Cartesian Genetic Programming (CGP) has previously shown capabilities in image processing tasks by evolving programs with a function set specialized for computer vision. A similar approach can be applied to Atari playing. Programs are evolved using mixed type CGP with a function set suited for matrix operations, including image processing, but allowing for controller behavior to emerge. While the programs are relatively small, many controllers are competitive with state of the art methods for the Atari benchmark set and require less training time. By evaluating the programs of the best evolved individuals, simple but effective strategies can be found.

Random weights in convolutional neural networks have shown promising results in previous studies yet remain below par compared to trained networks on image benchmarks. We explore depthwise convolutional neural networks with thousands of random filters in each layer, the sign activation function in between layers, and training performed only at the last layer with a linear support vector machine. We show that our network attains higher accuracies than previous random networks and is comparable to trained large networks on large images from the STL10 and ImageNet benchmarks. Since our network lacks a gradient due to the sign activation it is not possible to produce gradient-based adversarial examples targeting it. We show that our network is also less affected by gradient based adversarial examples produced from state of the art networks that considerably hamper their performance. As a possible explanation for our network's accuracy with random weights we show that the the margin of the linear support vector machine is larger on our final representation compared to the original dataset and increases with the number of random filters. Our network is simple and fast to train and predict, attains high classification accuracy particularly on large images, is hard to attack with adversarial examples, and is less affected by gradient based adversarial examples compared to state of the art networks.

The lack of comprehensive, high-quality health data in developing nations creates a roadblock for combating the impacts of disease. One key challenge is understanding the health information needs of people in these nations. Without understanding people's everyday needs, concerns, and misconceptions, health organizations and policymakers lack the ability to effectively target education and programming efforts. In this paper, we propose a bottom-up approach that uses search data from individuals to uncover and gain insight into health information needs in Africa. We analyze Bing searches related to HIV/AIDS, malaria, and tuberculosis from all 54 African nations. For each disease, we automatically derive a set of common search themes or topics, revealing a wide-spread interest in various types of information, including disease symptoms, drugs, concerns about breastfeeding, as well as stigma, beliefs in natural cures, and other topics that may be hard to uncover through traditional surveys. We expose the different patterns that emerge in health information needs by demographic groups (age and sex) and country. We also uncover discrepancies in the quality of content returned by search engines to users by topic. Combined, our results suggest that search data can help illuminate health information needs in Africa and inform discussions on health policy and targeted education efforts both on- and offline.

DBSCAN may not be sufficient when the input data type is heterogeneous in terms of textual description. When we aim to discover clusters of geo-tagged records relevant to a particular point-of-interest (POI) on social media, examining only one type of input data (e.g., the tweets relevant to a POI) may draw an incomplete picture of clusters due to noisy regions. To overcome this problem, we introduce DBSTexC, a newly defined density-based clustering algorithm using spatio--textual information. We first characterize POI-relevant and POI-irrelevant tweets as the texts that include and do not include a POI name or its semantically coherent variations, respectively. By leveraging the proportion of POI-relevant and POI-irrelevant tweets, the proposed algorithm demonstrates much higher clustering performance than the DBSCAN case in terms of $\mathcal{F}_1$ score and its variants. While DBSTexC performs exactly as DBSCAN with the textually homogeneous inputs, it far outperforms DBSCAN with the textually heterogeneous inputs. Furthermore, to further improve the clustering quality by fully capturing the geographic distribution of tweets, we present fuzzy DBSTexC (F-DBSTexC), an extension of DBSTexC, which incorporates the notion of fuzzy clustering into the DBSTexC. We then demonstrate the robustness of F-DBSTexC via intensive experiments. The computational complexity of our algorithms is also analytically and numerically shown.

This paper proposes Self-Imitation Learning (SIL), a simple off-policy actor-critic algorithm that learns to reproduce the agent's past good decisions. This algorithm is designed to verify our hypothesis that exploiting past good experiences can indirectly drive deep exploration. Our empirical results show that SIL significantly improves advantage actor-critic (A2C) on several hard exploration Atari games and is competitive to the state-of-the-art count-based exploration methods. We also show that SIL improves proximal policy optimization (PPO) on MuJoCo tasks.

We're in a golden age for hollow corporate statements sold as high-minded ethical treatises. Last year, in the thick of its fake news scandal, Facebook released a 5,000-word document outlining, well, I'm still not sure exactly. The letter attempted to pull the company out of its public opinion black hole by posing probing questions, including the head-scratcher: "How do we help people build supportive communities that strengthen traditional institutions in a world where membership in these institutions is declining?" The answers were generally of the "build more Facebook" variety. It was a masterstroke in corporate pablum, though not so masterful that it saved the company from the onslaught of bad press.

HARTFORD, CONNECTICUT – The developer of a school-shooting video game is vowing to continue selling it online as parents of slain children and other mass shooting victims work to get the game wiped off the internet. The "Active Shooter" game was created by Anton Makarevskiy, a 21-year-old developer from Moscow, and is being marketed by his entity Acid Software. Acid said in a Twitter posting Tuesday that it will not be censored and cited free expression rights. The game is branded as a "SWAT simulator" that lets players choose between being an active shooter terrorizing a school or the SWAT team responding to the shooting. Players can choose a gun, grenade or knife, and civilian and police death totals are shown on the screen.

Statisticians at German technical university Technische Universitat Dortmund built a model that used machine learning to predict Spain will win the 2018 World Cup. The prediction is based on 100,000 simulations of the tournament. Spain was followed by Germany, Brazil, France and Belgium in terms of their chances of winning. And it should be a good tournament because Spain, with a 17.8 percent chance of winning, is only slightly ahead of Germany at 17.1 percent. Brazil follows with 12.3 percent, and then it's France (11.2 percent) and Belgium (10.4 percent).

Are you prepared for the dawn of AI? Is automation going to displace workers? We examined all this and more this week in the Careers section. It's Automation Week here at Siliconrepublic.com, a week in which we put a spotlight on some of the most amazing developments in artificial intelligence (AI) and automation technology. It's difficult to have uncomplicated feelings about the advent of the AI revolution. You can't just simply marvel at the advances of human scientific endeavour and move on, because the larger implications of these kinds of technologies could drastically alter how we live.

Recruiters have a bias problem. A 2017 meta study from Northwestern, Harvard, and the Institute of Social Research in Norway found that hiring prejudice against black candidates hasn't changed in the last 25 years, and that Latinos have only seen a "moderate" drop. It is not just races and ethnicities that employers are discriminating against -- according to a recent paper authored by Harvard and Stanford researchers, women earn 78 cents on the dollar compared to men and are less likely to advance to the top of their fields. The solution, Caitlin MacGregor says, is artificial intelligence. She's the CEO and founder of Waterloo, Ontario-based Plum.io, a hiring platform that emphasizes "raw talent," as opposed to skills and knowledge.