OBJECTIVE: We aim to extract and denoise the attended speaker in a noisy, two-speaker acoustic scenario, relying on microphone array recordings from a binaural hearing aid, which are complemented with electroencephalography (EEG) recordings to infer the speaker of interest. METHODS: In this study, we propose a modular processing flow that first extracts the two speech envelopes from the microphone recordings, then selects the attended speech envelope based on the EEG, and finally uses this envelope to inform a multi-channel speech separation and denoising algorithm. RESULTS: Strong suppression of interfering (unattended) speech and background noise is achieved, while the attended speech is preserved. Furthermore, EEG-based auditory attention detection (AAD) is shown to be robust to the use of noisy speech signals. CONCLUSIONS: Our results show that AAD-based speaker extraction from microphone array recordings is feasible and robust, even in noisy acoustic environments, and without access to the clean speech signals to perform EEG-based AAD. SIGNIFICANCE: Current research on AAD always assumes the availability of the clean speech signals, which limits the applicability in real settings. We have extended this research to detect the attended speaker even when only microphone recordings with noisy speech mixtures are available. This is an enabling ingredient for new brain-computer interfaces and effective filtering schemes in neuro-steered hearing prostheses. Here, we provide a first proof of concept for EEG-informed attended speaker extraction and denoising.

We consider the problem of learning a realization for a linear time-invariant (LTI) dynamical system from input/output data. Given a single input/output trajectory, we provide finite time analysis for learning the system's Markov parameters, from which a balanced realization is obtained using the classical Ho-Kalman algorithm. By proving a stability result for the Ho-Kalman algorithm and combining it with the sample complexity results for Markov parameters, we show how much data is needed to learn a balanced realization of the system up to a desired accuracy with high probability.

Optimizing distributed learning systems is an art of balancing between computation and communication. There have been two lines of research that try to deal with slower networks: {\em communication compression} for low bandwidth networks, and {\em decentralization} for high latency networks. In this paper, We explore a natural question: {\em can the combination of both techniques lead to a system that is robust to both bandwidth and latency?} Although the system implication of such combination is trivial, the underlying theoretical principle and algorithm design is challenging: unlike centralized algorithms, simply compressing exchanged information, even in an unbiased stochastic way, within the decentralized network would accumulate the error and fail to converge. In this paper, we develop a framework of compressed, decentralized training and propose two different strategies, which we call {\em extrapolation compression} and {\em difference compression}. We analyze both algorithms and prove both converge at the rate of $O(1/\sqrt{nT})$ where $n$ is the number of workers and $T$ is the number of iterations, matching the convergence rate for full precision, centralized training. We validate our algorithms and find that our proposed algorithm outperforms the best of merely decentralized and merely quantized algorithm significantly for networks with {\em both} high latency and low bandwidth.

Designing a data sharing mechanism without sacrificing too much privacy can be considered as a game between data holders and malicious attackers. This paper describes a compressive adversarial privacy framework that captures the trade-off between the data privacy and utility. We characterize the optimal data releasing mechanism through convex optimization when assuming that both the data holder and attacker can only modify the data using linear transformations. We then build a more realistic data releasing mechanism that can rely on a nonlinear compression model while the attacker uses a neural network. We demonstrate in a series of empirical applications that this framework, consisting of compressive adversarial privacy, can preserve sensitive information.

We consider a set of learning agents in a collaborative peer-to-peer network, where each agent learns a personalized model according to its own learning objective. The question addressed in this paper is: how can agents improve upon their locally trained model by communicating with other agents that have similar objectives? We introduce and analyze two asynchronous gossip algorithms running in a fully decentralized manner. Our first approach, inspired from label propagation, aims to smooth pre-trained local models over the network while accounting for the confidence that each agent has in its initial model. In our second approach, agents jointly learn and propagate their model by making iterative updates based on both their local dataset and the behavior of their neighbors. To optimize this challenging objective, our decentralized algorithm is based on ADMM.

