-- This work addresses the problem of semantic scene understanding under foggy road conditions. Although marked progress has been made in semantic scene understanding over the recent years, it is mainly concentrated on clear weather outdoor scenes. Extending semantic segmentation methods to adverse weather conditions like fog is crucially important for outdoor applications such as self-driving cars. In this paper, we propose a novel method, which uses purely synthetic data to improve the performance on unseen real-world foggy scenes captured in the streets of Zurich and its surroundings. Our results highlight the potential and power of photo-realistic synthetic images for training and especially fine-tuning deep neural nets. Our contributions are threefold, 1) we created a purely synthetic, high-quality foggy dataset of 25,000 unique outdoor scenes, that we call Foggy Synscapes and plan to release publicly 2) we show that with this data we outperform previous approaches on real-world foggy test data 3) we show that a combination of our data and previously used data can even further improve the performance on real-world foggy data. The last years have seen tremendous progress in tasks relevant to autonomous driving [1].

Evidence-based reasoning is at the core of ma ny problem - solving and decision-making tasks in a wide variety of domains. Generalizing from the research and development of cognitive agents in several such domains, this paper presents progress toward a computational theory for the development of instructable cognitive agents for evide nce-based reasoning tasks. The paper also illustrates the application of this theory to the development of four prototype cognitive agents in domains that are critical to the government and the public sector . Two agents function as cognitive assistants, one in intelligence analysis, and the other in science education . The other two agents operate autonomously, one in cybersecurity and the other in intelligence, surveillance, and reconnaissance. The paper concludes with the directions of future research on th e proposed computational theory.

Recent policy optimization approaches have achieved substantial empirical success by constructing surrogate optimization objectives. The Approximate Policy Iteration objective (Schulman et al., 2015a; Kakade and Langford, 2002) has become a standard optimization target for reinforcement learning problems. Using this objective in practice requires an estimator of the advantage function. Policy optimization methods such as those proposed in Schulman et al. (2015b) estimate the advantages using a parametric critic. In this work we establish conditions under which the parametric approximation of the critic does not introduce bias to the updates of surrogate objective. These results hold for a general class of parametric policies, including deep neural networks. We obtain a result analogous to the compatible features derived for the original Policy Gradient Theorem (Sutton et al., 1999). As a result, we also identify a previously unknown bias that current state-of-the-art policy optimization algorithms (Schulman et al., 2015a, 2017) have introduced by not employing these compatible features.

Recent policy optimization approaches (Schulman et al., 2015a, 2017) have achieved substantial empirical successes by constructing new proxy optimization objectives. These proxy objectives allow stable and low variance policy learning, but require small policy updates to ensure that the proxy objective remains an accurate approximation of the target policy value. In this paper we derive an alternative objective that obtains the value of the target policy by applying importance sampling. This objective can be directly estimated from samples, as it takes an expectation over trajectories generated by the current policy. However, the basic importance sampled objective is not suitable for policy optimization, as it incurs unacceptable variance. We therefore introduce an approximation that allows us to directly trade-off the bias of approximation with the variance in policy updates. We show that our approximation unifies the proxy optimization approaches with the importance sampling objective and allows us to interpolate between them. We then provide a theoretical analysis of the method that directly quantifies the error term due to the approximation. Finally, we obtain a practical algorithm by optimizing the introduced objective with proximal policy optimization techniques (Schulman etal., 2017). We empirically demonstrate that the result-ing algorithm yields superior performance on continuous control benchmarks

The next frontier in solar system exploration will be missions targeting extreme and rugged environments such as caves, canyons, cliffs and crater rims of the Moon, Mars and icy moons. These environments are time capsules into early formation of the solar system and will provide vital clues of how our early solar system gave way to the current planets and moons. These sites will also provide vital clues to the past and present habitability of these environments. Current landers and rovers are unable to access these areas of high interest due to limitations in precision landing techniques, need for large and sophisticated science instruments and a mission assurance and operations culture where risks are minimized at all costs. Our past work has shown the advantages of using multiple spherical hopping robots called SphereX for exploring these extreme environments. Our previous work was based on performing exploration with a human-designed baseline design of a SphereX robot. However, the design of SphereX is a complex task that involves a large number of design variables and multiple engineering disciplines. In this work we propose to use Automated Multidisciplinary Design and Control Optimization (AMDCO) techniques to find near optimal design solutions in terms of mass, volume, power, and control for SphereX for different mission scenarios.

