AI powered by neural nets have not only excelled at tasks that require pattern recognition, they have also succeeded in performing tasks that require basic logic and reasoning -- areas that have conventionally been computers' Achilles' heel. In this backdrop, the question is, can neural networks be exploited to usher in an era of data-driven astronomy and create some of the sharpest ever images of celestial objects? The answer, according to a new study published in the Monthly Notices of the Royal Astronomical Society, is yes. In the paper, a group of researchers from the Swiss university ETH Zurich describe a neural net-enabled system that can recognize and reconstruct astronomical features that telescopes could not resolve, including star-forming regions, bars and streams of dust in galaxies. In order to create this system, the researchers used an adversarial learning technique, wherein two neural networks compete and try to outsmart each other.

A decision tree is one of the widely used algorithms for building classification or regression models in data mining and machine learning. A decision tree is so named because the output resulting from it is the form of a tree structure. Consider a sample stock dataset as shown in the table below. The dataset comprises of Open, High, Low, Close Prices and Volume indicators (OHLCV) for the stock. Let us add some technical indicators (RSI, SMA, LMA, ADX) to this dataset.

Notes from Reality is a series of posts on AI and its impact on humans, what can be done today, and what may happen tomorrow. No one has all the answers, but we are trying to arrive at the right questions. In this post, I interviewed Dr. David Bray, Harvard Executive In-Residence and Eisenhower Fellow. This effort began with the post "Let the New Machine Age Begin." The process to write that led to another interview with Dr. Bray and Michael Krigsman, a noted analyst, which is posted here.

Samsung Electronics Co., Ltd., a world leader in advanced semiconductor technology, today announced the launch of its latest premium application processor (AP), the Exynos 9 Series 8895. This is Samsung's first processor chipset to take advantage of the most advanced and industry leading 10-nanometer (nm) FinFET process technology with improved 3D transistor structure, which allows up to 27% higher performance while consuming 40% less power when compared to 14nm technology. The new Exynos 9 Series 8895 is the first processor of its kind to embed a gigabit LTE modem that supports five carrier aggregation, or 5CA. It delivers fast and stable data throughput at max.1Gbps (Cat.16) The Exynos 8895 is an octa-core processor, comprising of four of Samsung's 2nd generation custom designed CPU cores for improved performance and power efficiency in addition to four Cortex -A53 cores.

With the rise of email came the rise of spam filling inboxes. Email has become sophisticated faster than spamming technology and now, the internet's junk mail is often caught in a folder; out of sight and out of mind are messages with the subject line "Kindly get back to me urgently" and the greeting "Dear Beneficiary." There's good news for anybody who sees fake news -- not the sort that's simply true but politically difficult for the president; but actual, fake, conspiracy theory-baiting chum -- as another form of spam. At least that's what Dean Pomerleau, research scientist at Carnegie Mellon University's Robotics Institute, said recently during a panel in New York on the proliferation of fake news. We solved the spam problem using artificial intelligence, he argued, and with A.I., we can solve the problem of fake news by filtering out credible news from the misinformation.

Retailers are pushing for more technology to enhance consumers' shopping experience, such as chatbots, virtual reality and augmented reality, but new research shows customers might not care so much about it. The report, Reality of Retail Tech shows consumers are not that psyched about new tech from retailers, especially chatbots and smart mirrors. Research for the report was conducted by mobile commerce and engagement platform, GPShopper, along with research and consulting organization YouGov. Data show there is clear disconnect between companies and shoppers over what technology people want to use. "Developments in mobile are further giving way to more advanced technology like virtual reality and chatbots, being brought into the shopping experience," said GPShopper Co-founder and CMO Maya Mikhailov in a statement.

A recurrent neural network model of phonological pattern learning is proposed. The model is a relatively simple neural network with one recurrent layer, and displays biases in learning that mimic observed biases in human learning. Single-feature patterns are learned faster than two-feature patterns, and vowel or consonant-only patterns are learned faster than patterns involving vowels and consonants, mimicking the results of laboratory learning experiments. In non-recurrent models, capturing these biases requires the use of alpha features or some other representation of repeated features, but with a recurrent neural network, these elaborations are not necessary.

We introduce a new paradigm that is important for community detection in the realm of network analysis. Networks contain a set of strong, dominant communities, which interfere with the detection of weak, natural community structure. When most of the members of the weak communities also belong to stronger communities, they are extremely hard to be uncovered. We call the weak communities the hidden community structure. We present a novel approach called HICODE (HIdden COmmunity DEtection) that identifies the hidden community structure as well as the dominant community structure. By weakening the strength of the dominant structure, one can uncover the hidden structure beneath. Likewise, by reducing the strength of the hidden structure, one can more accurately identify the dominant structure. In this way, HICODE tackles both tasks simultaneously. Extensive experiments on real-world networks demonstrate that HICODE outperforms several state-of-the-art community detection methods in uncovering both the dominant and the hidden structure. In the Facebook university social networks, we find multiple non-redundant sets of communities that are strongly associated with residential hall, year of registration or career position of the faculties or students, while the state-of-the-art algorithms mainly locate the dominant ground truth category. In the Due to the difficulty of labeling all ground truth communities in real-world datasets, HICODE provides a promising approach to pinpoint the existing latent communities and uncover communities for which there is no ground truth. Finding this unknown structure is an extremely important community detection problem.

We consider the problem of estimating a regression function in the common situation where the number of features is small, where interpretability of the model is a high priority, and where simple linear or additive models fail to provide adequate performance. To address this problem, we present GapTV, an approach that is conceptually related both to CART and to the more recent CRISP algorithm, a state-of-the-art alternative method for interpretable nonlinear regression. GapTV divides the feature space into blocks of constant value and fits the value of all blocks jointly via a convex optimization routine. Our method is fully data-adaptive, in that it incorporates highly robust routines for tuning all hyperparameters automatically. We compare our approach against CART and CRISP and demonstrate that GapTV finds a much better trade-off between accuracy and interpretability.

We describe stochastic Newton and stochastic quasi-Newton approaches to efficiently solve large linear least-squares problems where the very large data sets present a significant computational burden (e.g., the size may exceed computer memory or data are collected in real-time). In our proposed framework, stochasticity is introduced in two different frameworks as a means to overcome these computational limitations, and probability distributions that can exploit structure and/or sparsity are considered. Theoretical results on consistency of the approximations for both the stochastic Newton and the stochastic quasi-Newton methods are provided. The results show, in particular, that stochastic Newton iterates, in contrast to stochastic quasi-Newton iterates, may not converge to the desired least-squares solution. Numerical examples, including an example from extreme learning machines, demonstrate the potential applications of these methods.