DNN-based video analytics have empowered many new applications (e.g., automated retail). Meanwhile, the proliferation of fog devices provides developers with more design options to improve performance and save cost. To the best of our knowledge, this paper presents the first serverless system that takes full advantage of the client-fog-cloud synergy to better serve the DNN-based video analytics. Specifically, the system aims to achieve two goals: 1) Provide the optimal analytics results under the constraints of lower bandwidth usage and shorter round-trip time (RTT) by judiciously managing the computational and bandwidth resources deployed in the client, fog, and cloud environment. 2) Free developers from tedious administration and operation tasks, including DNN deployment, cloud and fog's resource management. To this end, we implement a holistic cloud-fog system referred to as VPaaS (Video-Platform-as-a-Service). VPaaS adopts serverless computing to enable developers to build a video analytics pipeline by simply programming a set of functions (e.g., model inference), which are then orchestrated to process videos through carefully designed modules. To save bandwidth and reduce RTT, VPaaS provides a new video streaming protocol that only sends low-quality video to the cloud. The state-of-the-art (SOTA) DNNs deployed at the cloud can identify regions of video frames that need further processing at the fog ends. At the fog ends, misidentified labels in these regions can be corrected using a light-weight DNN model. To address the data drift issues, we incorporate limited human feedback into the system to verify the results and adopt incremental learning to improve our system continuously. The evaluation demonstrates that VPaaS is superior to several SOTA systems: it maintains high accuracy while reducing bandwidth usage by up to 21%, RTT by up to 62.5%, and cloud monetary cost by up to 50%.

There has been an increasing interest in harnessing deep learning to tackle combinatorial optimization (CO) problems in recent years. Typical CO deep learning approaches leverage the problem structure in the model architecture. Nevertheless, the model selection is still mainly based on the conventional machine learning setting. Due to the discrete nature of CO problems, a single model is unlikely to learn the problem entirely. We introduce ZTop, which stands for Zero Training Overhead Portfolio, a simple yet effective model selection and ensemble mechanism for learning to solve combinatorial problems. ZTop is inspired by algorithm portfolios, a popular CO ensembling strategy, particularly restart portfolios, which periodically restart a randomized CO algorithm, de facto exploring the search space with different heuristics. We have observed that well-trained models acquired in the same training trajectory, with similar top validation performance, perform well on very different validation instances. Following this observation, ZTop ensembles a set of well-trained models, each providing a unique heuristic with zero training overhead, and applies them, sequentially or in parallel, to solve the test instances. We show how ZTopping, i.e., using a ZTop ensemble strategy with a given deep learning approach, can significantly improve the performance of the current state-of-the-art deep learning approaches on three prototypical CO domains, the hardest unique-solution Sudoku instances, challenging routing problems, and the graph maximum cut problem, as well as on multi-label classification, a machine learning task with a large combinatorial label space.

We construct audio adversarial examples on automatic Speech-To-Text systems . Given any audio waveform, we produce an another by overlaying an audio vocal mask generated from the original audio. We apply our audio adversarial attack to five SOTA STT systems: DeepSpeech, Julius, Kaldi, wav2letter@anywhere and CMUSphinx. In addition, we engaged human annotators to transcribe the adversarial audio. Our experiments show that these adversarial examples fool State-Of-The-Art Speech-To-Text systems, yet humans are able to consistently pick out the speech. The feasibility of this attack introduces a new domain to study machine and human perception of speech.

We investigate and analyze principles of typical motion planning algorithms. These include traditional planning algorithms, supervised learning, optimal value reinforcement learning, policy gradient reinforcement learning. Traditional planning algorithms we investigated include graph search algorithms, sampling-based algorithms, and interpolating curve algorithms. Supervised learning algorithms include MSVM, LSTM, MCTS and CNN. Optimal value reinforcement learning algorithms include Q learning, DQN, double DQN, dueling DQN. Policy gradient algorithms include policy gradient method, actor-critic algorithm, A3C, A2C, DPG, DDPG, TRPO and PPO. New general criteria are also introduced to evaluate performance and application of motion planning algorithms by analytical comparisons. Convergence speed and stability of optimal value and policy gradient algorithms are specially analyzed. Future directions are presented analytically according to principles and analytical comparisons of motion planning algorithms. This paper provides researchers with a clear and comprehensive understanding about advantages, disadvantages, relationships, and future of motion planning algorithms in robotics, and paves ways for better motion planning algorithms.

