Reinforcement learning methods have been used to compute dialog policies from language-based interaction experiences. Efficiency is of particular importance in dialog policy learning, because of the considerable cost of interacting with people, and the very poor user experience from low-quality conversations. Aiming at improving the efficiency of dialog policy learning, we develop algorithm LHUA (Learning with Hindsight, User modeling, and Adaptation) that, for the first time, enables dialog agents to adaptively learn with hindsight from both simulated and real users. Simulation and hindsight provide the dialog agent with more experience and more (positive) reinforcements respectively. Experimental results suggest that, in success rate and policy quality, LHUA outperforms competitive baselines from the literature, including its no-simulation, no-adaptation, and no-hindsight counterparts.

Automated person re-identification in a multi-camera surveillance setup is very important for effective tracking and monitoring crowd movement. In the recent years, few deep learning based re-identification approaches have been developed which are quite accurate but time-intensive, and hence not very suitable for practical purposes. In this paper, we propose an efficient hierarchical re-identification approach in which color histogram based comparison is first employed to find the closest matches in the gallery set, and next deep feature based comparison is carried out using Siamese network. Reduction in search space after the first level of matching helps in achieving a fast response time as well as improving the accuracy of prediction by the Siamese network by eliminating vastly dissimilar elements. A silhouette part-based feature extraction scheme is adopted in each level of hierarchy to preserve the relative locations of the different body structures and make the appearance descriptors more discriminating in nature. The proposed approach has been evaluated on five public data sets and also a new data set captured by our team in our laboratory. Results reveal that it outperforms most state-of-the-art approaches in terms of overall accuracy.

Learning-based techniques are increasingly effective at controlling complex systems using data-driven models. However, most work done so far has focused on learning individual tasks or control laws. Hence, it is still a largely unaddressed research question how multiple tasks can be learned efficiently and simultaneously on the same system. In particular, no efficient state space exploration schemes have been designed for multi-task control settings. Using this research gap as our main motivation, we present an algorithm that approximates the smallest data set that needs to be collected in order to achieve high control performance for multiple learning-based control laws. We describe system uncertainty using a probabilistic Gaussian process model, which allows us to quantify the impact of potentially collected data on each learning-based controller. We then determine the optimal measurement locations by solving a stochastic optimization problem approximately. We show that, under reasonable assumptions, the approximate solution converges towards that of the exact problem. Additionally, we provide a numerical illustration of the proposed algorithm.

An important goal in reinforcement learning is to create agents that can quickly adapt to new goals while avoiding situations that might cause damage to themselves or their environments. One way agents learn is through exploration mechanisms, which are needed to discover new policies. However, in deep reinforcement learning, exploration is normally done by injecting noise in the action space. While performing well in many domains, this setup has the inherent risk that the noisy actions performed by the agent lead to unsafe states in the environment. Here we introduce a novel approach called Meta-Learned Instinctual Networks (MLIN) that allows agents to safely learn during their lifetime while avoiding potentially hazardous states. At the core of the approach is a plastic network trained through reinforcement learning and an evolved "instinctual" network, which does not change during the agent's lifetime but can modulate the noisy output of the plastic network. We test our idea on a simple 2D navigation task with no-go zones, in which the agent has to learn to approach new targets during deployment. MLIN outperforms standard meta-trained networks and allows agents to learn to navigate to new targets without colliding with any of the no-go zones. These results suggest that meta-learning augmented with an instinctual network is a promising new approach for safe AI, which may enable progress in this area on a variety of different domains.

Water quality has a direct impact on industry, agriculture, and public health. Algae species are common indicators of water quality. It is because algal communities are sensitive to changes in their habitats, giving valuable knowledge on variations in water quality. However, water quality analysis requires professional inspection of algal detection and classification under microscopes, which is very time-consuming and tedious. In this paper, we propose a novel multi-target deep learning framework for algal detection and classification. Extensive experiments were carried out on a large-scale colored microscopic algal dataset. Experimental results demonstrate that the proposed method leads to the promising performance on algal detection, class identification and genus identification.

