Facebook's AI team today introduced a series of upgrades for developers using machine learning tools including Ax, a platform for machine learning experimentation management that sits atop of PyTorch. PyTorch 1.1 was also released today with native TensorBoard support for machine learning visualization and improved performance speed for its JIT compiler. PyTorch 1.0 made its debut last fall. Ax is meant to run experiments to adjust things like learning rate and dropouts to see which approach produces AI models with the highest accuracy rate. "When you're tuning or training a neural network, you don't train a single instance of the neural network," PyTorch creator Soumith Chintala told VentureBeat in a phone interview.

Marketing automation aims to help Marketing and Sales coordinate and streamline time-consuming tasks. No wonder 75% of marketers say they use at least one type of marketing automation tool, according to Social Media Today's "The State of Marketing Automation" study. Marketing automation tools help marketers with a growing number of tasks--from scheduling social media posts to email marketing, text messaging, employing chatbots, and much more. And now, with the insertion of artificial intelligence (AI) and machine-learning (ML) into the automation process, not only rote tasks but also more complex ones that, until now, required immediate human discernment and judgment--such as analysis, customization, and personalization--can be automated. Two infographics from UK-based Market Inspector--provider of a service that allows businesses to compare quotes and offers from a range of suppliers--summarize the usage and benefits of automation and lay out how AI can boost B2B marketing automation.

While some people might think Cinco de Mayo is about Mexican independence, it's actually a holiday that celebrates the day three Americans fought and defeated El Guapo at the Battle of Santa Poco. And it's just one of the many things Mexico is famous for. Her rich cultural heritage has resulted in some of the world's best cuisine that has been exported to every corner of the planet. Then there are the other exports, like those depicted in the recent third season of Narcos, a gripping thriller about the country's cartels in the 1980s. Mexico also plays a key role in regional international trade as the US' neighbor and second largest export market.

So you're the CEO of a clothing retailer, a rental car agency, or a payroll processing company, and you hear that artificial intelligence is changing the world. What are you supposed to do? The short answer, says Paul Oyer at Stanford Graduate School of Business, is to start learning fast. "Artificial intelligence will affect every industry, whether it's clothing or shipping," says Oyer, a professor of economics and the codirector of a new multidisciplinary course on AI for senior executives. "We need to find a complementary relationship between those who deal with the technology of AI and the managers who understand what drives their companies. Managers don't need to learn all the technical details, but they do need to understand the implications for their business."

We propose novel algorithms for design and design space exploration. The designs computed by these algorithms are compositions of function types specified in component libraries. Our algorithms reduce the design problem to quantified satisfiability and use advanced solvers to find solutions that represent useful systems. The algorithms we present in this paper are sound and complete and are guaranteed to discover correct designs of optimal size, if they exist. We apply our method to the design of Boolean systems and discover new and more optimal classical and quantum circuits for common arithmetic functions such as addition and multiplication. The performance of our algorithms is evaluated through extensive experimentation. We have first created a benchmark consisting of specifications of scalable synthetic digital circuits and real-world mirochips. We have then generated multiple circuits functionally equivalent to the ones in the benchmark. The quantified satisfiability method shows more than four orders of magnitude speed-up, compared to a generate and test method that enumerates all non-isomorphic circuit topologies. Our approach generalizes circuit optimization. It uses arbitrary component libraries and has applications to areas such as digital circuit design, diagnostics, abductive reasoning, test vector generation, and combinatorial optimization.

We propose a topological learning algorithm for the estimation of the conditional dependency structure of large sets of random variables from sparse and noisy data. The algorithm, named Maximally Filtered Clique Forest (MFCF), produces a clique forest and an associated Markov Random Field (MRF) by generalising Prim's minimum spanning tree algorithm. To the best of our knowledge, the MFCF presents three elements of novelty with respect to existing structure learning approaches. The first is the repeated application of a local topological move, the clique expansion, that preserves the decomposability of the underlying graph. Through this move the decomposability and calculation of scores is performed incrementally at the variable (rather than edge) level, and this provides better computational performance and an intuitive application of multivariate statistical tests. The second is the capability to accommodate a variety of score functions and, while this paper is focused on multivariate normal distributions, it can be directly generalised to different types of statistics. Finally, the third is the variable range of allowed clique sizes which is an adjustable topological constraint that acts as a topological penalizer providing a way to tackle sparsity at $l_0$ semi-norm level; this allows a clean decoupling of structure learning and parameter estimation. The MFCF produces a representation of the clique forest, together with a perfect ordering of the cliques and a perfect elimination ordering for the vertices. As an example we propose an application to covariance selection models and we show that the MCFC outperforms the Graphical Lasso for a number of classes of matrices.