This paper considers the chattering problem of sliding mode control while delay in robot manipulator caused chaos in such electromechanical systems. Fractional calculus as a powerful theorem to produce a novel sliding mode; which has a dynamic essence is used for chattering elimination. To realize the control of a class of chaotic systems in master-slave configuration this novel fractional dynamic sliding mode control scheme is presented and examined on delay based chaotic robot in joint and work space. Also the stability of the closed-loop system is guaranteed by Lyapunov stability theory. Beside these, delayed robot motions are sorted out for qualitative and quantification study. Finally, numerical simulation example illustrates the feasibility of proposed control method.

Inverse Problems in medical imaging and computer vision are traditionally solved using purely model-based methods. Among those variational regularization models are one of the most popular approaches. We propose a new framework for applying data-driven approaches to inverse problems, using a neural network as a regularization functional. The network learns to discriminate between the distribution of ground truth images and the distribution of unregularized reconstructions. Once trained, the network is applied to the inverse problem by solving the corresponding variational problem. Unlike other data-based approaches for inverse problems, the algorithm can be applied even if only unsupervised training data is available. Experiments demonstrate the potential of the framework for denoising on the BSDS dataset and for computed tomography reconstruction on the LIDC dataset.

Several test function suites are being used for numerical benchmarking of multiobjective optimization algorithms. While they have some desirable properties, like well-understood Pareto sets and Pareto fronts of various shapes, most of the currently used functions possess characteristics that are arguably under-represented in real-world problems. They mainly stem from the easier construction of such functions and result in improbable properties such as separability, optima located exactly at the boundary constraints, and the existence of variables that solely control the distance between a solution and the Pareto front. Here, we propose an alternative way to constructing multiobjective problems-by combining existing single-objective problems from the literature. We describe in particular the bbob-biobj test suite with 55 bi-objective functions in continuous domain, and its extended version with 92 bi-objective functions (bbob-biobj-ext). Both test suites have been implemented in the COCO platform for black-box optimization benchmarking. Finally, we recommend a general procedure for creating test suites for an arbitrary number of objectives. Besides providing the formal function definitions and presenting their (known) properties, this paper also aims at giving the rationale behind our approach in terms of groups of functions with similar properties, objective space normalization, and problem instances. The latter allows us to easily compare the performance of deterministic and stochastic solvers, which is an often overlooked issue in benchmarking.

With the recent developments in the unmanned aerial vehicles (UAV), it is expected them to interact and collaborate with their surrounding objects, other robots and people in order to wisely plan and execute particular tasks. Although these interaction operations are inherently challenging as compared to free-flight missions, they might bring diverse advantages. One of them is their basic aerodynamic interaction during the flight in close proximities which can result in a reduction of the controller effort. In this study, by collecting real-time data, we have observed that the current drawn by the battery can be decreased while flying very close to the surroundings with the help of the ceiling effect. For the first time, this phenomenon is analyzed in terms of battery lifetime degradation by using a simple full equivalent cycle counting method. Results show that cycling related effect on battery degradation can be reduced by a 15.77% if the UAV can utilize ceiling effect.

Action anticipation, intent prediction, and proactive behavior are all desirable characteristics for autonomous driving policies in interactive scenarios. Paramount, however, is ensuring safety on the road --- a key challenge in doing so is accounting for uncertainty in human driver actions without unduly impacting planner performance. This paper introduces a minimally-interventional safety controller operating within an autonomous vehicle control stack with the role of ensuring collision-free interaction with an externally controlled (e.g., human-driven) counterpart. We leverage reachability analysis to construct a real-time (100Hz) controller that serves the dual role of (1) tracking an input trajectory from a higher-level planning algorithm using model predictive control, and (2) assuring safety through maintaining the availability of a collision-free escape maneuver as a persistent constraint regardless of whatever future actions the other car takes. A full-scale steer-by-wire platform is used to conduct traffic weaving experiments wherein the two cars, initially side-by-side, must swap lanes in a limited amount of time and distance, emulating cars merging onto/off of a highway. We demonstrate that, with our control stack, the autonomous vehicle is able to avoid collision even when the other car defies the planner's expectations and takes dangerous actions, either carelessly or with the intent to collide, and otherwise deviates minimally from the planned trajectory to the extent required to maintain safety.

