Recognizing facial expressions from static images or video sequences is a widely studied but still challenging problem. The recent progresses obtained by deep neural architectures, or by ensembles of heterogeneous models, have shown that integrating multiple input representations leads to state-of-the-art results. In particular, the appearance and the shape of the input face, or the representations of some face parts, are commonly used to boost the quality of the recognizer. This paper investigates the application of Convolutional Neural Networks (CNNs) with the aim of building a versatile recognizer of expressions in static images that can be further applied to video sequences. We first study the importance of different face parts in the recognition task, focussing on appearance and shape-related features. Then we cast the learning problem in the Semi-Supervised setting, exploiting video data, where only a few frames are supervised. The unsupervised portion of the training data is used to enforce three types of coherence, namely temporal coherence, coherence among the predictions on the face parts and coherence between appearance and shape-based representation. Our experimental analysis shows that coherence constraints can improve the quality of the expression recognizer, thus offering a suitable basis to profitably exploit unsupervised video sequences. Finally we present some examples with occlusions where the shape-based predictor performs better than the appearance one.

In this paper we develop a fully decentralized algorithm for policy evaluation with off-policy learning, linear function approximation, and $O(n)$ complexity in both computation and memory requirements. The proposed algorithm is of the variance reduced kind and achieves linear convergence. We consider the case where a collection of agents have distinct and fixed size datasets gathered following different behavior policies (none of which is required to explore the full state space) and they all collaborate to evaluate a common target policy. The network approach allows all agents to converge to the optimal solution even in situations where neither agent can converge on its own without cooperation. We provide simulations to illustrate the effectiveness of the method.

Low-rank inducing unitarily invariant norms have been introduced to convexify problems with low-rank/sparsity constraint. They are the convex envelope of a unitary invariant norm and the indicator function of an upper bounding rank constraint. The most well-known member of this family is the so-called nuclear norm. To solve optimization problems involving such norms with proximal splitting methods, efficient ways of evaluating the proximal mapping of the low-rank inducing norms are needed. This is known for the nuclear norm, but not for most other members of the low-rank inducing family. This work supplies a framework that reduces the proximal mapping evaluation into a nested binary search, in which each iteration requires the solution of a much simpler problem. This simpler problem can often be solved analytically as it is demonstrated for the so-called low-rank inducing Frobenius and spectral norms. Moreover, the framework allows to compute the proximal mapping of compositions of these norms with increasing convex functions and the projections onto their epigraphs. This has the additional advantage that we can also deal with compositions of increasing convex functions and low-rank inducing norms in proximal splitting methods.

It has been shown that neural network classifiers are not robust. This raises concerns about their usage in safety-critical systems. We propose in this paper a regularization scheme for ReLU networks which provably improves the robustness of the classifier by maximizing the linear region of the classifier as well as the distance to the decision boundary. Our techniques allow even to find the minimal adversarial perturbation for a fraction of test points for large networks. In the experiments we show that our approach improves upon adversarial training both in terms of lower and upper bounds on the robustness and is comparable or better than the state of the art in terms of test error and robustness.

In applications like computer aided design, geometric models are often represented numerically as polynomial splines or NURBS, even when they originate from primitive geometry. For purposes such as redesign and isogeometric analysis, it is of interest to extract information about the underlying geometry through reverse engineering. In this work we develop a novel method to determine these primitive shapes by combining clustering analysis with approximate implicitization. The proposed method is automatic and can recover algebraic hypersurfaces of any degree in any dimension. In exact arithmetic, the algorithm returns exact results. All the required parameters, such as the implicit degree of the patches and the number of clusters of the model, are inferred using numerical approaches in order to obtain an algorithm that requires as little manual input as possible. The effectiveness, efficiency and robustness of the method are shown both in a theoretical analysis and in numerical examples implemented in Python.