Bayesian predictive coding is a putative neuromorphic method for acquiring higher-level neural representations to account for sensory input. Although originating in the neuroscience community, there are also efforts in the machine learning community to study these models. This paper reviews some of the more well known models. Our review analyzes module connectivity and patterns of information transfer, seeking to find general principles used across the models. We also survey some recent attempts to cast these models within a deep learning framework. A defining feature of Bayesian predictive coding is that it uses top-down, reconstructive mechanisms to predict incoming sensory inputs or their lower-level representations. Discrepancies between the predicted and the actual inputs, known as prediction errors, then give rise to future learning that refines and improves the predictive accuracy of learned higher-level representations. Predictive coding models intended to describe computations in the neocortex emerged prior to the development of deep learning and used a communication structure between modules that we name the Rao-Ballard protocol. This protocol was derived from a Bayesian generative model with some rather strong statistical assumptions. The RB protocol provides a rubric to assess the fidelity of deep learning models that claim to implement predictive coding.

Recently, the outbreak of Coronavirus Disease 2019 (COVID-19) has spread rapidly across the world. Due to the large number of affected patients and heavy labor for doctors, computer-aided diagnosis with machine learning algorithm is urgently needed, and could largely reduce the efforts of clinicians and accelerate the diagnosis process. Chest computed tomography (CT) has been recognized as an informative tool for diagnosis of the disease. In this study, we propose to conduct the diagnosis of COVID-19 with a series of features extracted from CT images. To fully explore multiple features describing CT images from different views, a unified latent representation is learned which can completely encode information from different aspects of features and is endowed with promising class structure for separability. Specifically, the completeness is guaranteed with a group of backward neural networks (each for one type of features), while by using class labels the representation is enforced to be compact within COVID-19/community-acquired pneumonia (CAP) and also a large margin is guaranteed between different types of pneumonia. In this way, our model can well avoid overfitting compared to the case of directly projecting highdimensional features into classes. Extensive experimental results show that the proposed method outperforms all comparison methods, and rather stable performances are observed when varying the numbers of training data.

Segmentation is a prerequisite yet challenging task for medical image analysis. In this paper, we introduce a novel deeply supervised active learning approach for finger bones segmentation. The proposed architecture is fine-tuned in an iterative and incremental learning manner. In each step, the deep supervision mechanism guides the learning process of hidden layers and selects samples to be labeled. Extensive experiments demonstrated that our method achieves competitive segmentation results using less labeled samples as compared with full annotation.

Assistive robots enable people with disabilities to conduct everyday tasks on their own. However, these tasks can be complex, containing both coarse reaching motions and fine-grained manipulation. For example, when eating, not only does one need to move to the correct food item, but they must also precisely manipulate the food in different ways (e.g., cutting, stabbing, scooping). Shared autonomy methods make robot teleoperation safer and more precise by arbitrating user inputs with robot controls. However, these works have focused mainly on the high-level task of reaching a goal from a discrete set, while largely ignoring manipulation of objects at that goal. Meanwhile, dimensionality reduction techniques for teleoperation map useful high-dimensional robot actions into an intuitive low-dimensional controller, but it is unclear if these methods can achieve the requisite precision for tasks like eating. Our insight is that---by combining intuitive embeddings from learned latent actions with robotic assistance from shared autonomy---we can enable precise assistive manipulation. In this work, we adopt learned latent actions for shared autonomy by proposing a new model structure that changes the meaning of the human's input based on the robot's confidence of the goal. We show convergence bounds on the robot's distance to the most likely goal, and develop a training procedure to learn a controller that is able to move between goals even in the presence of shared autonomy. We evaluate our method in simulations and an eating user study.

We investigate learnability of possibilistic theories from entailments in light of Angluin's exact learning model. We consider cases in which only membership, only equivalence, and both kinds of queries can be posed by the learner. We then show that, for a large class of problems, polynomial time learnability results for classical logic can be transferred to the respective possibilistic extension. In particular, it follows from our results that the possibilistic extension of propositional Horn theories is exactly learnable in polynomial time. As polynomial time learnability in the exact model is transferable to the classical probably approximately correct model extended with membership queries, our work also establishes such results in this model.

