Convolutional neural networks (CNNs) have achieved breakthrough performances in a wide range of applications including image classification, semantic segmentation, and object detection. Previous research on characterizing the generalization ability of neural networks mostly focuses on fully connected neural networks (FNNs), regarding CNNs as a special case of FNNs without taking into account the special structure of convolutional layers. In this work, we propose a tighter generalization bound for CNNs by exploiting the sparse and permutation structure of its weight matrices. As the generalization bound relies on the spectral norm of weight matrices, we further study spectral norms of three commonly used convolution operations including standard convolution, depthwise convolution, and pointwise convolution. Theoretical and experimental results both demonstrate that our bounds for CNNs are tighter than existing bounds.

Silas: High Performance, Explainable and V erifiable Machine Learning Hadrien Bride, Zh e H ou Griffith University, Nathan, Brisbane, Australia Jie Dong Dependable Intelligence Pty Ltd, Brisbane, Australia Jin Song Dong National University of Singapore, Singapore Ali Mirjalili Griffith University, Nathan, Brisbane, AustraliaAbstract This paper introduces a new classification tool named Silas, which is built to provide a more transparent and dependable data analytics service. A focus of Silas is on providing a formal foundation of decision trees in order to support logical analysis and verification of learned prediction models. This paper describes the distinct features of Silas: The Model Audit module formally verifies the prediction model against user specifications, the Enforcement Learning module trains prediction models that are guaranteed correct, the Model Insight and Prediction Insight modules reason about the prediction model and explain the decision-making of predictions. We also discuss implementation details ranging from programming paradigm to memory management that help achieve high-performance computation.1. Introduction Machine learning has enjoyed great success in many research areas and industries, including entertainment [1], self-driving cars [2], banking [3], medical diagnosis [4], shopping [5], and among many others. However, the wide adoption of machine learn-Preprint submitted to Elsevier October 4, 2019 arXiv:1910.01382v1 The ramifications of the black-box approach are multifold. First, it may lead to unexpected results that are only observable after the deployment of the algorithm. For instance, Amazon's Alexa offered porn to a child [6], a self-driving car had a deadly accident [7], etc. Some of these accidents result in lawsuits or even lost lives, the cost of which is immeasurable. Second, it prevents the adoption in some applications and industries where an explanation is mandatory or certain specifications must be satisfied. For example, in some countries, it is required by law to give a reason why a loan application is rejected. In recent years, eXplainable AI (XAI) has been gaining attention, and there is a surge of interest in studying how prediction models work and how to provide formal guarantees for the models. A common theme in this space is to use statistical methods to analyse prediction models.

Deep neural network image classifiers are reported to be susceptible to adversarial evasion attacks, which use carefully crafted images created to mislead a classifier. Recently, various kinds of adversarial attack methods have been proposed, most of which focus on adding small perturbations to input images. Despite the success of existing approaches, the way to generate realistic adversarial images with small perturbations remains a challenging problem. In this paper, we aim to address this problem by proposing a novel adversarial method, which generates adversarial examples by imposing not only perturbations but also spatial distortions on input images, including scaling, rotation, shear, and translation. As humans are less susceptible to small spatial distortions, the proposed approach can produce visually more realistic attacks with smaller perturbations, able to deceive classifiers without affecting human predictions. We learn our method by amortized techniques with neural networks and generate adversarial examples efficiently by a forward pass of the networks. Extensive experiments on attacking different types of non-robustified classifiers and robust classifiers with defence show that our method has state-of-the-art performance in comparison with advanced attack parallels.

Recent algorithms with state-of-the-art few-shot classification results start their procedure by computing data features output by a large pretrained model. In this paper we systematically investigate which models provide the best representations for a few-shot image classification task when pretrained on the Imagenet dataset. We test their representations when used as the starting point for different few-shot classification algorithms. We observe that models trained on a supervised classification task have higher performance than models trained in an unsupervised manner even when transferred to out-of-distribution datasets. Models trained with adversarial robustness transfer better, while having slightly lower accuracy than supervised models.

