The widescale deployment of Autonomous Vehicles (AV) appears to be imminent despite many safety challenges that are yet to be resolved. It is well-known that there are no universally agreed Verification and Validation (VV) methodologies guarantee absolute safety, which is crucial for the acceptance of this technology. The uncertainties in the behaviour of the traffic participants and the dynamic world cause stochastic reactions in advanced autonomous systems. The addition of ML algorithms and probabilistic techniques adds significant complexity to the process for real-world testing when compared to traditional methods. Most research in this area focuses on generating challenging concrete scenarios or test cases to evaluate the system performance by looking at the frequency distribution of extracted parameters as collected from the real-world data. These approaches generally employ Monte-Carlo simulation and importance sampling to generate critical cases. This paper presents an efficient falsification method to evaluate the System Under Test. The approach is based on a parameter optimisation problem to search for challenging scenarios. The optimisation process aims at finding the challenging case that has maximum return. The method applies policy-gradient reinforcement learning algorithm to enable the learning. The riskiness of the scenario is measured by the well established RSS safety metric, euclidean distance, and instance of a collision. We demonstrate that by using the proposed method, we can more efficiently search for challenging scenarios which could cause the system to fail in order to satisfy the safety requirements.

To reduce doctors' workload, deep-learning-based automatic medical report generation has recently attracted more and more research efforts, where attention mechanisms and reinforcement learning are integrated with the classic encoder-decoder architecture to enhance the performance of deep models. However, these state-of-the-art solutions mainly suffer from two shortcomings: (i) their attention mechanisms cannot utilize high-order feature interactions, and (ii) due to the use of TF-IDF-based reward functions, these methods are fragile with generating repeated terms. Therefore, in this work, we propose a reinforced medical report generation solution with x-linear attention and repetition penalty mechanisms (ReMRG-XR) to overcome these problems. Specifically, x-linear attention modules are used to explore high-order feature interactions and achieve multi-modal reasoning, while repetition penalty is used to apply penalties to repeated terms during the model's training process. Extensive experimental studies have been conducted on two public datasets, and the results show that ReMRG-XR greatly outperforms the state-of-the-art baselines in terms of all metrics.

This paper presents the 'hyper-sinh', a variation of the m-arcsinh activation function suitable for Deep Learning (DL)-based algorithms for supervised learning, such as Convolutional Neural Networks (CNN). hyper-sinh, developed in the open source Python libraries TensorFlow and Keras, is thus described and validated as an accurate and reliable activation function for both shallow and deep neural networks. Improvements in accuracy and reliability in image and text classification tasks on five (N = 5) benchmark data sets available from Keras are discussed. Experimental results demonstrate the overall competitive classification performance of both shallow and deep neural networks, obtained via this novel function. This function is evaluated with respect to gold standard activation functions, demonstrating its overall competitive accuracy and reliability for both image and text classification.

This work proposes the continuous conditional generative adversarial network (CcGAN), the first generative model for image generation conditional on continuous, scalar conditions (termed regression labels). Existing conditional GANs (cGANs) are mainly designed for categorical conditions (e.g., class labels); conditioning on regression labels is mathematically distinct and raises two fundamental problems: (P1) Since there may be very few (even zero) real images for some regression labels, minimizing existing empirical versions of cGAN losses (a.k.a. empirical cGAN losses) often fails in practice; (P2) Since regression labels are scalar and infinitely many, conventional label input methods are not applicable. The proposed CcGAN solves the above problems, respectively, by (S1) reformulating existing empirical cGAN losses to be appropriate for the continuous scenario; and (S2) proposing a naive label input (NLI) method and an improved label input (ILI) method to incorporate regression labels into the generator and the discriminator. The reformulation in (S1) leads to two novel empirical discriminator losses, termed the hard vicinal discriminator loss (HVDL) and the soft vicinal discriminator loss (SVDL) respectively, and a novel empirical generator loss. The error bounds of a discriminator trained with HVDL and SVDL are derived under mild assumptions in this work. Two new benchmark datasets (RC-49 and Cell-200) and a novel evaluation metric (Sliding Fr\'echet Inception Distance) are also proposed for this continuous scenario. Our experiments on the Circular 2-D Gaussians, RC-49, UTKFace, Cell-200, and Steering Angle datasets show that CcGAN can generate diverse, high-quality samples from the image distribution conditional on a given regression label. Moreover, in these experiments, CcGAN substantially outperforms cGAN both visually and quantitatively.

