A couple of weeks ago at the Mobile World Congress event in Los Angeles, graphics processing unit market leader NVIDIA unveiled its EGX Edge Supercomputing platform. The product is designed for all edge applications including, but not limited to, artificial intelligence and internet of things. This was the first time NVIDIA has been part of a Mobile World Congress, and the announcement of the EGX certainly warranted its presence at the event. As is the case with most NVIDIA platforms, EGX is a reference design that other server manufacturers can use to roll out a validated design for edge computing use cases that include NVIDIA GPUs. At the time of announcement, Cisco, Fujitsu, Lenovo, HPE and others were confirmed partners.

Artificial intelligence is making waves in healthcare. More than 40 percent of healthcare executives consider it the technology that will have the greatest impact on their organizations within the next three years, Accenture reports. Some health systems are already using it to address a growing number of issues, from staff efficiencies to predicting patient outcomes that transform the delivery of care. Now, recipients of care are starting to leverage the functionality of AI as well. Consider Froedtert Health and the Medical College of Wisconsin Health Network, which is using Buoy -- an interactive digital tool that allows users to enter their symptoms and receive a personalized analysis and recommendations for care options in real time.

We consider distributed statistical optimization in one-shot setting, where there are $m$ machines each observing $n$ i.i.d. samples. Based on its observed samples, each machine then sends an $O(\log(mn))$-length message to a server, at which a parameter minimizing an expected loss is to be estimated. We propose an algorithm called Multi-Resolution Estimator (MRE) whose expected error is no larger than $\tilde{O}\big(m^{-{1}/{\max(d,2)}} n^{-1/2}\big)$, where $d$ is the dimension of the parameter space. This error bound meets existing lower bounds up to poly-logarithmic factors, and is thereby order optimal. The expected error of MRE, unlike existing algorithms, tends to zero as the number of machines ($m$) goes to infinity, even when the number of samples per machine ($n$) remains upper bounded by a constant. This property of the MRE algorithm makes it applicable in new machine learning paradigms where $m$ is much larger than $n$.

Unmanned Aerial Vehicles (UAVs), autonomously-guided aircraft, are widely used for tasks involving surveillance and reconnaissance. A version of the pursuit-evasion problems centered around UAVs and its variants has been extensively studied in recent years due to numerous breakthroughs in AI. We present an approach to UAV pursuit-evasion in a 2D aerial-engagement environment using reinforcement learning (RL), a machine learning paradigm concerned with goal-oriented algorithms. In this work, a UAV wielding the greedy shooter strategy engages with a UAV trained using deep Q-learning techniques. Simulated results show that the latter UAV wins every engagement in which the UAVs are suffciently separated during initialization. This approach highlights an exhaustive and robust application of reinforcement learning to pursuit-evasion that provides insight into effective strategies for UAV flight and interaction.

Mobile crowdsourcing has become easier thanks to the widespread of smartphones capable of seamlessly collecting and pushing the desired data to cloud services. However, the success of mobile crowdsourcing relies on balancing the supply and demand by first accurately forecasting spatially and temporally the supply-demand gap, and then providing efficient incentives to encourage participant movements to maintain the desired balance. In this paper, we propose Deep-Gap, a deep learning approach based on residual learning to predict the gap between mobile crowdsourced service supply and demand at a given time and space. The prediction can drive the incentive model to achieve a geographically balanced service coverage in order to avoid the case where some areas are over-supplied while other areas are under-supplied. This allows anticipating the supply-demand gap and redirecting crowdsourced service providers towards target areas. Deep-Gap relies on historical supply-demand time series data as well as available external data such as weather conditions and day type (e.g., weekday, weekend, holiday). First, we roll and encode the time series of supply-demand as images using the Gramian Angular Summation Field (GASF), Gramian Angular Difference Field (GADF) and the Recurrence Plot (REC). These images are then used to train deep Convolutional Neural Networks (CNN) to extract the low and high-level features and forecast the crowdsourced services gap. We conduct comprehensive comparative study by establishing two supply-demand gap forecasting scenarios: with and without external data. Compared to state-of-art approaches, Deep-Gap achieves the lowest forecasting errors in both scenarios.

Learning to solve complex goal-oriented tasks with sparse terminal-only rewards often requires an enormous number of samples. In such cases, using a set of expert trajectories could help to learn faster. However, Imitation Learning (IL) via supervised pre-training with these trajectories may not perform as well and generally requires additional finetuning with expert-in-the-loop. In this paper, we propose an approach which uses the expert trajectories and learns to decompose the complex main task into smaller sub-goals. We learn a function which partitions the state-space into sub-goals, which can then be used to design an extrinsic reward function. We follow a strategy where the agent first learns from the trajectories using IL and then switches to Reinforcement Learning (RL) using the identified sub-goals, to alleviate the errors in the IL step. To deal with states which are under-represented by the trajectory set, we also learn a function to modulate the sub-goal predictions. We show that our method is able to solve complex goal-oriented tasks, which other RL, IL or their combinations in literature are not able to solve.

