We study the problem of generating interpretable and verifiable policies through reinforcement learning. Unlike the popular Deep Reinforcement Learning (DRL) paradigm, in which the policy is represented by a neural network, the aim in Programmatically Interpretable Reinforcement Learning is to find a policy that can be represented in a high-level programming language. Such programmatic policies have the benefits of being more easily interpreted than neural networks, and being amenable to verification by symbolic methods. We propose a new method, called Neurally Directed Program Search (NDPS), for solving the challenging nonsmooth optimization problem of finding a programmatic policy with maxima reward. NDPS works by first learning a neural policy network using DRL, and then performing a local search over programmatic policies that seeks to minimize a distance from this neural "oracle". We evaluate NDPS on the task of learning to drive a simulated car in the TORCS car-racing environment. We demonstrate that NDPS is able to discover human-readable policies that pass some significant performance bars. We also find that a well-designed policy language can serve as a regularizer, and result in the discovery of policies that lead to smoother trajectories and are more easily transferred to environments not encountered during training.

We address the problem of image translation between domains or modalities for which no direct paired data is available (i.e. zero-pair translation). We propose mix and match networks, based on multiple encoders and decoders aligned in such a way that other encoder-decoder pairs can be composed at test time to perform unseen image translation tasks between domains or modalities for which explicit paired samples were not seen during training. We study the impact of autoencoders, side information and losses in improving the alignment and transferability of trained pairwise translation models to unseen translations. We show our approach is scalable and can perform colorization and style transfer between unseen combinations of domains. We evaluate our system in a challenging cross-modal setting where semantic segmentation is estimated from depth images, without explicit access to any depth-semantic segmentation training pairs. Our model outperforms baselines based on pix2pix and CycleGAN models.

Simulating the time-evolution of quantum mechanical systems is BQP-hard and expected to be one of the foremost applications of quantum computers. We consider the approximation of Hamiltonian dynamics using subsampling methods from randomized numerical linear algebra. We propose conditions for the efficient approximation of state vectors evolving under a given Hamiltonian. As an immediate application, we show that sample based quantum simulation, a type of evolution where the Hamiltonian is a density matrix, can be efficiently classically simulated under specific structural conditions. Our main technical contribution is a randomized algorithm for approximating Hermitian matrix exponentials. The proof leverages the Nystr\"om method to obtain low-rank approximations of the Hamiltonian. We envisage that techniques from randomized linear algebra will bring further insights into the power of quantum computation.

Google is betting that algorithms that understand images and text will draw business to its cloud services, make augmented reality popular, and prompt us to search using our smartphone cameras. From a report: The search company's machine learning systems work best on material from a few rich parts of the world, like the US. They stumble more frequently on data from less affluent countries -- particularly emerging economies like India that Google is counting on to maintain its growth. "We have a very sparse training data set from parts of the world that are not the United States and Western Europe," says Anurag Batra, a researcher at Google. When Batra travels to his native Delhi, he says Google's AI systems become less smart.

Netflix has released hundreds of Originals and plans to spend $8 billion over the next year on content. Creators of these stories pour their hearts and souls into turning ideas into joy for our viewers. The sublime art of doing this well is hard to describe, but it necessitates a careful orchestration of creative, business and technical decisions. Here we will focus on the latter two -- business & technical decisions like planning budgets, finding locations, building sets, and scheduling guest actors that enable the creative act of connecting with viewers. Each production is a mountain of operational and logistical challenges that consumes and produces tremendous amounts of data.

At 48 years old, Kersti Kaljulaid is Estonia's youngest president ever, and its first female president. A marathon runner with degrees in genetics and an MBA, she spent a career behind the scenes--mostly as a European government auditor--before being elected by Estonia's legislature in 2016. Known for its digital government, tax, and medical systems, Estonia is planning for the future. The country's "e-resident" program--which allows global citizens to obtain a government-issued ID card and set up remotely-operated businesses in Estonia--has attracted 35,000 people since 2014. Now the government is discussing a proposal to grant some rights to artificially intelligent systems.

The developments in Google's Cloud Computing segment, especially the Cloud Machine Learning service, have been so rapid that Google calls it one of its fastest growing product areas. Google has been ramping up their Cloud Platform quite aggressively in recent months. Just a few weeks ago, the Google Cloud Platform opened its newest zone in Tokyo, increasing the total number of regions they are present in to six - three in the US and one each in Belgium and Taiwan and Tokyo. Not long ago, the company announced its acquisition of Orbitera, a cloud commerce company. The developments in Google's Cloud Computing segment, especially the Cloud Machine Learning service, have been so rapid that Google calls it one of its fastest growing product areas.

Smart algorithms have taken Google a long way. They helped the company dominate search and create the first software to conquer the complex board game Go. Now the company is betting that algorithms that understand images and text will draw business to its cloud services, make augmented reality popular, and prompt us to search using our smartphone cameras. But some of the algorithms Google is staking its future on aren't equally smart everywhere. The search company's machine learning systems work best on material from a few rich parts of the world, like the US.

WMG at the University of Warwick in the UK has unveiled its new Centre for Applied Artificial Intelligence, which has been conceived to enable industry and business to gain competitive insights through artificial intelligence (AI) by leveraging large volumes of digital information. This new center brings together several applied areas of activity where WMG (Warwick Manufacturing Group) has an established track record of excellence, including transport, manufacturing and digital healthcare, and will support the continued expansion of existing research groups in response to UK industrial needs. Prof. Giovanni Montana and Prof. Mehrdad Dianati will head the center in close collaboration with other academic colleagues in intelligent vehicles, the WMG Cyber Security Centre, and the Institute of Digital Healthcare. Prof. Dianati from Intelligent Vehicles (IV) Research at WMG said, "I embrace the challenges to be overcome before fully autonomous vehicles move from concept to commercialization – this includes technical solutions, which will enable safe, efficient and secure connected autonomous vehicles. These are critical factors for ensuring consumer acceptance of autonomous vehicles. "WMG hosts a wide range of unique IV research facilities and [is]internationally renowned for its research in this area.

SEATTLE, April 05, 2018 (GLOBE NEWSWIRE) -- Applexus Technologies, a full-service business and technology solutions company based in the Seattle area, announced the launch of a new Artificial Intelligence (AI) practice to provide AI software and services to clients. The newly launched team is part of Applexus Product and Innovation. The new practice supports a wide variety of AI services and solutions, through custom and packaged solutions, using emerging technologies such as deep learning, machine learning and big data analysis. The Applexus Chief Technologist and AI practice leader is Dr. Thomas Koickal, one of the longest-serving global practitioners of machine learning based technologies. His career of more than 20 years has included work at the University of Edinburgh, UK and Vikram Sarabhai Space Centre, a research center of the Indian Space Research Organization.