We propose a new sample-efficient methodology, called Supervised Policy Update (SPU), for deep reinforcement learning. Starting with data generated by the current policy, SPU formulates and solves a constrained optimization problem in the non-parameterized proximal policy space. Using supervised regression, it then converts the optimal non-parameterized policy to a parameterized policy, from which it draws new samples. The methodology is general in that it applies to both discrete and continuous action spaces, and can handle a wide variety of proximity constraints for the non-parameterized optimization problem. We show how the Natural Policy Gradient and Trust Region Policy Optimization (NPG/TRPO) problems, and the Proximal Policy Optimization (PPO) problem can be addressed by this methodology. The SPU implementation is much simpler than TRPO. In terms of sample efficiency, our extensive experiments show SPU outperforms TRPO in Mujoco simulated robotic tasks and outperforms PPO in Atari video game tasks.

Determining extrinsic calibration parameters is a necessity in any robotic system composed of actuators and cameras. Once a system is outside the lab environment, parameters must be determined without relying on outside artifacts such as calibration targets. We propose a method that relies on structured motion of an observed arm to recover extrinsic calibration parameters. Our method combines known arm kinematics with observations of conics in the image plane to calculate maximum-likelihood estimates for calibration extrinsics. This method is validated in simulation and tested against a real-world model, yielding results consistent with ruler-based estimates. Our method shows promise for estimating the pose of a camera relative to an articulated arm's end effector without requiring tedious measurements or external artifacts. Index Terms: robotics, hand-eye problem, self-calibration, structure from motion

Botnet, a group of coordinated bots, is becoming the main platform of malicious Internet activities like DDOS, click fraud, web scraping, spam/rumor distribution, etc. This paper focuses on design and experiment of a new approach for botnet detection from streaming web server logs, motivated by its wide applicability, real-time protection capability, ease of use and better security of sensitive data. Our algorithm is inspired by a Principal Component Analysis (PCA) to capture correlation in data, and we are first to recognize and adapt Lanczos method to improve the time complexity of PCA-based botnet detection from cubic to sub-cubic, which enables us to more accurately and sensitively detect botnets with sliding time windows rather than fixed time windows. We contribute a generalized online correlation matrix update formula, and a new termination condition for Lanczos iteration for our purpose based on error bound and non-decreasing eigenvalues of symmetric matrices. On our dataset of an ecommerce website logs, experiments show the time cost of Lanczos method with different time windows are consistently only 20% to 25% of PCA.

Crash prediction is a critical component of road safety analyses. A widely adopted approach to crash prediction is application of regression based techniques. The underlying calibration process is often time-consuming, requiring significant domain knowledge and expertise and cannot be easily automated. This paper introduces a new machine learning (ML) based approach as an alternative to the traditional techniques. The proposed ML model is called regularized deep belief network, which is a deep neural network with two training steps: it is first trained using an unsupervised learning algorithm and then fine-tuned by initializing a Bayesian neural network with the trained weights from the first step. The resulting model is expected to have improved prediction power and reduced need for the time-consuming human intervention. In this paper, we attempt to demonstrate the potential of this new model for crash prediction through two case studies including a collision data set from 800 km stretch of Highway 401 and other highways in Ontario, Canada. Our intention is to show the performance of this ML approach in comparison to various traditional models including negative binomial (NB) model, kernel regression (KR), and Bayesian neural network (Bayesian NN). We also attempt to address other related issues such as effect of training data size and training parameters.

The low-rank matrix approximation problem with respect to the component-wise $\ell_1$-norm ($\ell_1$-LRA), which is closely related to robust principal component analysis (PCA), has become a very popular tool in data mining and machine learning. Robust PCA aims at recovering a low-rank matrix that was perturbed with sparse noise, with applications for example in foreground-background video separation. Although $\ell_1$-LRA is strongly believed to be NP-hard, there is, to the best of our knowledge, no formal proof of this fact. In this paper, we prove that $\ell_1$-LRA is NP-hard, already in the rank-one case, using a reduction from MAX CUT. Our derivations draw interesting connections between $\ell_1$-LRA and several other well-known problems, namely, robust PCA, $\ell_0$-LRA, binary matrix factorization, a particular densest bipartite subgraph problem, the computation of the cut norm of $\{-1,+1\}$ matrices, and the discrete basis problem, which we all prove to be NP-hard.