Understanding urban dynamics, i.e., how the types and intensity of urban residents' activities in the city change along with time, is of urgent demand for building an efficient and livable city. Nonetheless, this is challenging due to the expanding urban population and the complicated spatial distribution of residents. In this paper, to reveal urban dynamics, we propose a novel system UrbanRhythm to reveal the urban dynamics hidden in human mobility data. UrbanRhythm addresses three questions: 1) What mobility feature should be used to present residents' high-dimensional activities in the city? 2) What are basic components of urban dynamics? 3) What are the long-term periodicity and short-term regularity of urban dynamics? In UrbanRhythm, we extract staying, leaving, arriving three attributes of mobility and use a image processing method Saak transform to calculate the mobility distribution feature. For the second question, several city states are identified by hierarchy clustering as the basic components of urban dynamics, such as sleeping states and working states. We further characterize the urban dynamics as the transform of city states along time axis. For the third question, we directly observe the long-term periodicity of urban dynamics from visualization. Then for the short-term regularity, we design a novel motif analysis method to discovery motifs as well as their hierarchy relationships. We evaluate our proposed system on two real-life datesets and validate the results according to App usage records. This study sheds light on urban dynamics hidden in human mobility and can further pave the way for more complicated mobility behavior modeling and deeper urban understanding.

Recent research shows that for training with $\ell_2$ loss, convolutional neural networks (CNNs) whose width (number of channels in convolutional layers) goes to infinity correspond to regression with respect to the CNN Gaussian Process kernel (CNN-GP) if only the last layer is trained, and correspond to regression with respect to the Convolutional Neural Tangent Kernel (CNTK) if all layers are trained. An exact algorithm to compute CNTK (Arora et al., 2019) yielded the finding that classification accuracy of CNTK on CIFAR-10 is within 6-7% of that of that of the corresponding CNN architecture (best figure being around 78%) which is interesting performance for a fixed kernel. Here we show how to significantly enhance the performance of these kernels using two ideas. (1) Modifying the kernel using a new operation called Local Average Pooling (LAP) which preserves efficient computability of the kernel and inherits the spirit of standard data augmentation using pixel shifts. Earlier papers were unable to incorporate naive data augmentation because of the quadratic training cost of kernel regression. This idea is inspired by Global Average Pooling (GAP), which we show for CNN-GP and CNTK is equivalent to full translation data augmentation. (2) Representing the input image using a pre-processing technique proposed by Coates et al. (2011), which uses a single convolutional layer composed of random image patches. On CIFAR-10, the resulting kernel, CNN-GP with LAP and horizontal flip data augmentation, achieves 89% accuracy, matching the performance of AlexNet (Krizhevsky et al., 2012). Note that this is the best such result we know of for a classifier that is not a trained neural network. Similar improvements are obtained for Fashion-MNIST.

In many applications of machine learning, the training and test set data come from different distributions, or domains. A number of domain generalization strategies have been introduced with the goal of achieving good performance on out-of-distribution data. In this paper, we propose an adversarial approach to the problem. We propose a process that enforces pair-wise domain invariance while training a feature extractor over a diverse set of domains. We show that this process ensures invariance to any distribution that can be expressed as a mixture of the training domains. Following this insight, we then introduce an adversarial approach in which pair-wise divergences are estimated and minimized. Experiments on two domain generalization benchmarks for object recognition (i.e., PACS and VLCS) show that the proposed method yields higher average accuracy on the target domains in comparison to previously introduced adversarial strategies, as well as recently proposed methods based on learning invariant representations.

Deep learning architectures (DLA) have shown impressive performance in computer vision, natural language processing and so on. Many DLA make use of cloud computing to achieve classification due to the high computation and memory requirements. Privacy and latency concerns resulting from cloud computing has inspired the deployment of DLA on embedded hardware accelerators. To achieve short time-to-market and have access to global experts, state-of-the-art techniques of DLA deployment on hardware accelerators are outsourced to untrusted third parties. This outsourcing raises security concerns as hardware Trojans can be inserted into the hardware design of the mapped DLA of the hardware accelerator. We argue that existing hardware Trojan attacks highlighted in literature have no qualitative means how definite they are of the triggering of the Trojan. Also, most inserted Trojans show a obvious spike in the number of hardware resources utilized on the accelerator at the time of triggering the Trojan or when the payload is active. In this paper, we propose a hardware Trojan attack called Input Interception Attack (IIA). In this attack we make use of the statistical properties of layer-by-layer output to make sure that asides from being stealthy, our IIA is able to trigger with some measure of definiteness. This IIA attack is tested on DLA used to classify MNIST and Cifar-10 data sets. The attacked design utilizes approximately up to 2% more LUTs respectively compared to the un-compromised designs. This paper also discusses potential defensive mechanisms that could be used to combat such hardware Trojans based attack in hardware accelerators for DLA.