In this effort we propose a novel approach for reconstructing multivariate functions from training data, by identifying both a suitable network architecture and an initialization using polynomial-based approximations. Training deep neural networks using gradient descent can be interpreted as moving the set of network parameters along the loss landscape in order to minimize the loss functional. The initialization of parameters is important for iterative training methods based on descent. Our procedure produces a network whose initial state is a polynomial representation of the training data. The major advantage of this technique is from this initialized state the network may be improved using standard training procedures. Since the network already approximates the data, training is more likely to produce a set of parameters associated with a desirable local minimum. We provide the details of the theory necessary for constructing such networks and also consider several numerical examples that reveal our approach ultimately produces networks which can be effectively trained from our initialized state to achieve an improved approximation for a large class of target functions.

The linear quadratic regulator (LQR) problem has reemerged as an important theoretical benchmark for reinforcement learning-based control of complex dynamical systems with continuous state and action spaces. In contrast with nearly all recent work in this area, we consider multiplicative noise models, which are increasingly relevant because they explicitly incorporate inherent uncertainty and variation in the system dynamics and thereby improve robustness properties of the controller. Robustness is a critical and poorly understood issue in reinforcement learning; existing methods which do not account for uncertainty can converge to fragile policies or fail to converge at all. Additionally, intentional injection of multiplicative noise into learning algorithms can enhance robustness of policies, as observed in ad hoc work on domain randomization. Although policy gradient algorithms require optimization of a non-convex cost function, we show that the multiplicative noise LQR cost has a special property called gradient domination, which is exploited to prove global convergence of policy gradient algorithms to the globally optimum control policy with polynomial dependence on problem parameters. Results are provided both in the model-known and model-unknown settings where samples of system trajectories are used to estimate policy gradients.

Neuromorphic hardware architectures represent a growing family of potential post-Moore's Law Era platforms. Largely due to event-driving processing inspired by the human brain, these computer platforms can offer significant energy benefits compared to traditional von Neumann processors. Unfortunately there still remains considerable difficulty in successfully programming, configuring and deploying neuromorphic systems. We present the Fugu framework as an answer to this need. Rather than necessitating a developer attain intricate knowledge of how to program and exploit spiking neural dynamics to utilize the potential benefits of neuromorphic computing, Fugu is designed to provide a higher level abstraction as a hardware-independent mechanism for linking a variety of scalable spiking neural algorithms from a variety of sources. Individual kernels linked together provide sophisticated processing through compositionality. Fugu is intended to be suitable for a wide-range of neuromorphic applications, including machine learning, scientific computing, and more brain-inspired neural algorithms. Ultimately, we hope the community adopts this and other open standardization attempts allowing for free exchange and easy implementations of the ever-growing list of spiking neural algorithms.

For recurrent neural networks trained on time series with target and exogenous variables, in addition to accurate prediction, it is also desired to provide interpretable insights into the data. In this paper, we explore the structure of LSTM recurrent neural networks to learn variable-wise hidden states, with the aim to capture different dynamics in multi-variable time series and distinguish the contribution of variables to the prediction. With these variable-wise hidden states, a mixture attention mechanism is proposed to model the generative process of the target. Then we develop associated training methods to jointly learn network parameters, variable and temporal importance w.r.t the prediction of the target variable. Extensive experiments on real datasets demonstrate enhanced prediction performance by capturing the dynamics of different variables. Meanwhile, we evaluate the interpretation results both qualitatively and quantitatively. It exhibits the prospect as an end-to-end framework for both forecasting and knowledge extraction over multi-variable data.

