Inspired by works from the psychology community, we first study the link between the compact two-dimensional representation of the emotion known as arousal-valence, and discrete emotion classes (e.g. anger, happiness, sadness, etc.) used in the computer vision community. It enables to assess the benefits -- in terms of discrete emotion inference -- of adding an extra dimension to arousal-valence (usually named dominance). Building on these observations, we propose CAKE, a 3-dimensional representation of emotion learned in a multi-domain fashion, achieving accurate emotion recognition on several public datasets. Moreover, we visualize how emotions boundaries are organized inside DNN representations and show that DNNs are implicitly learning arousal-valence-like descriptions of emotions. Finally, we use the CAKE representation to compare the quality of the annotations of different public datasets.

We study invariant local expansion operators for conflict-free and admissible sets in Abstract Argumentation Frameworks (AFs). Such operators are directly applied on AFs, and are invariant with respect to a chosen "semantics" (that is w.r.t. each of the conflict free/admissible set of arguments). Accordingly, we derive a definition of robustness for AFs in terms of the number of times such operators can be applied without producing any change in the chosen semantics.

Mobile networks possess information about the users as well as the network. Such information is useful for making the network end-to-end visible and intelligent. Big data analytics can efficiently analyze user and network information, unearth meaningful insights with the help of machine learning tools. Utilizing big data analytics and machine learning, this work contributes in three ways. First, we utilize the call detail records (CDR) data to detect anomalies in the network. For authentication and verification of anomalies, we use k-means clustering, an unsupervised machine learning algorithm. Through effective detection of anomalies, we can proceed to suitable design for resource distribution as well as fault detection and avoidance. Second, we prepare anomaly-free data by removing anomalous activities and train a neural network model. By passing anomaly and anomaly-free data through this model, we observe the effect of anomalous activities in training of the model and also observe mean square error of anomaly and anomaly free data. Lastly, we use an autoregressive integrated moving average (ARIMA) model to predict future traffic for a user. Through simple visualization, we show that anomaly free data better generalizes the learning models and performs better on prediction task.

We study the problem of synthesizing a policy that maximizes the entropy of a Markov decision process (MDP) subject to a temporal logic constraint. Such a policy minimizes the predictability of the paths it generates, or dually, maximizes the continual exploration of different paths in an MDP while ensuring the satisfaction of a temporal logic specification. We first show that the maximum entropy of an MDP can be finite, infinite or unbounded. We provide necessary and sufficient conditions under which the maximum entropy of an MDP is finite, infinite or unbounded. We then present an algorithm to synthesize a policy that maximizes the entropy of an MDP. The proposed algorithm is based on a convex optimization problem and runs in time polynomial in the size of the MDP. We also show that maximizing the entropy of an MDP is equivalent to maximizing the entropy of the paths that reach a certain set of states in the MDP. Finally, we extend the algorithm to an MDP subject to a temporal logic specification. In numerical examples, we demonstrate the proposed method on different motion planning scenarios and illustrate that as the restrictions imposed on the paths by a specification increase, the maximum entropy decreases, which in turn, increases the predictability of paths.

This paper introduces the settlement generation competition for Minecraft, the first part of the Generative Design in Minecraft challenge. The settlement generation competition is about creating Artificial Intelligence (AI) agents that can produce functional, aesthetically appealing and believable settlements adapted to a given Minecraft map -- ideally at a level that can compete with human created designs. The aim of the competition is to advance procedural content generation for games, especially in overcoming the challenges of adaptive and holistic PCG. The paper introduces the technical details of the challenge, but mostly focuses on what challenges this competition provides and why they are scientifically relevant.

However, far-field speech, especially when recorded with single microphone, remains one of the major obstacles to achieving complete human parity, mainly because of challenging environments with a lot of noises and reverberations [3-7]. Another challenge is that it is almost impossible to collect data covering all recording environments to train and to test on due to variations of reverberations/noises and distances to microphones. While there were some advancements in this direction for a few widespread languages, a large number of low-resource languages will inevitably remain uncovered by such kind of resources. These facts motivate our interest for methods to improve robustness of acoustic model by utilizing available data, especially data from resource rich languages [8]. It is well known that a mismatch between training and testing conditions is likely to degrade accuracy of acoustic models.