The CP 2002 paper entitled "Breaking Row and Column Symmetries in Matrix Models" by Flener et al. [6] describes some of the first work for identifying and analyzing row and column symmetry in mat rix models and for efficiently and effectively dealing with such symmetry u sing static symmetry-breaking ordering constraints. This commentary provides a retrospective on that work and highlights some of the subsequent work on the topic.

While AI techniques have found many successful applications in autonomous systems, many of them permit behaviours that are difficult to interpret and may lead to uncertain results. We follow the "verification as planning" paradigm and propose to use model checking techniques to solve planning and goal reasoning problems for autonomous systems. We give a new formulation of Goal Task Network (GTN) that is tailored for our model checking based framework. We then provide a systematic method that models GTNs in the model checker Process Analysis Toolkit (PAT). We present our planning and goal reasoning system as a framework called Goal Reasoning And Verification for Independent Trusted Autonomous Systems (GRAVITAS) and discuss how it helps provide trustworthy plans in an uncertain environment. Finally, we demonstrate the proposed ideas in an experiment that simulates a survey mission performed by the REMUS-100 autonomous underwater vehicle.

UPS has become the first drone delivery service to receive full approval from the Federal Aviation Administration. The company's program, called Flight Forward, is operated in partnership with Matternet, which provides drone logistics networking company in Mountain View, California. Previously, UPS's pilots were only allowed to fly the drones within line of sight, but the FAA approval means they'll be able to significantly expand their delivery range. 'This is history in the making, and we aren't done yet,' said David Abney, UPS chief executive officer in a statement. UPS's Flight Forward drone delivery program is the first to earn full approval by the FAA (pictured one of the drones they will use in the program) The program's currently deployed in Raleigh, North Carolina, where UPS's drones have made more than 1,000 flights carrying deliveries around the WakeMed Health & Hospitals campus.

Cyber Security Cooperative Research Centre (CSCRC), together with Data61, the innovation arm of the Commonwealth Scientific and Industrial Research Organisation (CSIRO), and cybersecurity startup Penten, have announced a joint research project that will focus on developing artificial intelligence (AI) enabled cybersecurity defence mechanisms. Under the arrangement announced at D61 Live on Wednesday, Penten will have access to Data61's AI research, which it will use to extend on its existing work to build AI-enabled technology such as "cyber traps" and "decoys". According to Penten CEO Matthew Wilson, using AI will help speed up the creation of cyber traps and make them more realistic. "Our solutions use artificial intelligence to learn the patterns of activity and content from surrounding computers and data. We then use this information to create realistic and believable mimics. This means we can deliver suitable content extremely efficiently, tailored to a customer environment and with minimal effort on the part of the defender," he said.

In the latest regulatory boost for expanded commercial drone services, the company also intends to gradually phase in routine night flights and heavier cargo limits--areas now generally off-limits to most operators. Under the Federal Aviation Administration's announcement Tuesday, the company's Flight Forward unit obtained an immediate green light to ship medical products and specimens in North Carolina across various hospital campuses. But the broad approval for an entire fleet of future drones and pilots on the ground--going beyond what the FAA approved previously--opens the door for many other types of longer-range applications spanning rural and suburban areas. The FAA approval doesn't apply to urban areas. Calling it a major step to enhance services for health-care customers and ultimately an array of other industries, the company said the FAA's approval "has no limits on the size or scope of operations."

A look at some clever uses of AI in travel and how it is already helping travel marketers overcome some of the biggest problems they're currently facing in the industry. Earlier this year, Sojern's State of the Industry: The 2019 Report on Travel Advertising, billed as the largest-ever survey of global travel marketers, revealed what industry insiders consider to be the greatest challenges for modern travel brands. Delivering personalised offers in real-time topped the list of challenges (46%) with ROI and profitability (45%), targeting travellers at specific points along the path to purchase (45%), keeping with the industry's fast-paced changes (45%) and using customer data effectively (44%) all closely followed. Artificial intelligence is already solving a lot of these and in this article, we take a look of some of these solutions. The generational shift from Babyboomers to Millennials has been particularly challenging, compounded by rapid advances in technology.