Within a decade, almost every major auto company, along with fleet operators such as Uber, have announced plans to put autonomous vehicles on the road. At the same time, electric vehicles are quickly emerging as a next-generation technology that is cost effective, in addition to offering the benefits of reducing the carbon footprint. The combination of a centrally managed fleet of driverless vehicles, along with the operating characteristics of electric vehicles, is creating a transformative new technology that offers significant cost savings with high service levels. This problem involves a dispatch problem for assigning riders to cars, a surge pricing problem for deciding on the price per trip and a planning problem for deciding on the fleet size. We use approximate dynamic programming to develop high-quality operational dispatch strategies to determine which car is best for a particular trip, when a car should be recharged, and when it should be re-positioned to a different zone which offers a higher density of trips. We prove that the value functions are monotone in the battery and time dimensions and use hierarchical aggregation to get better estimates of the value functions with a small number of observations. Then, surge pricing is discussed using an adaptive learning approach to decide on the price for each trip. Finally, we discuss the fleet size problem which depends on the previous two problems.

The graph Laplacian is a standard tool in data science, machine learning, and image processing. The corresponding matrix inherits the complex structure of the underlying network and is in certain applications densely populated. This makes computations, in particular matrix-vector products, with the graph Laplacian a hard task. A typical application is the computation of a number of its eigenvalues and eigenvectors. Standard methods become infeasible as the number of nodes in the graph is too large. We propose the use of the fast summation based on the nonequispaced fast Fourier transform (NFFT) to perform the dense matrix-vector product with the graph Laplacian fast without ever forming the whole matrix. The enormous flexibility of the NFFT algorithm allows us to embed the accelerated multiplication into Lanczos-based eigenvalues routines or iterative linear system solvers and even consider other than the standard Gaussian kernels. We illustrate the feasibility of our approach on a number of test problems from image segmentation to semi-supervised learning based on graph-based PDEs. In particular, we compare our approach with the Nyström method. Moreover, we present and test an enhanced, hybrid version of the Nyström method, which internally uses the NFFT.

The authors present empirical distributions for the halting time (measured by the number of iterations to reach a given accuracy) of optimization algorithms applied to two random systems: spin glasses and deep learning. Given an algorithm, which we take to be both the optimization routine and the form of the random landscape, the fluctuations of the halting time follow a distribution that, after centering and scaling, remains unchanged even when the distribution on the landscape is changed. We observe two qualitative classes: A Gumbel-like distribution that appears in Google searches, human decision times, the QR eigenvalue algorithm and spin glasses, and a Gaussian-like distribution that appears in conjugate gradient method, deep network with MNIST input data and deep network with random input data. This empirical evidence suggests presence of a class of distributions for which the halting time is independent of the underlying distribution under some conditions.

In this paper we propose a deterministic approach for the reconstruction of Dynamic Susceptibility Contrast magnetic resonance imaging data and compare it with the compressed sensing solution existing in the literature for the same problem. Our study is based on the mathematical analysis of the problem, which is computationally intractable because of its non polynomial complexity, but suggests simple heuristics that perform quite well. We give results on real images and on artificial phantoms with added noise.

Although deep reinforcement learning (deep RL) methods have lots of strengths that are favorable if applied to autonomous driving, real deep RL applications in autonomous driving have been slowed down by the modeling gap between the source (training) domain and the target (deployment) domain. Unlike current policy transfer approaches, which generally limit to the usage of uninterpretable neural network representations as the transferred features, we propose to transfer concrete kinematic quantities in autonomous driving. The proposed robust-control-based (RC) generic transfer architecture, which we call RL-RC, incorporates a transferable hierarchical RL trajectory planner and a robust tracking controller based on disturbance observer (DOB). The deep RL policies trained with known nominal dynamics model are transfered directly to the target domain, DOB-based robust tracking control is applied to tackle the modeling gap including the vehicle dynamics errors and the external disturbances such as side forces. We provide simulations validating the capability of the proposed method to achieve zero-shot transfer across multiple driving scenarios such as lane keeping, lane changing and obstacle avoidance.

