We develop a framework to solve machine learning problems in cases where latent geometric structure in the feature space may be exploited. We consider cases where the number of training examples is either very large, or signals are sequentially observed by a platform operating in real-time such as an autonomous robot. In the former case, since the sample size is large-scale, processing a few training examples at a time is necessary due to computational cost. However, doing so at a centralized location may be impractical, which motivates the use of learning techniques that may be done collaboratively by a network of interconnected computing servers. In the later case, an autonomous robot with no priors on its operating environment only has access to information based on the path it has traversed, which may omit regions of the feature space crucial for tasks such as learning-based control. By communicating with other robots in a network, individuals may learn over a broader domain associated with that which has been explored by the whole network, and thus more effectively solve autonomous learning tasks.

Last year blockchain became one of the hottest topics in the world even much outside IT community. We saw a booming growth in the number of startups; large banks and even governments started investing in researching the technology. So definitely, there is much buzz about the topic, but seemingly it has nothing to do with machine learning and artificial intelligence. While articles and news on artificial intelligence as compared to blockchain and other cryptoworld topics are in no less degree blossoming these days, everybody keep silent on possible synergic implications in these truly breakthrough fields of computer science. At BICA Labs we do see a strong synergy between blockchain and AI – a synergy that goes much beyond just an applied science.

We present algorithms to effectively represent a set of Markov decision processes (MDPs), whose optimal policies have already been learned, by a smaller source subset for lifelong, policy-reuse-based transfer learning in reinforcement learning. This is necessary when the number of previous tasks is large and the cost of measuring similarity counteracts the benefit of transfer. The source subset forms an `$\epsilon$-net' over the original set of MDPs, in the sense that for each previous MDP $M_p$, there is a source $M^s$ whose optimal policy has $<\epsilon$ regret in $M_p$. Our contributions are as follows. We present EXP-3-Transfer, a principled policy-reuse algorithm that optimally reuses a given source policy set when learning for a new MDP. We present a framework to cluster the previous MDPs to extract a source subset. The framework consists of (i) a distance $d_V$ over MDPs to measure policy-based similarity between MDPs; (ii) a cost function $g(\cdot)$ that uses $d_V$ to measure how good a particular clustering is for generating useful source tasks for EXP-3-Transfer and (iii) a provably convergent algorithm, MHAV, for finding the optimal clustering. We validate our algorithms through experiments in a surveillance domain.

Vice President Joe Biden will push for international cooperation in the fight against cancer in a speech at the Vatican. The vice president's office says the address on Friday will look at global research partnerships and will describe how his cancer "moonshot" project may have an international impact. Biden is due to speak at an international conference on breakthroughs in regenerative medicine. The gathering of doctors, patients and researchers is hosted by the Pontifical Council for Culture and the Stem for Life Foundation. Biden's office says the vice president will visit with Pope Francis during the stop.

In professional cycling, it's well known that a pack of 40 or 50 riders can ride faster and more efficiently than a single rider or small group. As such, you'll often see cycling teams with different goals in a race work together to chase down a breakaway before the finish line. This analogy is one way to think about collaborative multi-agent intelligent systems, which are poised to change the technology landscape for individuals, businesses, and governments, says Dr. Mehdi Dastani, a computer scientist at Utrecht University. The proliferation of these multi-agent systems could lead to significant systemic changes across society in the next decade. "Multi-agent systems are basically a kind of distributed system with sets of software. A set can be very large. They are autonomous, they make their own decisions, they can perceive their environment, "Dastani said.

Human patrols serve as the most direct form of protection of endangered animals, especially in large national parks. However, protection agencies have limited resources for patrols. With support from the National Science Foundation (NSF) and the Army Research Office, researchers are using artificial intelligence (AI) and game theory to solve poaching, illegal logging and other problems worldwide, in collaboration with researchers and conservationists in the U.S., Singapore, Netherlands and Malaysia. "In most parks, ranger patrols are poorly planned, reactive rather than pro-active, and habitual," according to Fei Fang, a Ph.D. candidate in the computer science department at the University of Southern California (USC). Fang is part of an NSF-funded team at USC led by Milind Tambe, professor of computer science and industrial and systems engineering and director of the Teamcore Research Group on Agents and Multiagent Systems.

A century ago, more than 60,000 tigers roamed the wild. Today, the worldwide estimate has dwindled to around 3,200. Poaching is one of the main drivers of this precipitous drop. Whether killed for skins, medicine or trophy hunting, humans have pushed tigers to near-extinction. The same applies to other large animal species like elephants and rhinoceros that play unique and crucial roles in the ecosystems where they live.

A century ago, more than 60,000 tigers roamed the wild. Today, the worldwide estimate has dwindled to around 3,200. Poaching is one of the main drivers of this precipitous drop. Whether killed for skins, medicine or trophy hunting, humans have pushed tigers to near-extinction. The same applies to other large animal species like elephants and rhinoceros that play unique and crucial roles in the ecosystems where they live.

As the world celebrated Earth Day on Friday, a team led by an Indian-origin researcher has found a way to use artificial intelligence (AI) to protect the Earth's endangered animals and forests by outwitting poachers with technology. With support from the US National Science Foundation (NSF) and the US Army Research Office, researchers are using AI and game theory to solve poaching, illegal logging and other problems worldwide, in collaboration with researchers and conservationists in the US, Singapore, the Netherlands and Malaysia. "This research is a step in demonstrating that AI can have a really significant positive impact on society and allow us to assist humanity in solving some of the major challenges we face," said Milind Tambe, professor of computer science and industrial and systems engineering at the University of Southern California (USC). "In most parks, ranger patrols are poorly planned, reactive rather than pro-active and habitual," said Fei Fang, PhD candidate from the University of Southern California (USC). Fang is part of an NSF-funded team at USC led by Tambe who is also director of the Teamcore Research Group on Agents and Multiagent Systems.

As the world celebrated Earth Day on Friday, a team led by an Indian-origin researcher has found a way to use artificial intelligence (AI) to protect the Earth's endangered animals and forests by outwitting poachers with technology. With support from the US National Science Foundation (NSF) and the US Army Research Office, researchers are using AI and game theory to solve poaching, illegal logging and other problems worldwide, in collaboration with researchers and conservationists in the US, Singapore, the Netherlands and Malaysia. "This research is a step in demonstrating that AI can have a really significant positive impact on society and allow us to assist humanity in solving some of the major challenges we face," said Milind Tambe, professor of computer science and industrial and systems engineering at the University of Southern California (USC). "In most parks, ranger patrols are poorly planned, reactive rather than pro-active and habitual," said Fei Fang, PhD candidate from the University of Southern California (USC). Fang is part of an NSF-funded team at USC led by Tambe who is also director of the Teamcore Research Group on Agents and Multiagent Systems.