Microsoft today announced that it would invest $1 billion in OpenAI, the San Francisco-based AI research firm cofounded by CTO Greg Brockman, chief scientist Ilya Sutskever, Elon Musk, and others, with backing from luminaries like LinkedIn cofounder Reid Hoffman and former Y Combinator president Sam Altman. In a blog post, Brockman said the investment will support the development of artificial general intelligence (AGI) -- AI with the capacity to learn any intellectual task that a human can -- with "widely distributed" economic benefits. To this end, OpenAI intends to partner with Microsoft to jointly develop new AI technologies for the Seattle company's Azure cloud platform and will enter into an exclusivity agreement with Microsoft to "further extend" large-scale AI capabilities that "deliver on the promise of AGI." Additionally, OpenAI will license some of its technologies to Microsoft, which will commercialize them and sell them to as-yet-unnamed partners, and OpenAI will train and run AI models on Azure as it works to develop new supercomputing hardware while "adhering to principles on ethics and trust." "AI is one of the most transformative technologies of our time and has the potential to help solve many of our world's most pressing challenges," said Microsoft CEO Satya Nadella.

Predicting protein structures from their sequences would aid drug design.Credit: Edward Kinsman/Science Photo Library The race to crack one of biology's grandest challenges -- predicting the 3D structures of proteins from their amino-acid sequences -- is intensifying, thanks to new artificial-intelligence (AI) approaches. At the end of last year, Google's AI firm DeepMind debuted an algorithm called AlphaFold, which combined two techniques that were emerging in the field and beat established contenders in a competition on protein-structure prediction by a surprising margin. And in April this year, a US researcher revealed an algorithm that uses a totally different approach. He claims his AI is up to one million times faster at predicting structures than DeepMind's, although probably not as accurate in all situations. More broadly, biologists are wondering how else deep learning -- the AI technique used by both approaches -- might be applied to the prediction of protein arrangements, which ultimately dictate a protein's function.

Microsoft Corp. MSFT, 1.32% is making a huge bet on artificial intelligence by sinking $1 billion into AI startup OpenAI, the companies announced Monday. Under a partnership, OpenAI will run all of its services on Microsoft's Azure cloud platform and use Microsoft as its preferred partner for commercializing new AI tech. On its website, OpenAI says its mission is "to ensure that artificial general intelligence (AGI) -- by which we mean highly autonomous systems that outperform humans at most economically valuable work -- benefits all of humanity." Microsoft, which is currently the only U.S. company valued at more than $1 trillion, recently reported strong earnings growth driven by Azure. Shares were up 1.2% to $138.19 in recent trading Monday, compared with a flat Dow Jones Industrial Average DJIA, 0.07% a 0.3% gain in the S&P 500 index SPX, 0.28% and a 0.7% gain in the tech-heavy Nasdaq Composite Index COMP, 0.71%

The rising prominence of artificial intelligence (AI) in our conversations, the way we work and do business, protect communities against crime and even the way news is reported to us on television is unprecedented. Its ability to learn and process massive amount of data far outstrips any other current technologies and will only continue to grow as we make greater strides in computer processing power and deep learning algorithms. In Singapore, the AI ecosystem is thriving with the emergence of start-ups, growing collaboration across sectors and the drive to develop capabilities and innovative solutions. A recent study by Microsoft and IDC Asia/Pacific estimated that AI will nearly double the rate of innovation and employee productivity improvements in Singapore by 2021, and the majority of people in Singapore believe that AI will either help to do their existing jobs better or reduce repetitive tasks. From manufacturing to healthcare, financial services and the public sector, the adoption of AI is pervasive with promise for powerful capabilities beyond our imagination.

In an era when the performance of a single compute device plateaus, software must be designed to scale on a massively parallel system for better runtime performance. However, the commonly used back-propagation (BP) algorithm imposes a strong sequential dependency in the process of gradient computation. Under model parallelism, BP has a theoretical step complexity of $\Theta (n)$ which hinders its scalability in a parallel computing environment, where $n$ represents the number of compute devices into which a model is partitioned. In this work, we restructure such dependency and reformulate BP into a scan operation which is scaled by our modified version of the Blelloch scan algorithm. Our algorithm is able to achieve a theoretical step complexity of $\Theta (\log n)$. We perform an in-depth performance analysis and identify the challenges of deploying our algorithm in a practical setting, along with a variety of approaches to tackle such challenges. We demonstrate the scalability benefits of our algorithm in the use case of retraining pruned networks.

