Kernel methods are powerful machine learning techniques which implement generic non-linear functions to solve complex tasks in a simple way. They Have a solid mathematical background and exhibit excellent performance in practice. However, kernel machines are still considered black-box models as the feature mapping is not directly accessible and difficult to interpret.The aim of this work is to show that it is indeed possible to interpret the functions learned by various kernel methods is intuitive despite their complexity. Specifically, we show that derivatives of these functions have a simple mathematical formulation, are easy to compute, and can be applied to many different problems. We note that model function derivatives in kernel machines is proportional to the kernel function derivative. We provide the explicit analytic form of the first and second derivatives of the most common kernel functions with regard to the inputs as well as generic formulas to compute higher order derivatives. We use them to analyze the most used supervised and unsupervised kernel learning methods: Gaussian Processes for regression, Support Vector Machines for classification, Kernel Entropy Component Analysis for density estimation, and the Hilbert-Schmidt Independence Criterion for estimating the dependency between random variables. For all cases we expressed the derivative of the learned function as a linear combination of the kernel function derivative. Moreover we provide intuitive explanations through illustrative toy examples and show how to improve the interpretation of real applications in the context of spatiotemporal Earth system data cubes. This work reflects on the observation that function derivatives may play a crucial role in kernel methods analysis and understanding.

We present a method for enhancing the sensitivity of X-ray telescopic observations with imaging polarimeters, with a focus on the gas pixel detectors (GPDs) to be flown on the Imaging X-ray Polarimetry Explorer (IXPE). Our analysis determines photoelectron directions, X-ray absorption points and X-ray energies for 1-9 keV event tracks, with estimates for both the statistical and model (reconstruction) uncertainties. We use a weighted maximum likelihood combination of predictions from a deep ensemble of ResNet convolutional neural networks, trained on Monte Carlo event simulations. We define a figure of merit to compare the polarization bias-variance trade-off in track reconstruction algorithms. For power-law source spectra, our method improves on the current planned IXPE analysis (and previous deep learning approaches), providing ~45% increase in effective exposure times. For individual energies, our method produces 20-30% absolute improvements in modulation factor for simulated 100% polarized events, while keeping residual systematic modulation within 1 sigma of the finite sample minimum. Absorption point location and photon energy estimates are also significantly improved. We have validated our method with sample data from real GPD detectors.

Table entailment, the binary classification task of finding if a sentence is supported or refuted by the content of a table, requires parsing language and table structure as well as numerical and discrete reasoning. While there is extensive work on textual entailment, table entailment is less well studied. We adapt TAPAS (Herzig et al., 2020), a table-based BERT model, to recognize entailment. Motivated by the benefits of data augmentation, we create a balanced dataset of millions of automatically created training examples which are learned in an intermediate step prior to fine-tuning. This new data is not only useful for table entailment, but also for SQA (Iyyer et al., 2017), a sequential table QA task. To be able to use long examples as input of BERT models, we evaluate table pruning techniques as a pre-processing step to drastically improve the training and prediction efficiency at a moderate drop in accuracy. The different methods set the new state-of-the-art on the TabFact (Chen et al., 2020) and SQA datasets.

The sun is getting a close-up as NASA releases historic new photographs. Talk about "to boldly go." A new space toilet is making its way to the crew of the International Space Station aboard a Cygnus spacecraft. "Its features improve on current space toilet operations and help NASA prepare for future missions, including those to the Moon and Mars," explained NASA, in a statement. "The Universal Waste Management System (UWMS) demonstrates a compact toilet and the Urine Transfer System that further automates waste management and storage."

Hitachi Construction Machinery Co. Ltd and its consolidated subsidiary, Wenco International Mining Systems Ltd have jointly developed ConSite Mine, which helps resolve problems at mine sites by remotely monitoring mining machines on 24/7 basis through the use of Internet of Things (IoT) and artificial intelligence (AI) based analysis of equipment operations data. Hitachi Construction Machinery has developed this technology to help customers and Hitachi Construction Machinery dealers predict costly maintenance issues before they occur, such as the occurrence of cracks in and excavator boom or arm by utilising machine learning and applied analysis technologies. Currently, Hitachi Construction Machinery Group is piloting the technology in Australia, Zambia and Indonesia. The system will be further modified based on customer feedback before wider commercial release in 2021. ConSite Mine will enable the maintenance professionals for customers and Hitachi Construction Machinery dealers to monitor equipment health in real time and anticipate issues before they occur.