The U.S. and China are locked in an increasingly heated struggle for superpower status. Many perceived this confrontation initially only through the lenses of a trade war. However, the ZTE "saga" already indicated the issue was broader and involved a battle for supremacy over 21st century technologies and, relatedly, for international power (see When AI Started Creating AI – Artificial Intelligence and Computing Power, 7 May 2018). The technological battle increasingly looks like a fight to the death, with the offensive against Huawei, aiming notably to protect future 5G networks (Cassell Bryan-Low, Colin Packham, David Lague, Steve Stecklow And Jack Stubbs, "The China Challenge: the 5G Fight", Reuters Investigates, 21 May 2019). For Huawei and China, as well as for the world, consequences are far reaching, as, after Google "stopping Huawei's Android license", and an Intel and Qualcomm ban, the British chip designer ARM, held notably by Japanese Softbank, now stops relations with Huawei (Paul Sandle, "ARM supply halt deals fresh blow to Chinese tech giant Huawei", Reuters, 22 May 2019; "DealBook Briefing: The Huawei Backlash Goes Global", The New York Times, 23 May 2019; Tom Warren, "Huawei's Android And Windows Alternatives Are Destined For Failure", The Verge, 23 May 2019). The highly possible coming American move against Chinese Hikvision, one of the largest world producers of video surveillance systems involving notably "artificial intelligence, speech monitoring and genetic testing" would only further confirm the American offensive (Doina Chiacu, Stella Qi, "Trump says'dangerous' Huawei could be included in U.S.-China trade deal", Reuters, 23 May 2019; Ana Swanson and Edward Wong, "Trump Administration Could Blacklist China's Hikvision, a Surveillance Firm", The New York Times, 21 May 2019). China, for its part, answers to both the trade war and the technological fight with an ideologically martial mobilisation of its population along the lines of "People's War", "The Long March", and changing TV scheduling to broadcast war films (Iris Zhao and Alan Weedon, "Chinese television suddenly switches scheduling to anti-American films amid US-China trade war", ABC News, 20 May 2019; Michael Martina, David Lawder, "Prepare for difficult times, China's Xi urges as trade war simmers", Reuters, 22 May 2019). This highlights how much is as stake for the Middle Kingdom, as we explained previously ( Sensor and Actuator (4): Artificial Intelligence, the Long March towards Advanced Robots and Geopolitics).

We aim to perform unsupervised discovery of objects and their states such as location and velocity, as well as physical system parameters such as mass and gravity from video -- given only the differential equations governing the scene dynamics. Existing physical scene understanding methods require either object state supervision, or do not integrate with differentiable physics to learn interpretable system parameters and states. We address this problem through a $\textit{physics-as-inverse-graphics}$ approach that brings together vision-as-inverse-graphics and differentiable physics engines. This framework allows us to perform long term extrapolative video prediction, as well as vision-based model-predictive control. Our approach significantly outperforms related unsupervised methods in long-term future frame prediction of systems with interacting objects (such as ball-spring or 3-body gravitational systems). We further show the value of this tight vision-physics integration by demonstrating data-efficient learning of vision-actuated model-based control for a pendulum system. The controller's interpretability also provides unique capabilities in goal-driven control and physical reasoning for zero-data adaptation.

The field of fluid mechanics is rapidly advancing, driven by unprecedented volumes of data from experiments, field measurements, and large-scale simulations at multiple spatiotemporal scales. Machine learning presents us with a wealth of techniques to extract information from data that can be translated into knowledge about the underlying fluid mechanics. Moreover, machine learning algorithms can augment domain knowledge and automate tasks related to flow control and optimization. This article presents an overview of past history, current developments, and emerging opportunities of machine learning for fluid mechanics. We outline fundamental machine learning methodologies and discuss their uses for understanding, modeling, optimizing, and controlling fluid flows. The strengths and limitations of these methods are addressed from the perspective of scientific inquiry that links data with modeling, experiments, and simulations. Machine learning provides a powerful information processing framework that can augment, and possibly even transform, current lines of fluid mechanics research and industrial applications.

A fundamental issue in reinforcement learning algorithms is the balance between exploration of the environment and exploitation of information already obtained by the agent. Especially, exploration has played a critical role for both efficiency and efficacy of the learning process. However, Existing works for exploration involve task-agnostic design, that is performing well in one environment, but be ill-suited to another. To the purpose of learning an effective and efficient exploration policy in an automated manner. We formalized a feasible metric for measuring the utility of exploration based on counterfactual ideology. Based on that, We proposed an end-to-end algorithm to learn exploration policy by meta-learning. We demonstrate that our method achieves good results compared to previous works in the high-dimensional control tasks in MuJoCo simulator.

Jordan French is a multi-media journalist on the editorial staff at TheStreet.com He is also the Founder and Executive Editor at Grit Daily News. Formerly an engineer and attorney he represented the "People of the United States" in energy market manipulation cases as an enforcement attorney at the Federal Energy Regulatory Commission. As an engineer he worked on the Mars Gravity Biosatellite Program and later co-founded BeeHex, Inc., the personalized nutrition and robotics company that popularized 3D-printed pizza. The author of forthcoming book, The Gritty Entrepreneur, he is a frequent public speaker, technology evangelist and media moderator.

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.