The Listening Post focuses on women in the national security space. This new column offers a collection of experienced national security insights, interviews, and profiles of women who are ushering in the new era of national security. Lauren Zabierek is Executive Director of the Cyber Project at Harvard Kennedy School's Belfer Center for Science and International Affairs. OPINION -- Emerging technologies such as Artificial Intelligence (AI), 5G telecommunications, and Quantum Computing hold great promise for the global good–from disease detection and treatment development to greater internet connectivity and possibilities we haven't even imagined yet. However, adversarial countries like Russia and China exploit technology to further their worldview to the detriment of the United States and its allies.

Australia's artificial intelligence (AI) community has rallied to a call from Defence and the Office of National Intelligence (ONI) for solutions to key Defence and security challenges. The call was part of the'Artificial Intelligence for Decision Making' (AIDM) initiative, aimed at growing Australia's AI capability and fostering a national community focussed on developing innovative AI solutions for Defence and national security. More than 200 proposals were received. Dr Tim McKay of the Department of Defence said the response was overwhelming and demonstrated the depth and breadth of AI expertise across Australia. "The quality of the submissions was excellent; far above what we expected," he said.

This will be a journey into predicting whether or not observations, made by high powered telescopes on Earth and potentially deep space probes in the future, are pulsars. Before we jump into the machine learning model I have developed to help identify pulsars, let's talk a bit about what pulsars, or'pulsar stars', actually are since they aren't pulsating and actually aren't technically stars (anymore). Consider, for the sake of explanation, that stars have a life. If they are less massive, between 7 and 25 solar masses (7–25 times the mass of our sun) or maybe a bit larger if they are especially metal-rich, they then become neutron stars, a super-dense mass only around 10 kilometers in radius but so dense that a teaspoon full of their mass would be as heavy as Mt. Everest if placed on Earth.

Reprinted with permission from Quanta Magazine's Abstractions blog. Our sense of time may be the scaffolding for all of our experience and behavior, but it is an unsteady and subjective one, expanding and contracting like an accordion. Emotions, music, events in our surroundings and shifts in our attention all have the power to speed time up for us or slow it down. When presented with images on a screen, we perceive angry faces as lasting longer than neutral ones, spiders as lasting longer than butterflies, and the color red as lasting longer than blue. The watched pot never boils, and time flies when we're having fun.

Efficient gradient computation of the Jacobian determinant term is a core problem of the normalizing flow framework. Thus, most proposed flow models either restrict to a function class with easy evaluation of the Jacobian determinant, or an efficient estimator thereof. However, these restrictions limit the performance of such density models, frequently requiring significant depth to reach desired performance levels. In this work, we propose Self Normalizing Flows, a flexible framework for training normalizing flows by replacing expensive terms in the gradient by learned approximate inverses at each layer. This reduces the computational complexity of each layer's exact update from $\mathcal{O}(D^3)$ to $\mathcal{O}(D^2)$, allowing for the training of flow architectures which were otherwise computationally infeasible, while also providing efficient sampling. We show experimentally that such models are remarkably stable and optimize to similar data likelihood values as their exact gradient counterparts, while surpassing the performance of their functionally constrained counterparts.

Facebook says it's using AI to prioritize potentially problematic posts for human moderators to review as it works to more quickly remove content that violates its community guidelines. The social media giant previously leveraged machine learning models to proactively take down low-priority content and left high-priority content reported by users to human reviewers. But Facebook claims it now combines content identified by users and models into a single collection before filtering, ranking, and deduplicating it and handing it off to thousands of moderators, many of whom are contract employees. Facebook's continued investment in moderation comes as reports suggest the company is failing to stem the spread of misinformation, disinformation, and hate speech on its platform. Reuters recently found over three dozen pages and groups that featured discriminatory language about Rohingya refugees and undocumented migrants.