However, acquiring manual labels as ground truth is both labor intensive and time consuming. Furthermore, non-standardized manual segmentation protocols and inter-and intra-observer variability add another factor of variation to an already complex problem. Instead of increasing the number of manual labels, we propose to improve generalization by teaching a neural network to minimize an undesirable form of variation, namely acquisitionbased variation. The proposed network learns a representation [1] in which for example gray matter patches acquired with a 1.5T scanner and a 3T scanner are considered similar. Therefore it has the potential to fully exploit a 1.5T data set with fully labeled brain tissues for segmenting an unlabelled 3T data set. Overcoming acquisition-variation is a relatively new challenge in medical imaging. Transfer classifiers have been proposed that focus on weighting classifiers based on how well their training data matches the test data, such as weighted SVM's [2] and weighted ensembles [3].

We present a novel intelligent tutoring system which builds upon well-established hypotheses in educational psychology and incorporates them inside of a scalable software architecture. Specifically, we build upon the known benefits of knowledge vocalization, parallel learning, and immediate feedback in the context of student learning. We show that open-source data combined with state-of-the-art techniques in deep learning and natural language processing can apply the benefits of these three factors at scale, while still operating at the granularity of individual student needs and recommendations. Additionally, we allow teachers to retain full control of the outputs of the algorithms, and provide student statistics to help better guide classroom discussions towards topics that would benefit from more in-person review and coverage. Our experiments and pilot programs show promising results, and cement our hypothesis that the system is flexible enough to serve a wide variety of purposes in both classroom and classroom-free settings.

The discussion between the automotive industry, governments, ethicists, policy makers and general public about autonomous cars' moral agency is widening, and therefore we see the need to bring more insight into what meta-factors might actually influence the outcomes of such discussions, surveys and plebiscites. In our study, we focus on the psychological (personality traits), practical (active driving experience), gender and rhetoric/framing factors that might impact and even determine respondents' a priori preferences of autonomous cars' operation. We conducted an online survey (N=430) to collect data that show that the third person scenario is less biased than the first person scenario when presenting ethical dilemma related to autonomous cars. According to our analysis, gender bias should be explored in more extensive future studies as well. We recommend any participatory technology assessment discourse to use the third person scenario and to direct attention to the way any autonomous car related debate is introduced, especially in terms of linguistic and communication aspects and gender.

At IROS in Madrid a few weeks ago, Marc Raibert showed a few new videos during his keynote presentation. One was of Atlas doing parkour, which showed up on YouTube last week, and the other was just a brief clip of SpotMini dancing, which Raibert said was a work in progress. Today, Boston Dynamics posted a new video of SpotMini (which they're increasingly referring to as simply "Spot") dancing to Uptown Funk, and frankly displaying more talent than the original human performance. The twerking is cute, but gets a little weird when you realize that SpotMini's got some eyeballs back there as well. While we don't know exactly what's going on in this video (as with many of Boston Dynamics' video), my guess would be that these are a series of discrete, scripted behaviors that are played in sequence.

When we think of ancient Greece we generally imagine ruthless highly-trained warriors or cloth clad philosophers pondering the schematics and perimeters of geometry, geography, architecture and the like. But a new book is about to present them as "skilled forecasters, accurately predicting the rise of artificial intelligence, killer androids and driverless cars." More than 2,500 years ago, Greek mythologists, according to American historian Dr Adrienne Mayor of Stanford University, "envisioned many of the technology trends we grapple with today including Killer androids, driverless technology, GPS and AI-powered helper robots." According to an article about Mayors finding in Greek Reporter, in her forthcoming book Gods and Robots: Myths, Machines, and Ancient Dreams of Technology the creations of Hephaestus, the god of metalworking and an invention in Homer's Iliad, were "predictions of the rise of humanoid robots." Dr Mayor, who according to the Stanford University website is an independent folklorist/historian of science investigating natural knowledge contained in pre-scientific myths and oral traditions, claims Hephaestus crafted'mechanical maid's from gold that were designed to anticipate their master's requests and act on them without instruction, much like modern machine learning software.