Modern applications and progress in deep learning research have created renewed interest for generative models of text and of images. However, even today it is unclear what objective functions one should use to train and evaluate these models. In this paper we present two contributions. Firstly, we present a critique of scheduled sampling, a state-of-the-art training method that contributed to the winning entry to the MSCOCO image captioning benchmark in 2015. Here we show that despite this impressive empirical performance, the objective function underlying scheduled sampling is improper and leads to an inconsistent learning algorithm. Secondly, we revisit the problems that scheduled sampling was meant to address, and present an alternative interpretation. We argue that maximum likelihood is an inappropriate training objective when the end-goal is to generate natural-looking samples. We go on to derive an ideal objective function to use in this situation instead. We introduce a generalisation of adversarial training, and show how such method can interpolate between maximum likelihood training and our ideal training objective. To our knowledge this is the first theoretical analysis that explains why adversarial training tends to produce samples with higher perceived quality.

This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.It is available as a free download under a Creative Commons license. You are free to share the book, translate it, or remix it. Before you is a tool for learning basic data mining techniques. Most data mining textbooks focus on providing a theoretical foundation for data mining, and as result, may seem notoriously difficult to understand. Don't get me wrong, the information in those books is extremely important.

We describe an experiment in using IBM’s Watson cognitive system to teach about human-computer co-creativity in a Georgia Tech Spring 2015 class on computational creativity. The project-based class used Watson to support biologically inspired design, a design paradigm that uses biological systems as analogues for inventing technological systems. The twenty-four students in the class self-organized into six teams of four students each, and developed semester-long projects that built on Watson to support biologically inspired design. In this paper, we describe this experiment in using Watson to teach about human-computer co-creativity, present one project in detail, and summarize the remaining five projects. We also draw lessons on building on Watson for (i) supporting biologically inspired design, and (ii) enhancing human-computer co-creativity.

This paper presents an exploratory study where participants piloted a commercial UAS (unmanned aerial system) through an obstacle course. The goal was to determine how varying the instructions given to participants affected their performance. Preliminary data suggests future studies to perform, as well as guidelines for human-robot interaction, and some best practices for learning from demonstration studies.

#SMT, or model counting for logical theories, is a well-known hard problem that generalizes such tasks as counting the number of satisfying assignments to a Boolean formula and computing the volume of a polytope. In the realm of satisfiability modulo theories (SMT) there is a growing need for model counting solvers, coming from several application domains (quantitative information flow, static analysis of probabilistic programs). In this paper, we show a reduction from an approximate version of #SMT to SMT. We focus on the theories of integer arithmetic and linear real arithmetic. We propose model counting algorithms that provide approximate solutions with formal bounds on the approximation error. They run in polynomial time and make a polynomial number of queries to the SMT solver for the underlying theory, exploiting "for free" the sophisticated heuristics implemented within modern SMT solvers. We have implemented the algorithms and used them to solve the value problem for a model of loop-free probabilistic programs with nondeterminism.

IllinoisSL is a Java library for learning structured prediction models. It supports structured Support Vector Machines and structured Perceptron. The library consists of a core learning module and several applications, which can be executed from command-lines. Documentation is provided to guide users. In Comparison to other structured learning libraries, IllinoisSL is efficient, general, and easy to use.

We propose nested sequential Monte Carlo (NSMC), a methodology to sample from sequences of probability distributions, even where the random variables are high-dimensional. NSMC generalises the SMC framework by requiring only approximate, properly weighted, samples from the SMC proposal distribution, while still resulting in a correct SMC algorithm. Furthermore, NSMC can in itself be used to produce such properly weighted samples. Consequently, one NSMC sampler can be used to construct an efficient high-dimensional proposal distribution for another NSMC sampler, and this nesting of the algorithm can be done to an arbitrary degree. This allows us to consider complex and high-dimensional models using SMC. We show results that motivate the efficacy of our approach on several filtering problems with dimensions in the order of 100 to 1 000.

We study the value of information in sequential compressed sensing by characterizing the performance of sequential information guided sensing in practical scenarios when information is inaccurate. In particular, we assume the signal distribution is parameterized through Gaussian or Gaussian mixtures with estimated mean and covariance matrices, and we can measure compressively through a noisy linear projection or using one-sparse vectors, i.e., observing one entry of the signal each time. We establish a set of performance bounds for the bias and variance of the signal estimator via posterior mean, by capturing the conditional entropy (which is also related to the size of the uncertainty), and the additional power required due to inaccurate information to reach a desired precision. Based on this, we further study how to estimate covariance based on direct samples or covariance sketching. Numerical examples also demonstrate the superior performance of Info-Greedy Sensing algorithms compared with their random and non-adaptive counterparts.

This paper establishes the consistency of spectral approaches to data clustering. We consider clustering of point clouds obtained as samples of a ground-truth measure. A graph representing the point cloud is obtained by assigning weights to edges based on the distance between the points they connect. We investigate the spectral convergence of both unnormalized and normalized graph Laplacians towards the appropriate operators in the continuum domain. We obtain sharp conditions on how the connectivity radius can be scaled with respect to the number of sample points for the spectral convergence to hold. We also show that the discrete clusters obtained via spectral clustering converge towards a continuum partition of the ground truth measure. Such continuum partition minimizes a functional describing the continuum analogue of the graph-based spectral partitioning. Our approach, based on variational convergence, is general and flexible.

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.