The ones old enough to remember, might recall the times when image communication seemed a far distant impossible reality… a futuristic dream that would never be achieved! In the last few decades, we have seen what seems like reality surpassing imagination. Incredible technological advancements are happening at such quick pace that one is almost incapable to keep up with all the innovations. And one of the most radical inventions that is promising a tsunami in our lives is AI. The tsunami AI, has been out there actually for a long time.

The global life insurance industry has seen significant changes over the past decade. Developing economies--predominantly emerging markets in Asia that were formerly small contributors--have become global growth drivers and now account for more than half of global premium growth (Exhibit 1) and 84 percent of individual annuities growth (Exhibit 2). The availability of data has skyrocketed, and insurers have made progress in advanced analytics and artificial intelligence. Digital and mobile advances have raised the bar on transparency and service quality: customers can now file claims and access agents, insurance quotes, and policy information with a few taps on a screen. The past decade has also introduced new challenges. Life insurers have not benefitted from the bull market (Exhibit 3). Global penetration fell to 3 percent, and premium growth within most developed markets, hovering just below 2 percent per year, struggled to match GDP.

Given a large data matrix, sparsifying, quantizing, and/or performing other entry-wise nonlinear operations can have numerous benefits, ranging from speeding up iterative algorithms for core numerical linear algebra problems to providing nonlinear filters to design state-of-the-art neural network models. Here, we exploit tools from random matrix theory to make precise statements about how the eigenspectrum of a matrix changes under such nonlinear transformations. In particular, we show that very little change occurs in the informative eigenstructure even under drastic sparsification/quantization, and consequently that very little downstream performance loss occurs with very aggressively sparsified or quantized spectral clustering. We illustrate how these results depend on the nonlinearity, we characterize a phase transition beyond which spectral clustering becomes possible, and we show when such nonlinear transformations can introduce spurious non-informative eigenvectors.

Louis Columbus in 10 Ways AI Is Going To Improve Fintech In 2020 stated that "Bottom Line: AI & machine learning will improve Fintech in 2020 by increasing the accuracy and personalization of payment, lending, and insurance services while also helping to discover new borrower pools." Since that time the Covid-19 crisis and tragedy arose. On the one hand Paul Clarke noted that UK fintech investment slumps by 40% amid Covid-19 crisis, whilst on the other Deloitte in Beyond COVID-19: New opportunities for Fintech companies note that "As the COVID-19 pandemic continues to create uncertainty, many fintechs are under stress on a number of fronts. But, as the broader economy shifts from "respond" to "recover", new opportunities may be created for some fintechs. A key question is how fintechs may leverage their unique assets and skills to seize new opportunities in the future. It could be an opportune time to think big and act boldly." Pavrita R considered the impact of Covid-19 and noted in 5 U.S. FinTech startups reimagining the healthcare industry notes that FinTech is undoubtedly shaping the face of the Health Care industry. "FinTech companies leverage powerful innovations blockchain, Artificial Intelligence, and Machine Learning to eliminate the inefficiencies and knowledge gaps endemic to most healthcare payment plans." The likes of Nigel Wilson (@nigewillson) and Brian Ahier (@ahier) have stressed the importance to apply AI to positive use cases such as preventative medicine and improved Health Care outcomes. McKinsey in an article entitled AI-bank of the future: Can banks meet the AI challenge? " The potential for value creation is one of the largest across industries, as AI can potentially unlock $1 trillion of incremental value for banks, annually (Exhibit 1)." Source for image above: AI-bank of the future: Can banks meet the AI challenge? "While for many financial services firms, the use of AI is episodic and focused on specific use cases, an increasing number of banking leaders are taking a comprehensive approach to deploying advanced AI, and embedding it across the full lifecycle, from the front- to the back-office (Exhibit 2)" Source for image above: AI-bank of the future: Can banks meet the AI challenge? The Covid-19 crisis is a challenge both in terms of human health and also to the Fintech world.

The period of voice-enabled search and commerce has shown up, and organizations need to prepare themselves for this new paradigm. By implanting brands into conversations, organizations can give customized solutions for pretty much any issue. Voice frameworks have quickly advanced from the simple voice commands to entire ecosystems of applications and interactions. Intelligent speakers like Amazon Echo, Apple Home Pod, and Google Home give various entertainment choices inside your home. These voice AI-empowered systems have cleared another dimension to execute tasks that were initially limited to a screen.