Skills learned through (deep) reinforcement learning often generalizes poorly across domains and re-training is necessary when presented with a new task. We present a framework that combines techniques in \textit{formal methods} with \textit{reinforcement learning} (RL). The methods we provide allows for convenient specification of tasks with logical expressions, learns hierarchical policies (meta-controller and low-level controllers) with well-defined intrinsic rewards, and construct new skills from existing ones with little to no additional exploration. We evaluate the proposed methods in a simple grid world simulation as well as a more complicated kitchen environment in AI2Thor

We propose a new algorithm to learn a one-hidden-layer convolutional neural network where both the convolutional weights and the outputs weights are parameters to be learned. Our algorithm works for a general class of (potentially overlapping) patches, including commonly used structures for computer vision tasks. Our algorithm draws ideas from (1) isotonic regression for learning neural networks and (2) landscape analysis of non-convex matrix factorization problems. We believe these findings may inspire further development in designing provable algorithms for learning neural networks and other complex models.

Developing a safe and efficient collision avoidance policy for multiple robots is challenging in the decentralized scenarios where each robot generate its paths without observing other robots' states and intents. While other distributed multi-robot collision avoidance systems exist, they often require extracting agent-level features to plan a local collision-free action, which can be computationally prohibitive and not robust. More importantly, in practice the performance of these methods are much lower than their centralized counterparts. We present a decentralized sensor-level collision avoidance policy for multi-robot systems, which directly maps raw sensor measurements to an agent's steering commands in terms of movement velocity. As a first step toward reducing the performance gap between decentralized and centralized methods, we present a multi-scenario multi-stage training framework to find an optimal policy which is trained over a large number of robots on rich, complex environments simultaneously using a policy gradient based reinforcement learning algorithm. We validate the learned sensor-level collision avoidance policy in a variety of simulated scenarios with thorough performance evaluations and show that the final learned policy is able to find time efficient, collision-free paths for a large-scale robot system. We also demonstrate that the learned policy can be well generalized to new scenarios that do not appear in the entire training period, including navigating a heterogeneous group of robots and a large-scale scenario with 100 robots. Videos are available at https://sites.google.com/view/drlmaca

We introduce a new multi-dimensional nonlinear embedding -- Piecewise Flat Embedding (PFE) -- for image segmentation. Based on the theory of sparse signal recovery, piecewise flat embedding with diverse channels attempts to recover a piecewise constant image representation with sparse region boundaries and sparse cluster value scattering. The resultant piecewise flat embedding exhibits interesting properties such as suppressing slowly varying signals, and offers an image representation with higher region identifiability which is desirable for image segmentation or high-level semantic analysis tasks. We formulate our embedding as a variant of the Laplacian Eigenmap embedding with an $L_{1,p} (0

The ubiquitous complex networks are often composed of regular and irregular components, which makes uncovering the complexity of network structure into a fundamental challenge in network science. Exploring the regular information and identifying the roles of microscopic elements in network organization can help practitioners to recognize the universal principles of network formation and facilitate network data mining.Despite many algorithms having been proposed for link prediction and network reconstruction, estimating and regulating the reconstructability of complex networks remains an inadequately explored problem. With the practical assumption that there has consistence between local structures of networks and the corresponding adjacency matrices are approximately low rank, we obtain a self-representation network model in which the organization principles of networks are captured by representation matrix. According to the model, original networks can be reconstructed based on observed structure. What's more, the model enables us to estimate to what extent networks are regulable, in other words, measure the reconstructability of complex networks. In addition, the model enables us to measure the importance of network links for network regularity thereby allowing us to regulate the reconstructability of networks. The extensive experiments on disparate networks demonstrate the effectiveness of the proposed algorithm and measure. Specifically, the structural regularity reflects the reconstructability of networks, and the reconstruction accuracy can be promoted via the deleting of irregular network links independent of specific algorithms.

Interpretability has become an important issue in the machine learning field, along with the success of layered neural networks in various practical tasks. Since a trained layered neural network consists of a complex nonlinear relationship between large number of parameters, we failed to understand how they could achieve input-output mappings with a given data set. In this paper, we propose the non-negative task decomposition method, which applies non-negative matrix factorization to a trained layered neural network. This enables us to decompose the inference mechanism of a trained layered neural network into multiple principal tasks of input-output mapping, and reveal the roles of hidden units in terms of their contribution to each principal task.

Concertgoers will soon live in their own personalized version of hell above and beyond the Ticketmaster convenience fee. Live Nation, Ticketmaster's parent company, recently announced a pilot program to ditch tickets in favor of advanced facial recognition technology. For the pilot, Ticketmaster partnered with Blink Identity, a Texas-based biometric company that previously worked to implement biometric security programs in both Afghanistan and Iraq. The company claims it can make a positive ID in "half a second," even if those being scanned aren't looking directly at its cameras. Once scanned, the system flies through a potential database of tens (or hundreds) of thousands of attendees in an attempt to make a positive ID.

Two words you'll have heard a lot of over the past year or so. It's been such a popular term that it even made Word of the Year for 2017. But there is a much more to it than being a large part of Trump's vocabulary. This is a'uge problem that needs to be addressed and tackled. So, what is it then?

Leslie D'Monte is a journalist with over two decades of experience, specializing in technology and science editing and writing. He has worked with leading media groups like HT Media Ltd. (Mint), Business Standard, The Times of India, The Indian Express, Jasubhai Media group and ZdNet India, both as a reporter and editor. Leslie is currently the National Technology Editor of Mint, the business publication of HT Media Ltd, and also a part of Mint's Leadership team. Leslie talks about the rebirth of artificial intelligence and gives his take on what impacts it is going to have on life as we know it. He also addresses some myths surrounding AI and machine learning.

Yet the four-year-old firm has become Japan's most valuable startup, with a venture capital funding that priced it at more than $2 billion, according to people familiar with the matter. Toyota Motor Corp., its biggest backer, handed over $110 million on a bet its algorithms will help them compete with Google in driverless cars. Last February, Prime Minister Shinzo Abe posed for pictures with the firm's two young founders at his office, where they were awarded a prize for promising new ventures.