Deep Reinforcement Learning has enabled the control of increasingly complex and high-dimensional problems. However, the need of vast amounts of data before reasonable performance is attained prevents its widespread application. We employ binary corrective feedback as a general and intuitive manner to incorporate human intuition and domain knowledge in model-free machine learning. The uncertainty in the policy and the corrective feedback is combined directly in the action space as probabilistic conditional exploration. As a result, the greatest part of the otherwise ignorant learning process can be avoided. We demonstrate the proposed method, Predictive Probabilistic Merging of Policies (PPMP), in combination with DDPG. In experiments on continuous control problems of the OpenAI Gym, we achieve drastic improvements in sample efficiency, final performance, and robustness to erroneous feedback, both for human and synthetic feedback. Additionally, we show solutions beyond the demonstrated knowledge.

Lifted inference scales to large probability models by exploiting symmetry. However, existing exact lifted inference techniques do not apply to general factor graphs, as they require a relational representation. In this work we provide a theoretical framework and algorithm for performing exact lifted inference on symmetric factor graphs by computing colored graph automorphisms, as is often done for approximate lifted inference. Our key insight is to represent variable assignments directly in the colored factor graph encoding. This allows us to generate representatives and compute the size of each orbit of the symmetric distribution. In addition to exact inference, we use this encoding to implement an MCMC algorithm that explores the space of orbits quickly by uniform orbit sampling.

He has demanded "goddamned steam" to power the Navy's aircraft carriers and prefers a wall to drones and other technology to secure the country's southern border. He has rejected the scientific consensus on climate change and repeatedly, wrongly, pointed to occasional wintry weather as proof that he's right. And this week, amid a safety scare involving Boeing's 737 MAX 8 and MAX 9 airplanes, President Trump complained that modern jets are "too complex to fly." He added: "I see it all the time in many products. Always seeking to go one unnecessary step further, when often old and simpler is far better."

Siri, Alexa, Google Home--technology that parses language is increasingly finding its way into everyday life. Boris Katz, a principal research scientist at MIT, isn't that impressed. Over the past 40 years, Katz has made key contributions to the linguistic abilities of machines. In the 1980s, he developed START, a system capable of responding to naturally phrased queries. The ideas used in START helped IBM's Watson win on Jeopardy!

The Navy has previously said the LDUSVs might fill the role of "arsenal ships" packed with stand-off missiles to provide additional firepower for a surface task force. Rear Admiral Crites said that a vertical launch system capability would be one requirement for the LDUSV. Crites comment that these ships will also be "sensors" indicates that they could also pack capable and diverse sensors suites, potentially including those not necessary found on manned ships. Doing so would offer commanders increased situational awareness across a broad front. The Navy over-arching unmanned surface vessel plan has three tiers – small, medium, and large – and the service has been very clear in the past that it expected the medium-sized types to fill the requirement for unmanned scouts operating ahead of larger surface action groups.

C100, a non-profit that connects the Canadian and Silicon Valley startup ecosystems, has accepted 27 companies into the the 2019 cohort of its 48Hrs in the Valley program. The competitive annual program, which is referral-only, pairs Canadian companies with a mentor, then brings them to Silicon Valley for two days of meetings with investors and executives. This year's cohort will run from May 7 to 9. It includes eight firms from Toronto; five from Montreal and one from Laval, Que.; six from Vancouver; two apiece from Calgary and Ottawa; and one each from Halifax, Kitchener, Ont. and Waterloo. The program has been running since 2010. So far, over 250 companies have participated, many of which have gone on to raise money soon after their Silicon Valley visits.

Santa Clara based Hotify Inc, an Artificial Intelligence Platform as a Service (AI PaaS) company, announced it has joined the NVIDIA Inception program. The program is conducted by NVIDIA, a pioneer in 3D GPUs and AI Computing, to recognize exceptional startups in the Artificial Intelligence space. Hotify Inc is an Artificial Intelligence (AI) software company and is the developer of NuGene, a cognitive Automation platform which can be used to develop fast and robust Intelligence Agents (Bots) in minutes. The selection of Hotify involved multiple rounds of information exchange including telephonic interaction. "We are happy to become part of this program. Working closely with NVIDIA shall help us in building AI Platform for scale. Getting selected in this program also is a good validation of our focus, approach and offerings. We aim to gain from early developers access of NVIDIA technology, their Go to Market help and vast knowledge repository," said Chinmay Joshi, Co-Founder, VP Product & Engineering, Hotify.

Both developing babies and elderly adults share a common characteristic: the many cells making up their bodies are always on the move. As we humans commute to work, cells migrate through the body to get their jobs done. Biologists have long struggled to quantify the movement and changing morphology of cells through time, but now, scientists at the Okinawa Institute of Science and Technology Graduate University (OIST) have devised an elegant tool to do just that. Using machine learning, the researchers designed a software to analyze microscopic snapshots of migrating cells. They named the software Usiigaci, a Ryukyuan word that refers to tracing the outlines of objects, as the innovative tool detects the changing outlines of individual cells.

Cleveland Clinic has launched a center to advance the use of artificial intelligence (AI) in healthcare. The Center for Clinical Artificial Intelligence will focus on developing innovative clinical applications of AI and leveraging machine-learning technology in hopes of improving healthcare delivery in areas such as diagnostics, disease prediction and treatment planning, according to a news release. Launched by Cleveland Clinic Enterprise Analytics, the center aims to foster collaboration and communication between physicians, researchers and data-scientists; offer programmatic and technology support for AI initiatives at the Clinic; and conduct research in several areas of medicine, according to the release. "Cleveland Clinic has formed the Center for Clinical Artificial Intelligence to translate AI-based concepts into clinical tools that will improve patient care and advance medical research," said Dr. Aziz Nazha, director of the new center and associate medical director for AI, in a prepared statement. The center will facilitate collaboration among physicians, researchers, computer scientists and statisticians across the United States and around the world, as well as between academia and industry, to advance the application of AI in healthcare.

AngelPad just wrapped the 12th run of its months-long New York City startup accelerator. For the second time, the program didn't culminate in a demo day; rather, the 19 participating startups were given pre-arranged one-on-one meetings with venture capital investors late last week. AngelPad co-founders Thomas Korte and Carine Magescas did away with the demo day tradition last year after nearly a decade operating AngelPad, which is responsible for mentoring startups including Postmates, Twitter-acquired Mopub, Pipedrive, Periscope Data, Zum and DroneDeploy. "Demo days are great ways for accelerators to expose a large number of companies to a lot of investors, but we don't think it is the most productive way," Korte told TechCrunch last year. Competing accelerator Y Combinator has purportedly considered their eliminating demo day as well, though sources close to YC deny this.