Insurance is one of the oldest modern industries. Most policies sold today are still based on concepts of coverage and pricing invented centuries ago, by early insurance companies in England and continental Europe. Now the industry is being re-invented--and much of the action can be found among new insurtech companies in China and Southeast Asia. Insurtech is the use of digital technology to cut costs and enhance processes for both new and existing types of insurance. A recent Forbes Tech Council report summed up its potential: "Imagine getting a policy that is custom-tailored to your exact needs, lets you start and stop coverage on demand, makes you pay only for the coverage you use, and can be underwritten within seconds on your smartphone." That vision is fast becoming reality.

Sen. Jerry Moran (R., Kan.), chairman of the Senate's consumer protection subcommittee, said he was considering joining in an effort by Sen. Richard Blumenthal (D., Conn.) to pass a privacy bill of rights in Congress. His comments showed that the risks for big internet companies haven't dissipated since Facebook's scandal involving Cambridge Analytica, a political data consultancy that worked with President Donald Trump's 2016 campaign and obtained data of millions of Facebook users from an app developer, Aleksandr Kogan. Sen. John Thune (R., S.D.), the chairman of the powerful Commerce Committee, added that Facebook "remains under the microscope" and said lawmakers continue to examine potential measures to protect user privacy. But key lawmakers appeared to be far from a consensus on how to proceed. At Tuesday's hearing, Mr. Kogan, a social psychologist and University of Cambridge lecturer, in prepared testimony, called for strengthening the system of obtaining users' consent for subsequent use of their information.

Thanks to the digitized instruments found on Pro Tools and GarageBand, any wannabe music producer can command a virtual orchestra in 2018 using no more hardware than a single laptop. If they're really serious about their craft, they might plug in an MIDI keyboard, a guitar, or a stand-alone sampler to go one step further. That's nothing compared to Italian electronic music producer Leonardo Barbadoro. For his latest album, he's still using a computer to program his instruments -- but, thanks to some impressive robot technology, the instruments are all real. In all, Barbadoro's music is composed using a robot orchestra that's capable of playing more than 50 acoustic instruments on command.

Paediatric and child trauma experts are sounding the alarm that separating migrant children from their parents at the US border can cause serious physical and psychological damage. As more stories emerge about children being separated from their parents at the border between Mexico and the US, doctors and scientists are warning that there could be long-term, irreversible health impacts on children if they're not reunited expediently. The head of the American Academy of Pediatrics went so far as to call the policy "child abuse" and against "everything we stand for as paediatricians". "This is completely ridiculous and I'm approaching that not as someone who's taking a position in the politics, but as a scientist," says Charles A Nelson III, a professor of paediatrics and neuroscience at Harvard Medical School. "We just know the science does not support that this is good for kids."

The search giant is building alliances as it races Amazon to develop new ways for people to shop, from voice-enabled smart speakers to faster and more convenient home grocery delivery. Google last year teamed up with Walmart Inc. WMT 0.73% to let users order a selection of the retailer's products on Google's virtual assistant and speakers, a challenge to Amazon's Alexa service. Earlier this month, Google joined with Carrefour SA, Europe's largest retailer, to offer same-day delivery of perishable groceries to people's homes in France. The deal announced Monday also could help Google boost advertising revenue, which has been threatened by Amazon recently as businesses increasingly shift ads to the internet shopping site. The JD investment comes as Google seeks to strengthen its connections in China.

In the previous blog posts in this series, we discussed the motivation for clustering attacks and the data used and how to calculate the distance between two attacks using different methods on each feature we extracted. In this final blog post, we'll discuss the clustering algorithm itself – how to use the distance we calculated to create clusters from the data. We will discuss clustering in real time when only a small amount of data can be stored in memory. Finally, we'll show some results of the algorithm based on real data from Imperva customers. Now we have all the basic ingredients to input into the algorithm.

Very soon, your phone might be able to tell if you are lying or telling the truth. There is new machine algorithm wants to tap into the digital interactions that reveal when you are bluffing. Researchers have been finding some ways in which they can turn your phone into a lie detector instrument. There is a new machine learning algorithm which has been built by computer scientists at the University of Copenhagen which can detect honesty and dishonesty by analyzing the way you swipe or tap a smartphone. The research is based on the assumption that dishonesty interactions always take longer and involve more hand movement than honesty interaction.

We study finite-sum nonconvex optimization problems, where the objective function is an average of $n$ nonconvex functions. We propose a new stochastic gradient descent algorithm based on nested variance reduction. Compared with conventional stochastic variance reduced gradient (SVRG) algorithm that uses two reference points to construct a semi-stochastic gradient with diminishing variance in each iteration, our algorithm uses $K+1$ nested reference points to build a semi-stochastic gradient to further reduce its variance in each iteration. For smooth nonconvex functions, the proposed algorithm converges to an $\epsilon$-approximate first-order stationary point (i.e., $\|\nabla F(\mathbf{x})\|_2\leq \epsilon$) within $\tilde{O}(n\land \epsilon^{-2}+\epsilon^{-3}\land n^{1/2}\epsilon^{-2})$ number of stochastic gradient evaluations. This improves the best known gradient complexity of SVRG $O(n+n^{2/3}\epsilon^{-2})$ and that of SCSG $O(n\land \epsilon^{-2}+\epsilon^{-10/3}\land n^{2/3}\epsilon^{-2})$. For gradient dominated functions, our algorithm also achieves a better gradient complexity than the state-of-the-art algorithms.

Genetic Algorithms (GAs) are used to solve search and optimization problems in which an optimal solution can be found using an iterative process with probabilistic and non-deterministic transitions. However, depending on the problem's nature, the time required to find a solution can be high in sequential machines due to the computational complexity of genetic algorithms. This work proposes a parallel implementation of a genetic algorithm on field-programmable gate array (FPGA). Optimization of the system's processing time is the main goal of this project. Results associated with the processing time and area occupancy (on FPGA) for various population sizes are analyzed. Studies concerning the accuracy of the GA response for the optimization of two variables functions were also evaluated for the hardware implementation. However, the high-performance implementation proposes in this paper is able to work with more variable from some adjustments on hardware architecture.

In this paper, we introduce a skill-balancing mechanism for adversarial non-player characters (NPCs), called Skilled Experience Catalogue (SEC). The objective of this mechanism is to approximately match the skill level of an NPC to an opponent in real-time. We test the technique in the context of a First-Person Shooter (FPS) game. Specifically, the technique adjusts a reinforcement learning NPC's proficiency with a weapon based on its current performance against an opponent. Firstly, a catalogue of experience, in the form of stored learning policies, is built up by playing a series of training games. Once the NPC has been sufficiently trained, the catalogue acts as a timeline of experience with incremental knowledge milestones in the form of stored learning policies. If the NPC is performing poorly, it can jump to a later stage in the learning timeline to be equipped with more informed decision-making. Likewise, if it is performing significantly better than the opponent, it will jump to an earlier stage. The NPC continues to learn in real-time using reinforcement learning but its policy is adjusted, as required, by loading the most suitable milestones for the current circumstances.