In recent work, redressed warped frames have been introduced for the analysis and synthesis of audio signals with non-uniform frequency and time resolutions. In these frames, the allocation of frequency bands or time intervals of the elements of the representation can be uniquely described by means of a warping map. Inverse warping applied after time-frequency sampling provides the key to reduce or eliminate dispersion of the warped frame elements in the conjugate variable, making it possible, e.g., to construct frequency warped frames with synchronous time alignment through frequency. The redressing procedure is however exact only when the analysis and synthesis windows have compact support in the domain where warping is applied. This implies that frequency warped frames cannot have compact support in the time domain. This property is undesirable when online computation is required. Approximations in which the time support is finite are however possible, which lead to small reconstruction errors. In this paper we study the approximation error for compactly supported frequency warped analysis-synthesis elements, providing a few examples and case studies.

Convolution has been playing a prominent role in various applications in science and engineering for many years. It is the most important operation in convolutional neural networks. There has been a recent growth of interests of research in generalizing convolutions on curved domains such as manifolds and graphs. However, existing approaches cannot preserve all the desirable properties of Euclidean convolutions, namely compactly supported filters, directionality, transferability across different manifolds. In this paper we develop a new generalization of the convolution operation, referred to as parallel transport convolution (PTC), on Riemannian manifolds and their discrete counterparts. PTC is designed based on the parallel transportation which is able to translate information along a manifold and to intrinsically preserve directionality. PTC allows for the construction of compactly supported filters and is also robust to manifold deformations. This enables us to preform wavelet-like operations and to define deep convolutional neural networks on curved domains.

The wide adoption of DNNs has given birth to unrelenting computing requirements, forcing datacenter operators to adopt domain-specific accelerators to train them. These accelerators typically employ densely packed full precision floating-point arithmetic to maximize performance per area. Ongoing research efforts seek to further increase that performance density by replacing floating-point with fixed-point arithmetic. However, a significant roadblock for these attempts has been fixed point's narrow dynamic range, which is insufficient for DNN training convergence. We identify block floating point (BFP) as a promising alternative representation since it exhibits wide dynamic range and enables the majority of DNN operations to be performed with fixed-point logic. Unfortunately, BFP alone introduces several limitations that preclude its direct applicability. In this work, we introduce HBFP, a hybrid BFP-FP approach, which performs all dot products in BFP and other operations in floating point. HBFP delivers the best of both worlds: the high accuracy of floating point at the superior hardware density of fixed point. For a wide variety of models, we show that HBFP matches floating point's accuracy while enabling hardware implementations that deliver up to 8.5x higher throughput.

Advances in the field of inverse reinforcement learning (IRL) have led to sophisticated inference frameworks that relax the original modeling assumption of observing an agent behavior that reflects only a single intention. Instead of learning a global behavioral model, recent IRL methods divide the demonstration data into parts, to account for the fact that different trajectories may correspond to different intentions, e.g., because they were generated by different domain experts. In this work, we go one step further: using the intuitive concept of subgoals, we build upon the premise that even a single trajectory can be explained more efficiently locally within a certain context than globally, enabling a more compact representation of the observed behavior. Based on this assumption, we build an implicit intentional model of the agent's goals to forecast its behavior in unobserved situations. The result is an integrated Bayesian prediction framework that significantly outperforms existing IRL solutions and provides smooth policy estimates consistent with the expert's plan. Most notably, our framework naturally handles situations where the intentions of the agent change over time and classical IRL algorithms fail. In addition, due to its probabilistic nature, the model can be straightforwardly applied in active learning scenarios to guide the demonstration process of the expert.

A multitude of imaging and vision tasks have seen recently a major transformation by deep learning methods and in particular by the application of convolutional neural networks. These methods achieve impressive results, even for applications where it is not apparent that convolutions are suited to capture the underlying physics. In this work we develop a network architecture based on nonlinear diffusion processes, named DiffNet. By design, we obtain a nonlinear network architecture that is well suited for diffusion related problems in imaging. Furthermore, the performed updates are explicit, by which we obtain better interpretability and generalisability compared to classical convolutional neural network architectures. The performance of DiffNet tested on the inverse problem of nonlinear diffusion with the Perona-Malik filter on the STL-10 image dataset. We obtain competitive results to the established U-Net architecture, with a fraction of parameters and necessary training data.