Massive MIMO communication systems have a huge potential both in terms of data rate and energy efficiency, although channel estimation becomes challenging for a large number of antennas. Using a physical model allows to ease the problem by injecting a priori information based on the physics of propagation. However, such a model rests on simplifying assumptions and requires to know precisely the configuration of the system, which is unrealistic in practice. In this paper we present mpNet, an unfolded neural network specifically designed for massive MIMO channel estimation. It is trained online in an unsupervised way. Moreover, mpNet is computationally efficient and automatically adapts its depth to the SNR. The method we propose adds flexibility to physical channel models by allowing a base station to automatically correct its channel estimation algorithm based on incoming data, without the need for a separate offline training phase. It is applied to realistic millimeter wave channels and shows great performance, achieving a channel estimation error almost as low as one would get with a perfectly calibrated system. It also allows incident detection and automatic correction, making the base station resilient and able to automatically adapt to changes in its environment.

When surgeons remove cancer, one of the first questions is, "Did they get it all?" Researchers from Rice University and the University of Texas MD Anderson Cancer Center have created a new microscope that can quickly and inexpensively image large tissue sections, potentially during surgery, to find the answer. The microscope can rapidly image relatively thick pieces of tissue with cellular resolution, and could allow surgeons to inspect the margins of tumors within minutes of their removal. It was created by engineers and applied physicists at Rice and is described in a study published in the Proceedings of the National Academy of Sciences. "The main goal of the surgery is to remove all the cancer cells, but the only way to know if you got everything is to look at the tumor under a microscope," said Rice's Mary Jin, a Ph.D. student in electrical and computer engineering and co-lead author of the study.

The Internet has been replete with news headlines about GPT-3 writing articles, Google's Neural Network creating eerie artwork, artificial intelligence (AI) models creating music and what not. While these may seems quite intriguing for a tech enthusiast, for an average person, it may be overwhelming. Not only he shall be worried about ever-increasing capabilities of artificial intelligence, it also births fear to AI and robots dominating humans – as portrayed in dystopian movies. Hence, all these milestones achieved by AI begs the question – Will artificial intelligence be conscious someday? Artificial intelligence tries to solve real-world problems by simulating human brain intelligence to perform the assigned task. Generally, it can be categorized into two distinct types: Weak AI and Strong AI.

Chapter 5 of this free 15 chapter AI handbook provides an overview of natural language processing.

In this paper, we investigate the problem of the inverse reinforcement learning (IRL), especially the beyond-demonstrator (BD) IRL. The BD-IRL aims to not only imitate the expert policy but also extrapolate BD policy based on finite demonstrations of the expert. Currently, most of the BD-IRL algorithms are two-stage, which first infer a reward function then learn the policy via reinforcement learning (RL). Because of the two separate procedures, the two-stage algorithms have high computation complexity and lack robustness. To overcome these flaw, we propose a BD-IRL framework entitled hybrid adversarial inverse reinforcement learning (HAIRL), which successfully integrates the imitation and exploration into one procedure. The simulation results show that the HAIRL is more efficient and robust when compared with other similar state-of-the-art (SOTA) algorithms.

This paper introduces a new loss function induced by the Fourier-based Metric. This metric is equivalent to the Wasserstein distance but is computed very efficiently using the Fast Fourier Transform algorithm. We prove that the Fourier loss function is twice differentiable, and we provide the explicit formula for both its gradient and its Hessian matrix. More importantly, we show that minimising the Fourier loss function is equivalent to maximising the likelihood of the data under a Gaussian noise in the space of frequencies. We apply our loss function to a multi-class classification task using MNIST, Fashion-MNIST, and CIFAR10 datasets. The computational results show that, while its accuracy is competitive with other state-of-the-art loss functions, the Fourier loss function is significantly more robust to noisy data.