High dimensional sequential data exhibits complex structure, a successful generative model for such data must involve highly dependent, structured variables. Thus it is desired or even necessary to model correlations and dependencies between the multiple input, output variables and latent variables in such scenario. To achieve this goal, we introduce Variational Structured Stochastic Network(VS...

Knowledge based artificial networks networks have been applied quite successfully to propositional knowledge representation and reasoning tasks. However, as soon as these tasks are extended to structured objects and structure-sensitive processes it is not obvious at all how neural symbolic systems should look like such that they are truly connectionist and allow for a declarative reading at the...

Modern studies in the field of environment science and engineering show that deterministic models struggle to capture the relationship between the concentration of atmospheric pollutants and their emission sources. The recent advances in statistical modeling based on machine learning approaches have emerged as solution to tackle these issues. It is a fact that, input variable type largely affec...

Supervised learning is about learning functions given a set of input and corresponding output examples. A recent trend in this field is to consider structured outputs such as sequences, trees or graphs. When predicting such structured data, learning models have to select solutions within very large discrete spaces. The combinatorial nature of this problem has recently led to learning models int...

Language is increasingly being used to define rich visual recognition problems with supporting image collections sourced from the web. Structured prediction models are used in these tasks to take advantage of correlations between co-occurring labels and visual input but risk inadvertently encoding social biases found in web corpora. In this work, we study data and models associated with multila...

Most vision research is based on some sort of a model of the world. The model is usually highly specific about one aspect of the world, for instance, the appearance of a human face, or the motion model for an object, but it does not model other parts of the scene. This makes models very brittle in any realistic application. We believe that in order to build more robust vision algorithms, models...

The utility of vision-based face tracking for dual pointing tasks is evaluated. We first describe a 3-D face tracking technique based on real-time parametric motion-stereo, which is non-invasive, robust, and self-initialized. The tracker provides a real-time estimate of a “frontal face ray” whose intersection with the display surface plane is used as a second stream of input for scrolling or po...

Modern neural networks are often augmented with an attention mechanism, which tells the network where to focus within the input. We propose in this paper a new framework for sparse and structured attention, building upon a smoothed max operator. We show that the gradient of this operator defines a mapping from real values to probabilities, suitable as an attention mechanism. Our framework inclu...

Two experiments investigated free sorting, a type of unsupervised learning, with multiattribute drawings of alien animals. In previous research on concept formation, with simpler stimulus structure than ours, participants were insensitive to correlational structure in the stimuli, producing primarily "ID sorts," based on the values ofjust 1 dimension or attribute. Our experiments showed that pa...