Marine buoys aid in the battle against Illegal, Unreported and Unregulated (IUU) fishing by detecting fishing vessels in their vicinity. Marine buoys, however, may be disrupted by natural causes and buoy vandalism. To minimize the effects of buoy disruption on a buoy network, we propose a more robust buoy placement using dropout k-means and dropout k-median. We apply dropout k-means and dropout k-median to determine locations for deploying marine buoys in the Gabonese waters near West Africa. We simulated the passage of ships using historical Automatic Identification System (AIS) data, then compared the ship detection probability of dropout k-means to classic k-means and dropout k-median to classic k-median, taking into account that the current sensor detection radius is 10km. With 5 buoys, the buoy arrangement computed by classic k-means, dropout k-means, classic k-median and dropout k-median have ship detection probabilities of 38%, 45%, 48% and 52%.

We review recent works [1, 2, 3] on analyzing the dynamics of gradient-based algorithms in a prototypical statistical inference problem. Using methods and insights from the physics of glassy systems, these works showed how to understand quantitatively and qualitatively the performance of gradient-based algorithms. Here we review the key results and their interpretation in nontechnical terms accessible to a wide audience of physicists in the context of related works. PACS numbers: 00.00, 20.00, 42.10 Keywords: analysis of algorithms, statistical inference, spin glasses, machine learning.

Personal use of this material is permitted. Abstract --Pre-training a deep neural network on the ImageNet dataset is a common practice for training deep learning models, and generally yields improved performance and faster training times. The technique of pre-training on one task and then retraining on a new one is called transfer learning. We perform three sets of experiments with varying levels of similarity between source and target tasks to investigate the behaviour of different types of knowledge transfer . We transfer both parameters and features and analyse their behaviour . Our results demonstrate that no significant advantage is gained by using a transfer learning approach over a traditional machine learning approach for our character recognition tasks. This suggests that using transfer learning does not necessarily presuppose a better performing model in all cases. Learning to drive a car makes learning to drive a truck easier, and knowing how to speak Spanish makes learning Portuguese easier.

It's easy to get cynical about artificial intelligence (AI). China is using facial recognition against the Uighurs. NYT: 'One Month, 500,000 Face Scans: How China Is Using A.I. to Profile a Minority' Google's participating in the development of autonomous weapons. The Intercept: 'Google Continues Investments in Military and Police AI Technology Through Venture Capital Arm' And facial recognition programmes are still struggling to recognise black faces. But last year I also saw another side.

At Voyance, our ultimate mission is to democratize machine learning for everyone in the data science ecosystem and as such, we are so happy to announce WithData. WithData is a 5 min video interview showcasing and interviewing data analyst, scientist, product managers and engineers helping African organisations make data driven decisions. The data science ecosystem in Nigeria is still very nascent and our goal with this series is to help bring spotlight into it and showcase the ever growing amazing talented individuals working in this industry. This video series will also enable these people talk about their work i.e what goes into building a complete predictive models and so much more. If you would like to be part of the video series, kindly fill this Airtable form https://airtable.com/shrDUiLwTVkyWcj6e with your information and we'll get back to you ASAP.

The global artificial intelligence in fashion market accounted for US$ 270.0 Mn in 2018 and is expected to grow at a CAGR of 36.9% over the forecast period 2019-2027, to account for US$ 4,391.7 Mn in 2027. Driving factors such as availability of massive amount of data due to increasing proliferation of digital services across the globe, and real time consumer behavior insights and increased operational efficiency are driving the adoption of AI in fashion industry will drive the market during the forecast period and have a high impact in the short term. However, factors such as concerns related to data privacy and security is anticipated to hinder the market growth in the coming years. AI integration in fashion plays a crucial role in sales, marketing, and customer-focused purposes.Initial adopters point toward the key impacts of technology in improving customer experience and decent growth in company revenue. Elevated customer experience helps the retailer to crack entirely new tactics of customer engagement and communication.With AI integration, the retailers can precisely spot the customers' expected needs at precise times and offer the appropriate product to gain a competitive advantage. Some of the past initiatives taken in the fashion industry sector which has revolutionize the use of AI in the sector are North Face leveraging IBM Watson's ML technology to recommend more personalized apparel to the customers.Further, eBay's AI integration helps their sellers sell more by better inventory management and pricing recommendations.