Machine learning models, especially neural networks (NNs), have achieved outstanding performance on diverse and complex applications. However, recent work has found that they are vulnerable to Trojan attacks where an adversary trains a corrupted model with poisoned data or directly manipulates its parameters in a stealthy way. Such Trojaned models can obtain good performance on normal data during test time while predicting incorrectly on the adversarially manipulated data samples. This paper aims to develop ways to detect Trojaned models. We mainly explore the idea of meta neural analysis, a technique involving training a meta NN model that can be used to predict whether or not a target NN model has certain properties. We develop a novel pipeline Meta Neural Trojaned model Detection (MNTD) system to predict if a given NN is Trojaned via meta neural analysis on a set of trained shadow models. We propose two ways to train the meta-classifier without knowing the Trojan attacker's strategies. The first one, one-class learning, will fit a novel detection meta-classifier using only benign neural networks. The second one, called jumbo learning, will approximate a general distribution of Trojaned models and sample a "jumbo" set of Trojaned models to train the meta-classifier and evaluate on the unseen Trojan strategies. Extensive experiments demonstrate the effectiveness of MNTD in detecting different Trojan attacks in diverse areas such as vision, speech, tabular data, and natural language processing. We show that MNTD reaches an average of 97% detection AUC (Area Under the ROC Curve) score and outperforms existing approaches. Furthermore, we design and evaluate MNTD system to defend against strong adaptive attackers who have exactly the knowledge of the detection, which demonstrates the robustness of MNTD.

Modern deep learning methods provide an effective means to learn good representations. However, is a good representation itself sufficient for efficient reinforcement learning? This question is largely unexplored, and the extant body of literature mainly focuses on conditions which permit efficient reinforcement learning with little understanding of what are necessary conditions for efficient reinforcement learning. This work provides strong negative results for reinforcement learning methods with function approximation for which a good representation (feature extractor) is known to the agent, focusing on natural representational conditions relevant to value-based learning and policy-based learning. For value-based learning, we show that even if the agent has a highly accurate linear representation, the agent still needs to sample exponentially many trajectories in order to find a near-optimal policy. For policy-based learning, we show even if the agent's linear representation is capable of perfectly representing the optimal policy, the agent still needs to sample exponentially many trajectories in order to find a near-optimal policy. These lower bounds highlight the fact that having a good (value-based or policy-based) representation in and of itself is insufficient for efficient reinforcement learning. In particular, these results provide new insights into why the existing provably efficient reinforcement learning methods rely on further assumptions, which are often model-based in nature. Additionally, our lower bounds imply exponential separations in the sample complexity between 1) value-based learning with perfect representation and value-based learning with a good-but-not-perfect representation, 2) value-based learning and policy-based learning, 3) policy-based learning and supervised learning and 4) reinforcement learning and imitation learning.

Testing two potentially multivariate variables for statistical dependence on the basis finite samples is a fundamental statistical challenge. Here we explore a family of tests that adapt to the complexity of the relationship between the variables, promising robust power across scenarios. Building on the distance correlation, we introduce a family of adaptive independence criteria based on nonlinear monotonic transformations of distances. We show that these criteria, like the distance correlation and RKHS-based criteria, provide dependence indicators. We propose a class of adaptive (multi-threshold) test statistics, which form the basis for permutation tests. These tests empirically outperform some of the established tests in average and worst-case statistical sensitivity across a range of univariate and multivariate relationships and might deserve further exploration.

Blizzard Entertainment has banned a professional Hearthstone player who expressed support for protestors in Hong Kong during a live broadcast following the recent Asia-Pacific Grandmasters tournament in which the top pro players from the region participate -- and rescinded the money he won in the competition. Blizzard Entertainment, a U.S.-based video game developer that's a part of the entertainment company Activision Blizzard, is the publisher behind the digital collectible card game Hearthstone. During a post-game interview Sunday on the official Hearthstone Taiwan livestream, the player, Ng "Blitzchung" Wai Chung, pulled down a pro-democracy Hong Kong-style mask and shouted, "Liberate Hong Kong. Inven Global, a website that covers esports and gaming news, reports that Blitzchung shouted the phrase in Chinese. Blitzchung is from Hong Kong, according to Inven Global. A clip of the interview can be seen here. In response, Blizzard, a U.S.-based video game developer, banned Blitzchung from competing in Hearthstone tournaments for a year, starting on Oct. 5. The company said Blitzchung has been removed from the Grandmasters roster, and will not receive any prize money he earned during the Grandmasters season 2 tournament. According to a statement from Blizzard, Blitzchung violated a competition rule that bars players from doing anything that "brings you into public disrepute, offends a portion or group of the public, or otherwise damages Blizzard image." Blitzchung lost $10,000 in prize earnings, Bloomberg reports. In a statement to Inven Global, Blitzchung said he viewed his comments as a continuation of his participation in the protests. "As you know, there are serious protests in my country now.

Editor's note: This is an excerpt from the full report. You can read the full survey report here. The survey was conducted on LinkedIn in April 2019 as a part of the University thesis prepared by A.Disbudak. The survey sought to evaluate the relevance of Machine Learning in operations today, assess the current state of Machine Learning adoption and to identify tools used for Machine Learning. The 140 qualified respondents represented a variety of company sizes from very small (one-person startups) to very large (multinationals with more than 10,000 employees).