Semantic labeling for very high resolution (VHR) images in urban areas, is of significant importance in a wide range of remote sensing applications. However, many confusing manmade objects and intricate fine-structured objects make it very difficult to obtain both coherent and accurate labeling results. For this challenging task, we propose a novel deep model with convolutional neural networks (CNNs), i.e., an end-to-end self-cascaded network (ScasNet). Specifically, for confusing manmade objects, ScasNet improves the labeling coherence with sequential global-to-local contexts aggregation. Technically, multi-scale contexts are captured on the output of a CNN encoder, and then they are successively aggregated in a self-cascaded manner. Meanwhile, for fine-structured objects, ScasNet boosts the labeling accuracy with a coarse-to-fine refinement strategy. It progressively refines the target objects using the low-level features learned by CNN's shallow layers. In addition, to correct the latent fitting residual caused by multi-feature fusion inside ScasNet, a dedicated residual correction scheme is proposed. It greatly improves the effectiveness of ScasNet. Extensive experimental results on three public datasets, including two challenging benchmarks, show that ScasNet achieves the state-of-the-art performance.

In this work, we propose an alternative solution for parallel wave generation by WaveNet. In contrast to parallel WaveNet (Oord et al., 2018), we distill a Gaussian inverse autoregressive flow from the autoregressive WaveNet by minimizing a novel regularized KL divergence between their highly-peaked output distributions. Our method computes the KL divergence in closed-form, which simplifies the training algorithm and provides very efficient distillation. In addition, we propose the first text-to-wave neural architecture for speech synthesis, which is fully convolutional and enables fast end-to-end training from scratch. It significantly outperforms the previous pipeline that connects a text-to-spectrogram model to a separately trained WaveNet (Ping et al., 2018). We also successfully distill a parallel waveform synthesizer conditioned on the hidden representation in this end-to-end model.

Convolutional Neural Networks (CNN) for image recognition tasks are seeing rapid advances in the available architectures and how networks are trained based on large computational infrastructure and standard datasets with millions of images. In contrast, performance and time constraints for example, of small devices and free cloud GPUs necessitate efficient network training (i.e., highest accuracy in the shortest inference time possible), often on small datasets. Here, we hypothesize that initially decreasing image size during training makes the training process more efficient, because pre-shaping weights with small images and later utilizing these weights with larger images reduces initial network parameters and total inference time. We test this Efficient Network TRaining (ENTR) Hypothesis by training pre-trained Residual Network (ResNet) models (ResNet18, 34, & 50) on three small datasets (steel microstructures, bee images, and geographic aerial images) with a free cloud GPU. Based on three training regimes of i) not, ii) gradually or iii) in one step increasing image size over the training process, we show that initially reducing image size increases training efficiency consistently across datasets and networks. We interpret these results mechanistically in the framework of regularization theory. Support for the ENTR hypothesis is an important contribution, because network efficiency improvements for image recognition tasks are needed for practical applications. In the future, it will be exciting to see how the ENTR hypothesis holds for large standard datasets like ImageNet or CIFAR, to better understand the underlying mechanisms, and how these results compare to other fields such as structural learning.

We describe a general framework for probabilistic modeling of complex scenes and inference from ambiguous observations. The approach is motivated by applications in image analysis and is based on the use of priors defined by stochastic grammars. We define a class of grammars that capture relationships between the objects in a scene and provide important contextual cues for statistical inference. The distribution over scenes defined by a probabilistic scene grammar can be represented by a graphical model and this construction can be used for efficient inference with loopy belief propagation. We show experimental results with two different applications. One application involves the reconstruction of binary contour maps. Another application involves detecting and localizing faces in images. In both applications the same framework leads to robust inference algorithms that can effectively combine local information to reason about a scene.