Spatial studies of transcriptome provide biologists with gene expression maps of heterogeneous and complex tissues. However, most experimental protocols for spatial transcriptomics suffer from the need to select beforehand a small fraction of genes to be quantified over the entire transcriptome. Standard single-cell RNA sequencing (scRNA-seq) is more prevalent, easier to implement and can in principle capture any gene but cannot recover the spatial location of the cells. In this manuscript, we focus on the problem of imputation of missing genes in spatial transcriptomic data based on (unpaired) standard scRNA-seq data from the same biological tissue. Building upon domain adaptation work, we propose gimVI, a deep generative model for the integration of spatial transcriptomic data and scRNA-seq data that can be used to impute missing genes. After describing our generative model and an inference procedure for it, we compare gimVI to alternative methods from computational biology or domain adaptation on real datasets and outperform Seurat Anchors, Liger and CORAL to impute held-out genes.

There is an abundance of complex dynamic systems that are critical to our daily lives and our society but that are hardly understood, and even with today's possibilities to sense and collect large amounts of experimental data, they are so complex and continuously evolving that it is unlikely that their dynamics will ever be understood in full detail. Nevertheless, through computational tools we can try to make the best possible use of the current technologies and available data. We believe that the most useful models will have to take into account the imbalance between system complexity and available data in the context of limited knowledge or multiple hypotheses. The complex system of biological cells is a prime example of such a system that is studied in systems biology and has motivated the methods presented in this paper. They were developed as part of the DARPA Rapid Threat Assessment (RTA) program, which is concerned with understanding of the mechanism of action (MoA) of toxins or drugs affecting human cells. Using a combination of Gaussian processes and abstract network modeling, we present three fundamentally different machine-learning-based approaches to learn causal relations and synthesize causal networks from high-dimensional time series data. While other types of data are available and have been analyzed and integrated in our RTA work, we focus on transcriptomics (that is gene expression) data obtained from high-throughput microarray experiments in this paper to illustrate capabilities and limitations of our algorithms. Our algorithms make different but overall relatively few biological assumptions, so that they are applicable to other types of biological data and potentially even to other complex systems that exhibit high dimensionality but are not of biological nature.

Domain adaptation provides a powerful set of model training techniques given domain-specific training data and supplemental data with unknown relevance. The techniques are useful when users need to develop models with data from varying sources, of varying quality, or from different time ranges. We build CrossTrainer, a system for practical domain adaptation. CrossTrainer utilizes loss reweighting, which provides consistently high model accuracy across a variety of datasets in our empirical analysis. However, loss reweighting is sensitive to the choice of a weight hyperparameter that is expensive to tune. We develop optimizations leveraging unique properties of loss reweighting that allow CrossTrainer to output accurate models while improving training time compared to naive hyperparameter search.

High-level synthesis (HLS) shortens the development time of hardware designs and enables faster design space exploration at a higher abstraction level. Optimization of complex applications in HLS is challenging due to the effects of implementation issues such as routing congestion. Routing congestion estimation is absent or inaccurate in existing HLS design methods and tools. Early and accurate congestion estimation is of great benefit to guide the optimization in HLS and improve the efficiency of implementation. However, routability, a serious concern in FPGA designs, has been difficult to evaluate in HLS without analyzing post-implementation details after Place and Route. To this end, we propose a novel method to predict routing congestion in HLS using machine learning and map the expected congested regions in the design to the relevant high-level source code. This is greatly beneficial in early identification of routability oriented bottlenecks in the high-level source code without running time-consuming register-transfer level (RTL) implementation flow. Experiments demonstrate that our approach accurately estimates vertical and horizontal routing congestion with errors of 6.71% and 10.05% respectively. By presenting Face Detection application as a case study, we show that by discovering the bottlenecks in high-level source code, routing congestion can be easily and quickly resolved compared to the efforts involved in RTL implementation and design feedback.