"Andrew Ingram" is a digital assistant that scans your emails, gives scheduling ideas for the meetings and appointments you discuss with your coworkers, sets up tasks, and sends invites to the relevant parties with very little assistance. It uses the advanced artificial-intelligence capabilities of X.ai, a New York–based startup that specializes in developing AI assistants. The problems it solves can save a lot of time and frustration for people (like me) who have a messy schedule. But according to a Wired story published in May, the intelligence behind Andrew Ingram is not totally artificial. It's backed by a group of 40 Filipinos in a highly secured building on the outskirts of Manila who monitor the AI's behavior and take over whenever the assistant runs into a case it can't handle.

Continuing the recent trend of rapid updates introducing significant fixes and new features, Tensorflow has released its version Tensorflow 1.10 during my summer vacations. This is good for our research in Artificial Intelligence and Deep Learning at BSC. The full release notes for details on added features and changes that version 1.10 has over its predecessor can be found here: Official release page on GitHub. Some of us were expecting the next major release of Tensorflow, Tensorflow 2.0, to be released in late August. However, the mention of the next version update (1.11) means that we will have to wait for some more time!!!.;-)

Machine learning platforms are not the wave of the future. Developers need to know how and when to harness their power. Working within the ML landscape while using the right tools like Filestack can make it easier for developers to create a productive algorithm that taps into its power. The following machine learning platforms and tools -- listed in no certain order -- are available now as resources to seamlessly integrate the power of ML into daily tasks. H2O was designed for the Python, R and Java programming languages by H2O.ai. By using these familiar languages, this open source software makes it easy for developers to apply both predictive analytics and machine learning to a variety of situations.

An AI system created by Google's DeepMind Health, Moorfields Eye Hospital NHS Foundation Trust, and University College London (UCL) Institute of Ophthalmology can correctly determine how to refer optometry patients in 94 percent of cases, putting it on par with top human experts. The advances in AI-driven eye disease treatment were detailed in a study being published online in the journal Nature Medicine. Results of the work that began in 2016 were first made public in a Financial Times report in February, which found AI used to analyze retinal scans for signs of the biggest eye diseases -- like glaucoma, age-related macular degeneration, and diabetic retinopathy -- could be more accurate than trained human experts. Neural networks trained to discover patterns in images have also been used to do things like detect cardiovascular disease, breast cancer, and kidney disease. "The AI technology we're developing is designed to prioritize patients who need to be seen and treated urgently by a doctor or eye care professional," said UCL scientist Dr. Pearse Keane in a statement shared with VentureBeat.

AI research group DeepMind created the new tech that is able to spot key signs of eye disease just as well as the world's top doctors. A link has been sent to your friend's email address. A link has been posted to your Facebook feed. AI research group DeepMind created the new tech that is able to spot key signs of eye disease just as well as the world's top doctors.

Machine learning, a form of artificial intelligence, enjoys unprecedented success in commercial applications. However, the use of machine learning in high performance computing for science has been limited. Why? Advanced machine learning tools weren't designed for big data sets, like those used to study stars and planets. A team from Intel, National Energy Research Scientific Computing Center (NERSC), and Stanford changed that situation. They developed the first 15-petaflop deep-learning software.

Google's AI division is making artificial intelligence more alien, a copy of Fahrenheit 451 you need to burn to read and the arrival of Windows Mixed Reality headsets - this is what you might have missed this week in tech news.

In a paper published in Nature Medicine on Monday, Google's DeepMind subsidiary, UCL, and researchers at Moorfields Eye Hospital showed off their new AI system. The researchers used deep learning to create algorithm-driven software that can identify common patterns in data culled from dozens of common eye diseases from 3D scans. The result is an AI that can identify more than 50 diseases with incredible accuracy and can then refer patients to a specialist. Even more important, though, is that the AI can explain why a diagnosis was made, indicating which part of the scan prompted the outcome. That's all well and good when an AI helps you cry at a movie or write a Yelp review, but when it comes to diagnosing medical conditions, patients (and doctors) would prefer a little more context.

In manufacture, steel and other metals are mainly cut and shaped during the fabrication process by computer numerical control (CNC) machines. To keep high productivity and efficiency of the fabrication process, engineers need to monitor the real-time process of CNC machines, and the lifetime management of machine tools. In a real manufacturing process, breakage of machine tools usually happens without any indication, this problem seriously affects the fabrication process for many years. Previous studies suggested many different approaches for monitoring and detecting the breakage of machine tools. However, there still exists a big gap between academic experiments and the complex real fabrication processes such as the high demands of real-time detections, the difficulty in data acquisition and transmission. In this work, we use the spindle current approach to detect the breakage of machine tools, which has the high performance of real-time monitoring, low cost, and easy to install. We analyze the features of the current of a milling machine spindle through tools wearing processes, and then we predict the status of tool breakage by a convolutional neural network(CNN). In addition, we use a BP neural network to understand the reliability of the CNN. The results show that our CNN approach can detect tool breakage with an accuracy of 93%, while the best performance of BP is 80%.

Recent work on adversarial attack has shown that Projected Gradient Descent (PGD) Adversary is a universal first-order adversary, and the classifier adversarially trained by PGD is robust against a wide range of first-order attacks. However, it is worth noting that the objective of an attacking/defense model relies on a data distribution, typically in the form of risk maximization/minimization: $\max\!/\!\min \mathbb{E}_{p(\mathbf{x})} \mathcal{L}(\mathbf{x})$, with $p(\mathbf{x})$ the data distribution and $\mathcal{L}(\cdot)$ a loss function. While PGD generates attack samples independently for each data point, the procedure does not necessary lead to good generalization in terms of risk maximization. In the paper, we achieve the goal by proposing distributionally adversarial attack (DAA), a framework to solve an optimal {\em adversarial data distribution}, a perturbed distribution that is close to the original data distribution but increases the generalization risk maximally. Algorithmically, DAA performs optimization on the space of probability measures, which introduces direct dependency between all data points when generating adversarial samples. DAA is evaluated by attacking state-of-the-art defense models, including the adversarially trained models provided by MadryLab. Notably, DAA outperforms all the attack algorithms listed in MadryLab's white-box leaderboard, reducing the accuracy of their secret MNIST model to $88.79\%$ (with $l_\infty$ perturbations of $\epsilon = 0.3$) and the accuracy of their secret CIFAR model to $44.73\%$ (with $l_\infty$ perturbations of $\epsilon = 8.0$). Code for the experiments is released on https://github.com/tianzheng4/Distributionally-Adversarial-Attack