Robot dogs have come along way from the days of being tipped over by humans. A surprising new video shows off just how advanced the four-legged droids have become, as a'HyQReal' robo-dog can be seen dragging an airplane that weighs a whopping 3 tons across the Geneva Airport in Italy. HyQReal was created by researchers at the Istituto Italiano di Tecnologia (IIT) as a device designed to support humans in emergency situations. Luckily, as the video shows, the robot dog would almost certainly be capable of lifting a heavy human. The robot dog drags the heavy airplane with apparent ease across approximately 33 feet before a researcher with a game controller makes it stop. It's an amazing feat, considering the HyQReal weighs just over 280lbs and is roughly 4ft long.

As if the world of deep-faked pictures and video wasn't scary enough, researchers from Samsung's AI center in Moscow have demonstrated an algorithm that can fabricate videos using only one image. In a video demonstration and a paper published in the pre-print journal ArXiv, the researchers show the capabilities of what is described as'one-shot' and'few-shot' machine learning. The results of their system bring to life popular faces like those of surrealist painter Salvador Dali and actress Marilyn Monroe using a single still image. The more images that are fed into the program, the more realistic the resulting video becomes. Though a single image translated into a moving face may look noticeably altered, a sample of 32 images produces a moving picture with near lifelike accuracy.

The analysis of Belief Propagation and other algorithms for the {\em reconstruction problem} plays a key role in the analysis of community detection in inference on graphs, phylogenetic reconstruction in bioinformatics, and the cavity method in statistical physics. We prove a conjecture of Evans, Kenyon, Peres, and Schulman (2000) which states that any bounded memory message passing algorithm is statistically much weaker than Belief Propagation for the reconstruction problem. More formally, any recursive algorithm with bounded memory for the reconstruction problem on the trees with the binary symmetric channel has a phase transition strictly below the Belief Propagation threshold, also known as the Kesten-Stigum bound. The proof combines in novel fashion tools from recursive reconstruction, information theory, and optimal transport, and also establishes an asymptotic normality result for BP and other message-passing algorithms near the critical threshold.

The control of complex systems is of critical importance in many branches of science, engineering, and industry. Controlling an unsteady fluid flow is particularly important, as flow control is a key enabler for technologies in energy (e.g., wind, tidal, and combustion), transportation (e.g., planes, trains, and automobiles), security (e.g., tracking airborne contamination), and health (e.g., artificial hearts and artificial respiration). However, the high-dimensional, nonlinear, and multi-scale dynamics make real-time feedback control infeasible. Fortunately, these high-dimensional systems exhibit dominant, low-dimensional patterns of activity that can be exploited for effective control in the sense that knowledge of the entire state of a system is not required. Advances in machine learning have the potential to revolutionize flow control given its ability to extract principled, low-rank feature spaces characterizing such complex systems. We present a novel deep learning model predictive control (DeepMPC) framework that exploits low-rank features of the flow in order to achieve considerable improvements to control performance. Instead of predicting the entire fluid state, we use a recurrent neural network (RNN) to accurately predict the control relevant quantities of the system. The RNN is then embedded into a MPC framework to construct a feedback loop, and incoming sensor data is used to perform online updates to improve prediction accuracy. The results are validated using varying fluid flow examples of increasing complexity.

Graph convolutional networks (GCNs) are powerful tools for graph-structured data. However, they have been recently shown to be prone to topological attacks. Despite substantial efforts to search for new architectures, it still remains a challenge to improve performance in both benign and adversarial situations simultaneously. In this paper, we re-examine the fundamental building block of GCN---the Laplacian operator---and highlight some basic flaws in the spatial and spectral domains. As an alternative, we propose an operator based on graph powering, and prove that it enjoys a desirable property of "spectral separation." Based on the operator, we propose a robust learning paradigm, where the network is trained on a family of "'smoothed" graphs that span a spatial and spectral range for generalizability. We also use the new operator in replacement of the classical Laplacian to construct an architecture with improved spectral robustness, expressivity and interpretability. The enhanced performance and robustness are demonstrated in extensive experiments.

The minimization of loss functions is the heart and soul of Machine Learning. In this paper, we propose an off-the-shelf optimization approach that can minimize virtually any non-differentiable and non-decomposable loss function (e.g. Miss-classification Rate, AUC, F1, Jaccard Index, Mathew Correlation Coefficient, etc.) seamlessly. Our strategy learns smooth relaxation versions of the true losses by approximating them through a surrogate neural network. The proposed loss networks are set-wise models which are invariant to the order of mini-batch instances. Ultimately, the surrogate losses are learned jointly with the prediction model via bilevel optimization. Empirical results on multiple datasets with diverse real-life loss functions compared with state-of-the-art baselines demonstrate the efficiency of learning surrogate losses.