With the advent of the Internet of Things (IoT), an increasing number of energy harvesting methods are being used to supplement or supplant battery based sensors. Energy harvesting sensors need to be configured according to the application, hardware, and environmental conditions to maximize their usefulness. As of today, the configuration of sensors is either manual or heuristics based, requiring valuable domain expertise. Reinforcement learning (RL) is a promising approach to automate configuration and efficiently scale IoT deployments, but it is not yet adopted in practice. We propose solutions to bridge this gap: reduce the training phase of RL so that nodes are operational within a short time after deployment and reduce the computational requirements to scale to large deployments. We focus on configuration of the sampling rate of indoor solar panel based energy harvesting sensors. We created a simulator based on 3 months of data collected from 5 sensor nodes subject to different lighting conditions. Our simulation results show that RL can effectively learn energy availability patterns and configure the sampling rate of the sensor nodes to maximize the sensing data while ensuring that energy storage is not depleted. The nodes can be operational within the first day by using our methods. We show that it is possible to reduce the number of RL policies by using a single policy for nodes that share similar lighting conditions.

Accurate information of inertial parameters is critical to motion planning and control of space robots. Before the launch, only a rudimentary estimate of the inertial parameters is available from experiments and computer-aided design (CAD) models. After the launch, on-orbit operations substantially alter the value of inertial parameters. In this work, we propose a new momentum model-based method for identifying the minimal parameters of a space robot while on orbit. Minimal parameters are combinations of the inertial parameters of the links and uniquely define the momentum and dynamic models. Consequently, they are sufficient for motion planning and control of both the satellite and robotic arms mounted on it. The key to the proposed framework is the unique formulation of momentum model in the linear form of minimal parameters. Further, to estimate the minimal parameters, we propose a novel joint trajectory planning and optimization technique based on direction combinations of joints' velocity. The efficacy of the identification framework is demonstrated on a 12 degrees-of-freedom, spatial, dual-arm space robot. The methodology is developed for tree-type space robots, requires just the pose and twist data, and scalable with increasing number of joints.

This paper introduces Adversarial Resilience Learning (ARL), a concept to model, train, and analyze artificial neural networks as representations of competitive agents in highly complex systems. In our examples, the agents normally take the roles of attackers or defenders that aim at worsening or improving-or keeping, respectively-defined performance indicators of the system. Our concept provides adaptive, repeatable, actor-based testing with a chance of detecting previously unknown attack vectors. We provide the constitutive nomenclature of ARL and, based on it, the description of experimental setups and results of a preliminary implementation of ARL in simulated power systems.

The energy output of photovoltaic (PV) power plants depends on the environment and thus fluctuates over time. As a result, PV power can cause instability in the power grid, in particular when increasingly used. Limiting the rate of change of the power output is a common way to mitigate these fluctuations, often with the help of large batteries. A reactive controller that uses these batteries to compensate ramps works in practice, but causes stress on the battery due to a high energy throughput. In this paper, we present a deep learning approach that uses images of the sky to compensate power fluctuations predictively and reduces battery stress. In particular, we show that the optimal control policy can be computed using information that is only available in hindsight. Based on this, we use imitation learning to train a neural network that approximates this hindsight-optimal policy, but uses only currently available sky images and sensor data. We evaluate our method on a large dataset of measurements and images from a real power plant and show that the trained policy reduces stress on the battery.

In this paper, we present a deep reinforcement learning method for quadcopter bypassing the obstacle on the flying path. In the past study, the algorithm only controls the forward direction about quadcopter. In this letter, we use two functions to control quadcopter. One is quadcopter navigating function. It is based on calculating coordination point and find the straight path to the goal. The other function is collision avoidance function. It is implemented by deep Q-network model. Both two function will output rotating degree, the agent will combine both output and turn direct. Besides, deep Q-network can also make quadcopter fly up and down to bypass the obstacle and arrive at the goal. Our experimental result shows that the collision rate is 14% after 500 flights. Based on this work, we will train more complex sense and transfer model to the real quadcopter.