De-An Huang 1, 2, Y u-Wei Chao, 2, Chris Paxton, 2, Xinke Deng 2, 3, Li Fei-Fei 1, Juan Carlos Niebles 1, Animesh Garg 2, 4, Dieter Fox 2, 5 Abstract -- We address goal-based imitation learning, where the aim is to output the symbolic goal from a third-person video demonstration. This enables the robot to plan for execution and reproduce the same goal in a completely different environment. The key challenge is that the goal of a video demonstration is often ambiguous at the level of semantic actions. The human demonstrators might unintentionally achieve certain subgoals in the demonstrations with their actions. Our main contribution is to propose a motion reasoning framework that combines task and motion planning to disambiguate the true intention of the demonstrator in the video demonstration. This allows us to robustly recognize the goals that cannot be disambiguated by previous action-based approaches. We evaluate our approach by collecting a dataset of 96 video demonstrations in a mockup kitchen environment. We show that our motion reasoning plays an important role in recognizing the actual goal of the demonstrator and improves the success rate by over 20%. We further show that by using the automatically inferred goal from the video demonstration, our robot is able to reproduce the same task in a real kitchen environment. I NTRODUCTION We are interested in allowing robots to learn new tasks from video demonstrations. Recently, there has been rapid progress in imitation learning [1-4], which even enables learning a new task from a single demonstration of the task [5-7]. By leveraging meta-learning [8], the robot learns to follow the actions in the demonstration.

The research in hierarchical planning has made considerable progress in the last few years. Many recent systems do not rely on hand-tailored advice anymore to find solutions, but are supposed to be domain-independent systems that come with sophisticated solving techniques. In principle, this development would make the comparison between systems easier (because the domains are not tailored to a single system anymore) and -- much more important -- also the integration into other systems, because the modeling process is less tedious (due to the lack of advice) and there is no (or less) commitment to a certain planning system the model is created for. However, these advantages are destroyed by the lack of a common input language and feature set supported by the different systems. In this paper, we propose an extension to PDDL, the description language used in non-hierarchical planning, to the needs of hierarchical planning systems. We restrict our language to a basic feature set shared by many recent systems, give an extension of PDDL's EBNF syntax definition, and discuss our extensions with respect to several planner-specific input languages from related work.

Chronic disease progression is emerging as an important area of investment for healthcare providers. As the quantity and richness of available clinical data continue to increase along with advances in machine learning, there is great potential to advance our approaches to caring for patients. An ideal approach to this problem should generate good performance on at least three axes namely, a) perform across many clinical conditions without requiring deep clinical expertise or extensive data scientist effort, b) generalization across populations, and c) be explainable (model interpretability). We present SAVEHR, a self-attention based architecture on heterogeneous structured EHR data that achieves $>$ 0.51 AUC-PR and $>$ 0.87 AUC-ROC gains on predicting the onset of four clinical conditions (CHF, Kidney Failure, Diabetes and COPD) 15-months in advance, and transfers with high performance onto a new population. We demonstrate that SAVEHR model performs superior to ten baselines on all three axes stated formerly.

Learning from offline task demonstrations is a problem of great interest in robotics. For simple short-horizon manipulation tasks with modest variation in task instances, offline learning from a small set of demonstrations can produce controllers that successfully solve the task. However, leveraging a fixed batch of data can be problematic for larger datasets and longer-horizon tasks with greater variations. The data can exhibit substantial diversity and consist of suboptimal solution approaches. In this paper, we propose Implicit Reinforcement without Interaction at Scale (IRIS), a novel framework for learning from large-scale demonstration datasets. IRIS factorizes the control problem into a goal-conditioned low-level controller that imitates short demonstration sequences and a high-level goal selection mechanism that sets goals for the low-level and selectively combines parts of suboptimal solutions leading to more successful task completions. We evaluate IRIS across three datasets, including the RoboTurk Cans dataset collected by humans via crowdsourcing, and show that performant policies can be learned from purely offline learning. Additional results and videos at https://stanfordvl.github.io/iris/ .