Filter banks are a popular tool for the analysis of piecewise smooth signals such as natural images. Motivated by the empirically observed properties of scale and detail coefficients of images in the wavelet domain, we propose a hierarchical deep generative model of piecewise smooth signals that is a recursion across scales: the low pass scale coefficients at one layer are obtained by filtering the scale coefficients at the next layer, and adding a high pass detail innovation obtained by filtering a sparse vector. This recursion describes a linear dynamic system that is a non-Gaussian Markov process across scales and is closely related to multilayer-convolutional sparse coding (ML-CSC) generative model for deep networks, except that our model allows for deeper architectures, and combines sparse and non-sparse signal representations. We propose an alternating minimization algorithm for learning the filters in this hierarchical model given observations at layer zero, e.g., natural images. The algorithm alternates between a coefficient-estimation step and a filter update step. The coefficient update step performs sparse (detail) and smooth (scale) coding and, when unfolded, leads to a deep neural network. We use MNIST to demonstrate the representation capabilities of the model, and its derived features (coefficients) for classification.

Personalized size and fit recommendations bear crucial significance for any fashion e-commerce platform. Predicting the correct fit drives customer satisfaction and benefits the business by reducing costs incurred due to size-related returns. Traditional collaborative filtering algorithms seek to model customer preferences based on their previous orders. A typical challenge for such methods stems from extreme sparsity of customer-article orders. To alleviate this problem, we propose a deep learning based content-collaborative methodology for personalized size and fit recommendation. Our proposed method can ingest arbitrary customer and article data and can model multiple individuals or intents behind a single account. The method optimizes a global set of parameters to learn population-level abstractions of size and fit relevant information from observed customer-article interactions. It further employs customer and article specific embedding variables to learn their properties. Together with learned entity embeddings, the method maps additional customer and article attributes into a latent space to derive personalized recommendations. Application of our method to two publicly available datasets demonstrate an improvement over the state-of-the-art published results. On two proprietary datasets, one containing fit feedback from fashion experts and the other involving customer purchases, we further outperform comparable methodologies, including a recent Bayesian approach for size recommendation.

Analyzing and utilizing spatiotemporal big data are essential for studies concerning climate change. However, such data are not fully integrated into climate models owing to limitations in statistical frameworks. Herein, we employ VARENN (visually augmented representation of environment for neural networks) to efficiently summarize monthly observations of climate data for 1901-2016 into 2-dimensional graphical images. Using red, green, and blue channels of color images, three different variables are simultaneously represented in a single image. For global datasets, models were trained via convolutional neural networks. These models successfully classified rises and falls in temperature and precipitation. Moreover, similarities between the input and target variables were observed to have a significant effect on model accuracy. The input variables had both seasonal and interannual variations, whose importance was quantified for model efficacy. VARENN is thus an effective method to summarize spatiotemporal data objectively and accurately.

Neural networks are vulnerable to adversarial examples, malicious inputs crafted to fool trained models. Adversarial examples often exhibit black-box transfer, meaning that adversarial examples for one model can fool another model. However, adversarial examples are typically overfit to exploit the particular architecture and feature representation of a source model, resulting in sub-optimal black-box transfer attacks to other target models. We introduce the Intermediate Level Attack (ILA), which attempts to fine-tune an existing adversarial example for greater black-box transferability by increasing its perturbation on a pre-specified layer of the source model, improving upon state-of-the-art methods. We show that we can select a layer of the source model to perturb without any knowledge of the target models while achieving high transferability. Additionally, we provide some explanatory insights regarding our method and the effect of optimizing for adversarial examples in intermediate feature maps.

Deep learning techniques, namely convolutional neural networks (CNN), have previously been adapted to select gamma-ray events in the TAIGA experiment, having achieved a good quality of selection as compared with the conventional Hillas approach. Another important task for the TAIGA data analysis was also solved with CNN: gamma-ray energy estimation showed some improvement in comparison with the conventional method based on the Hillas analysis. Furthermore, our software was completely redeveloped for the graphics processing unit (GPU), which led to significantly faster calculations in both of these tasks. All the results have been obtained with the simulated data of TAIGA Monte Carlo software; their experimental confirmation is envisaged for the near future.