We asked 9 industry experts to contribute their thoughts on the year ahead, and a common theme was the need for these technologies to mature, with the genuinely useful implementations finally getting to market. Expanding on last year, we have chosen seven areas of interest to focus on in 2019. Each represents a vital area of innovation in the financial industry, and has a particular relevance to Luxembourg's thriving financial technology ecosystem. Each week we will be choosing one of the topics to focus on, both in the content we share on social media, but also in a dedicated newsletter looking at the top five stories from that week. First, let's introduce the topics with some of our favourite summaries for the uninitiated: "Regtech growth will explode in 2019 because regulators worldwide will start truly driving it. Multiple countries will hold a joint hackathon at midyear, aiming to use technology to remove one of the biggest regtech blockers: how to share data widely to find risk patterns and fight financial crime, while fully protecting privacy and cybersecurity. Solutions will solve myriad regulatory problems. Even more importantly, the shared experience will move regulatory bodies into a new era of active innovation and collaboration with each other, industry, and academia. Anti-money laundering will continue to be a leading use case, because the current system is so broken and costly and there's so much low-hanging fruit to harvest through technology. We'll also see AI and blockchain solving more problems, from digital identity and financial fairness and inclusion to API-based regulatory reporting, machine-readable regulations, and even machine-executable compliance. These regulatory breakthroughs are not just nice-to-have. They are essential, if fintech innovation is to flourish. The regulations are the rules of the road we're all traveling."

Buildings often have impressive facades but hidden flaws can bring expensive disasters. Densely developed cities have strong demand for "infrastructure-building doctors" which use artificial intelligence (AI) technologies and robotics to find structural flaws – demand that Harris Sun, Chief Executive Officer and Founder of RaSpect, is eager to meet. The start-up improves on existing building inspections by using AI and cloud-based data analysis to build up models of the structures. This permits remote detection which saves costs and time. Being among the winners of a competition held as part of the Hong Kong Trade Development Council's (HKTDC) Start-up Express 2019 development programme, Mr Sun is looking forward to using the HKTDC's business-matching activities to expand overseas.

Smart grid is an alternative solution of the conventional power grid which harnesses the power of the information technology to save the energy and meet today's environment requirements. Due to the inherent vulnerabilities in the information technology, the smart grid is exposed to a wide variety of threats that could be translated into cyber-attacks. In this paper, we develop a deep learning-based intrusion detection system to defend against cyber-attacks in the advanced metering infrastructure network. The proposed machine learning approach is trained and tested extensively on an empirical industrial dataset which is composed of several attack categories including the scanning, buffer overflow, and denial of service attacks. Then, an experimental comparison in terms of detection accuracy is conducted to evaluate the performance of the proposed approach with Naive Bayes, Support Vector Machine, and Random Forest. The obtained results suggest that the proposed approaches produce optimal results comparing to the other algorithms. Finally, we propose a network architecture to deploy the proposed anomaly-based intrusion detection system across the Advanced Metering Infrastructure network. In addition, we propose a network security architecture composed of two types of Intrusion detection system types, Host and Network-based, deployed across the Advanced Metering Infrastructure network to inspect the traffic and detect the malicious one at all the levels.

Background. Recently, In Italy the vaccination coverage for key immunizations, as MMR, has been declining, with measles outbreaks. In 2017, the Italian Government expanded the number of mandatory immunizations establishing penalties for families of unvaccinated children. During the 2018 elections campaign, immunization policy entered the political debate, with the government accusing oppositions of fuelling vaccine scepticism. A new government established in 2018 temporarily relaxed penalties and announced the introduction of flexibility. Objectives and Methods. By a sentiment analysis on tweets posted in Italian during 2018, we aimed at (i) characterising the temporal flow of communication on vaccines, (ii) evaluating the usefulness of Twitter data for estimating vaccination parameters, and (iii) investigating whether the ambiguous political communication might have originated disorientation among the public. Results. The population appeared to be mostly composed by "serial twitterers" tweeting about everything including vaccines. Tweets favourable to vaccination accounted for 75% of retained tweets, undecided for 14% and unfavourable for 11%. Twitter activity of the Italian public health institutions was negligible. After smoothing the temporal pattern, an up-and-down trend in the favourable proportion emerged, synchronized with the switch between governments, providing clear evidence of disorientation. Conclusion. The reported evidence of disorientation documents that critical health topics, as immunization, should never be used for political consensus. This is especially true given the increasing role of online social media as information source, which might yield to social pressures eventually harmful for vaccine uptake, and is worsened by the lack of institutional presence on Twitter. This calls for efforts to contrast misinformation and the ensuing spread of hesitancy.