Tensor decomposition methods (TDMs) have recently gained popularity as ways of performing inference for latent variable models [Anandkumar et al., 2014]. The interest in these methods is motivated by the fact that they come with theoretical global convergence guarantees in the limit of infinite data [Anandkumar et al., 2012, Arora et al., 2013]. However, a main limitation of these methods is that they lack natural methods for regularization or encouraging desired properties on the model parameters when the amount of data is limited. Previous works attempted to alleviate this drawback by modifying existing tensor decomposition methods to incorporate specific constraints, such as sparsity [Sun et al., 2015], or incorporate modeling assumptions, such as the existence of anchor words [Arora et al., 2013, Nguyen et al., 2014]. All of these works develop bespoke algorithms tailored to those constraints or assumptions. Furthermore, many of these methods impose hard constraints on the learned model, which may be detrimental as the size of the data grow--framed in the context of Bayesian intuition, when we have a lot of data, we want our methods to allow the evidence to overwhelm our priors. We introduce an alternative approach which can be applied to encourage any (differentiable) desired structure or properties on the model parameters, and which will only encourage this "prior" information when the data is insufficient. Specifically, we adopt the common view of Bayesian priors as representing "pseudo-observations" of artificial data which bias our learned model parameters towards our prior belief [Bishop, 2006]. We apply the tensor decomposition method of Anandkumar et al.

Recent reinforcement learning algorithms, though achieving impressive results in various fields, suffer from brittle training effects such as regression in results and high sensitivity to initialization and parameters. We claim that some of the brittleness stems from variance differences, i.e. when different environment areas - states and/or actions - have different rewards variance. This causes two problems: First, the "Boring Areas Trap" in algorithms such as Q-learning, where moving between areas depends on the current area variance, and getting out of a boring area is hard due to its low variance. Second, the "Manipulative Consultant" problem, when value-estimation functions used in DQN and Actor-Critic algorithms influence the agent to prefer boring areas, regardless of the mean rewards return, as they maximize estimation precision rather than rewards. This sheds a new light on how exploration contribute to training, as it helps with both challenges. Cognitive experiments in humans showed that noised reward signals may paradoxically improve performance. We explain this using the two mentioned problems, claiming that both humans and algorithms may share similar challenges. Inspired by this result, we propose the Adaptive Symmetric Reward Noising (ASRN), by which we mean adding Gaussian noise to rewards according to their states' estimated variance, thus avoiding the two problems while not affecting the environment's mean rewards behavior. We conduct our experiments in a Multi Armed Bandit problem with variance differences. We demonstrate that a Q-learning algorithm shows the brittleness effect in this problem, and that the ASRN scheme can dramatically improve the results. We show that ASRN helps a DQN algorithm training process reach better results in an end to end autonomous driving task using the AirSim driving simulator.

In Multi-Agent Systems (MAS) there are two main models of interaction: among agents, and between agents and the environment. Although there are studies considering these models, there is no practical tool to afford the interaction with external entities with both models. This paper presents a proposal for such a tool based on the Apache Camel framework by designing two new components, namely camel-jason and camel-artifact. By means of these components, an external entity is modelled according to its nature, i.e., whether it is autonomous or non-autonomous, interacting with the MAS respectively as an agent or an artifact. It models coherently external entities whereas Camel provides interoperability with several communication protocols.

We explore self-supervised models that can be potentially deployed on mobile devices to learn general purpose audio representations. Specifically, we propose methods that exploit the temporal context in the spectrogram domain. One method estimates the temporal gap between two short audio segments extracted at random from the same audio clip. The other methods are inspired by Word2Vec, a popular technique used to learn word embeddings, and aim at reconstructing a temporal spectrogram slice from past and future slices or, alternatively, at reconstructing the context of surrounding slices from the current slice. We focus our evaluation on small encoder architectures, which can be potentially run on mobile devices during both inference (re-using a common learned representation across multiple downstream tasks) and training (capturing the true data distribution without compromising users' privacy when combined with federated learning). We evaluate the quality of the embeddings produced by the self-supervised learning models, and show that they can be re-used for a variety of downstream tasks, and for some tasks even approach the performance of fully supervised models of similar size.