users with respect to a set of items... Read More
Describing Multimedia Content using Attention-based Encoder–Decoder Networks
Posted on23/09/2015
Whereas deep neural networks were first mostly used for classification tasks, they are rapidly expanding in the realm of structured output problems, where the... Read More
A Recurrent Latent Variable Model for Sequential Data
Posted on07/06/2015
In this paper, we explore the inclusion of random variables into the dynamic hidden state of a recurrent neural network (RNN) by... Read More
Deep Learning
Posted on28/05/2015
Deep learning allows computational models that are composed of multiple processing layers to learn representations of data with multiple levels of abstraction. These... Read More
Deep Exponential Families
Posted on23/05/2015
We describe deep exponential families (DEFs), a class of latent variable models that are inspired by the hidden structures used in deep... Read More
Content-based recommendations with Poisson factorization
Posted on23/12/2014
We develop collaborative topic Poisson factorization (CTPF), a generative model of articles and reader preferences. CTPF can be used to build recommender... Read More
Modeling Deep Temporal Dependencies with Recurrent “Grammar Cells”
Posted on23/12/2014
We propose modeling time series by representing the transformations that take a frame at time t to a frame at time t+1.... Read More
Neural Machine Translation by Jointly Learning to Align and Translate
Posted on01/09/2014
Neural machine translation is a recently proposed approach to machine translation. Unlike the traditional statistical machine translation, the neural machine translation aims... Read More
Leveraging User Libraries to Bootstrap Collaborative Filtering
Posted on23/08/2014
We introduce a novel graphical model, the collaborative score topic model (CSTM), for personal recommendations of textual documents. CSTM’s chief novelty lies... Read More
Generative Adversarial Networks
Posted on10/06/2014
We propose a new framework for estimating generative models via an adversarial process, in which we simultaneously train two models: a generative... Read More