Most structure inference methods either rely on exhaustive search or are purely data-driven. Exhaustive search robustly infers the structure of arbitrarily complex data, but it is slow. Data-driven methods allow efficient inference, but do not generalize when test data have more complex structures than training data. In this paper, we propose a hybrid inference algorithm, the Neurally-Guided Structure Inference (NG-SI), keeping the advantages of both search-based and data-driven methods. The key idea of NG-SI is to use a neural network to guide the hierarchical, layer-wise search over the compositional space of structures. We evaluate our algorithm on two representative structure inference tasks: probabilistic matrix decomposition and symbolic program parsing. It outperforms data-driven and search-based alternatives on both tasks.

We describe a novel extension of soft actor-critics for hierarchical Deep Q-Networks (HDQN) architectures using mutual information metric. The proposed extension provides a suitable framework for encouraging explorations in such hierarchical networks. A natural utilization of this framework is an adversarial setting, where meta-controller and controller play minimax over the mutual information objective but cooperate on maximizing expected rewards.

We build a theoretical framework for understanding practical meta-learning methods that enables the integration of sophisticated formalizations of task-similarity with the extensive literature on online convex optimization and sequential prediction algorithms. Our approach enables the task-similarity to be learned adaptively, provides sharper transfer-risk bounds in the setting of statistical learning-to-learn, and leads to straightforward derivations of average-case regret bounds for efficient algorithms in settings where the task-environment changes dynamically or the tasks share a certain geometric structure. We use our theory to modify several popular meta-learning algorithms and improve their training and meta-test-time performance on standard problems in few-shot and federated deep learning.

Learning high-quality node embeddings is a key building block for machine learning models that operate on graph data, such as social networks and recommender systems. However, existing graph embedding techniques are unable to cope with fairness constraints, e.g., ensuring that the learned representations do not correlate with certain attributes, such as age or gender. Here, we introduce an adversarial framework to enforce fairness constraints on graph embeddings. Our approach is compositional---meaning that it can flexibly accommodate different combinations of fairness constraints during inference. For instance, in the context of social recommendations, our framework would allow one user to request that their recommendations are invariant to both their age and gender, while also allowing another user to request invariance to just their age. Experiments on standard knowledge graph and recommender system benchmarks highlight the utility of our proposed framework.

The University of South Carolina announced plans last week to open an artificial intelligence institute that give students and faculty a shared space for interdisciplinary collaboration. The institute, which the university hopes to have running by this fall, will focus on research to advance AI applications across a wide range of industries, Hossein Haj-Hariri, dean of the College of Engineering and Computing, told EdScoop. "[Industries] are already being transformed or will be transformed by artificial intelligence," Haj-Hariri said. "The window where we can really lead the injection of research into application areas is open," he said. To drive innovation and develop cutting-edge solutions using AI, the institute will draw on the knowledge and experience of students and faculty from all 15 colleges across the university's campus, making it a hub for interdisciplinary collaboration.

For technology investors, artificial intelligence (AI) is the next frontier. And for good reason, as Accenture finds investments in AI will turbocharge the economy, boosting productivity in the U.S. by more than a third and nearly doubling GDP growth rates. Early-stage AI investors are in a key position for multidecade returns. We asked a trio of our Motley Fool contributors to highlight three companies well poised to take advantage of AI's growth. Anders Bylund (IBM): With $78.7 billion of trailing revenues and $17.7 billion in EBITDA profits, IBM is an instant giant in pretty much any niche it decides to address.

Ready to make an impact on the global automation revolution? McKinsey Global Institute ranked "automation of knowledge" work as #2 in their top 12 disruptive technologies that will transform life, business, and the global economy. Automation Anywhere is the market leader in driving the adoption of robotic process automation technology across leading Fortune 1000 and other companies across more than 90 countries. At Automation Anywhere, we are passionate in our belief that Digital Colleagues will free people to create, think, discover, and ultimately build great companies. As a Key Account Manager, you have a proven sales record of successful software sales to the largest Enterprises.

ARTIFICIAL intelligence (AI) has already changed some activities, including parts of finance like fraud prevention, but not yet fund management and stock-picking. That seems odd: machine learning, a subset of AI that excels at finding patterns and making predictions using reams of data, looks like an ideal tool for the business. Yet well-established "quant" hedge funds in London or New York are often sniffy about its potential. In San Francisco, however, where machine learning is so much part of the furniture the term features unexplained on roadside billboards, a cluster of upstart hedge funds has sprung up in order to exploit these techniques. These new hedgies are modest enough to concede some of their competitors' points.

Researchers at the University of Washington plan to release their AI algorithm – GROVER -- that they say can generate extremely convincing, text-based fake news. The system is also able to write in the style of highly respected publications like The New York Times, The Washington Post and Wired. Researchers say their motivation for releasing the algorithm is to alert the public that such technology can be easily created and deployed. Data journalists formulate the appropriate story templates, and human editors review each story, according to Jason Hwang, head of partnerships, Hoodline. Essentially, they want AI-generated writing to be more human.

The challenge to analyze earthquake signals with optimum precision grows along with the amount of available seismic data. At the Karlsruhe Institute of Technology (KIT), researchers have deployed a neural network to determine the arrival-time of seismic waves and thus precisely locate the epicenter of the earthquake. In their report in the Seismological Research Letters journal, they point out that Artificial Intelligence is able to evaluate the data with the same precision as an experienced seismologist. For precisely locating an earthquake event, it is critical to determine the exact arrival-time of the majority of seismic waves at the seismometer station (the so-called phase arrival). Without this knowledge, further accurate seismological evaluations are not possible.