Reconstructing components of a genomic mixture from data obtained by means of DNA sequencing is a challenging problem encountered in a variety of applications including single individual haplotyping and studies of viral communities. High-throughput DNA sequencing platforms oversample mixture components to provide massive amounts of reads whose relative positions can be determined by mapping the reads to a known reference genome; assembly of the components, however, requires discovery of the reads' origin -- an NP-hard problem that the existing methods struggle to solve with the required level of accuracy. In this paper, we present a learning framework based on a graph auto-encoder designed to exploit structural properties of sequencing data. The algorithm is a neural network which essentially trains to ignore sequencing errors and infers the posteriori probabilities of the origin of sequencing reads. Mixture components are then reconstructed by finding consensus of the reads determined to originate from the same genomic component. Results on realistic synthetic as well as experimental data demonstrate that the proposed framework reliably assembles haplotypes and reconstructs viral communities, often significantly outperforming state-of-the-art techniques.

Given a stream of graph edges from a dynamic graph, how can we assign anomaly scores to edges in an online manner, for the purpose of detecting unusual behavior, using constant time and memory? Existing approaches aim to detect individually surprising edges. In this work, we propose MIDAS, which focuses on detecting microcluster anomalies, or suddenly arriving groups of suspiciously similar edges, such as lockstep behavior, including denial of service attacks in network traffic data. MIDAS has the following properties: (a) it detects microcluster anomalies while providing theoretical guarantees about its false positive probability; (b) it is online, thus processing each edge in constant time and constant memory, and also processes the data 108-505 times faster than state-of-the-art approaches; (c) it provides 46%-52% higher accuracy (in terms of AUC) than state-of-the-art approaches.

Microsoft's big experiment in real-world augmented reality gaming, Minecraft Earth, is live now for players in North America, the U.K., and a number of other areas. The pocket-size AR game lets you collect blocks and critters wherever you go, undertake little adventures with friends, and of course build sweet castles. I played an early version of Minecraft Earth earlier this year, and found it entertaining and the AR aspect surprisingly seamless. The gameplay many were first introduced to in Pokemon GO is adapted here in a more creative and collaborative way. You still walk around your neighborhood, rendered in this case charmingly like a Minecraft world, and tap little icons that pop up around your character. These may be blocks you can use to build, animals you can collect, or events like combat encounters that you can do alone or with friends for rewards.

Microsoft's big experiment in real-world augmented reality gaming, Minecraft Earth, is live now for players in North America, the U.K., and a number of other areas. The pocket-size AR game lets you collect blocks and critters wherever you go, undertake little adventures with friends, and of course build sweet castles. I played an early version of Minecraft Earth earlier this year, and found it entertaining and the AR aspect surprisingly seamless. The gameplay many were first introduced to in Pokemon GO is adapted here in a more creative and collaborative way. You still walk around your neighborhood, rendered in this case charmingly like a Minecraft world, and tap little icons that pop up around your character. These may be blocks you can use to build, animals you can collect, or events like combat encounters that you can do alone or with friends for rewards.

Let's look at the latest face of automation - the good, the bad, and the ugly! It solves some of today's problems and is starting to create new ones. Find out if your job is at risk .of My books on Amazon: The Little Book of Fundamental Indicators: Hands-On Market Analysis with Python: Find Your Market Bearings with Python, Jupyter Notebooks, and Freely Available Data: https://amzn.to/2DERG3d Create Income Streams with Online Classes: Design Classes That Generate Long-Term Revenue: https://amzn.to/2VToEHK

Two of the largest drugmakers in the country are investing in a startup applying artificial intelligence in pathology. Boston-based PathAI said that it had closed its $75 million Series B financing round with funding from New York-based Bristol-Myers Squibb and the Merck Global Health Innovation Fund, part of Kenilworth, New Jersey-based Merck & Co. PathAI said it would use the money to bolster its clinical development capabilities. PathAI had announced its $60 million Series B financing its April, led by venture capital firms General Atlantic and General Catalyst, with participation from LabCorp, which the company said the latest investment follows and extends.