Smart meters enable remote and automatic electricity, water and gas consumption reading and are being widely deployed in developed countries. Nonetheless, there is still a huge number of non-smart meters in operation. Image-based Automatic Meter Reading (AMR) focuses on dealing with this type of meter readings. We estimate that the Energy Company of Paran'a (Copel), in Brazil, performs more than 850,000 readings of dial meters per month. Those meters are the focus of this work. Our main contributions are: (i) a public real-world dial meter dataset (shared upon request) called UFPR-ADMR; (ii) a deep learning-based recognition baseline on the proposed dataset; and (iii) a detailed error analysis of the main issues present in AMR for dial meters. To the best of our knowledge, this is the first work to introduce deep learning approaches to multi-dial meter reading, and perform experiments on unconstrained images. We achieved a 100.0% F1-score on the dial detection stage with both Faster R-CNN and YOLO, while the recognition rates reached 93.6% for dials and 75.25% for meters using Faster R-CNN (ResNext-101).

Narrowband internet-of-things (NB-IoT) is a competitive 5G technology for massive machine-type communication scenarios, but meanwhile introduces narrowband interference (NBI) to existing broadband transmission such as the long term evolution (LTE) systems in enhanced mobile broadband (eMBB) scenarios. In order to facilitate the harmonic and fair coexistence in wireless heterogeneous networks, it is important to eliminate NB-IoT interference to LTE systems. In this paper, a novel sparse machine learning based framework and a sparse combinatorial optimization problem is formulated for accurate NBI recovery, which can be efficiently solved using the proposed iterative sparse learning algorithm called sparse cross-entropy minimization (SCEM). To further improve the recovery accuracy and convergence rate, regularization is introduced to the loss function in the enhanced algorithm called regularized SCEM. Moreover, exploiting the spatial correlation of NBI, the framework is extended to multiple-input multiple-output systems. Simulation results demonstrate that the proposed methods are effective in eliminating NB-IoT interference to LTE systems, and significantly outperform the state-of-the-art methods.

Recently, the Edge Computing paradigm has gained significant popularity both in industry and academia. Researchers now increasingly target to improve performance and reduce energy consumption of such devices. Some recent efforts focus on using emerging RRAM technologies for improving energy efficiency, thanks to their no leakage property and high integration density. As the complexity and dynamism of applications supported by such devices escalate, it has become difficult to maintain ideal performance by static RRAM controllers. Machine Learning provides a promising solution for this, and hence, this work focuses on extending such controllers to allow dynamic parameter updates. In this work we propose an Adaptive RRAM Variability-Aware Controller, AVAC, which periodically updates Wait Buffer and batch sizes using on-the-fly learning models and gradient ascent. AVAC allows Edge devices to adapt to different applications and their stages, to improve computation performance and reduce energy consumption. Simulations demonstrate that the proposed model can provide up to 29% increase in performance and 19% decrease in energy, compared to static controllers, using traces of real-life healthcare applications on a Raspberry-Pi based Edge deployment.

In this paper, we continue our prior work on using imitation learning (IL) and model free reinforcement learning (RL) to learn driving policies for autonomous driving in urban scenarios, by introducing a model based RL method to drive the autonomous vehicle in the Carla urban driving simulator. Although IL and model free RL methods have been proved to be capable of solving lots of challenging tasks, including playing video games, robots, and, in our prior work, urban driving, the low sample efficiency of such methods greatly limits their applications on actual autonomous driving. In this work, we developed a model based RL algorithm of guided policy search (GPS) for urban driving tasks. The algorithm iteratively learns a parameterized dynamic model to approximate the complex and interactive driving task, and optimizes the driving policy under the nonlinear approximate dynamic model. As a model based RL approach, when applied in urban autonomous driving, the GPS has the advantages of higher sample efficiency, better interpretability, and greater stability. We provide extensive experiments validating the effectiveness of the proposed method to learn robust driving policy for urban driving in Carla. We also compare the proposed method with other policy search and model free RL baselines, showing 100x better sample efficiency of the GPS based RL method, and also that the GPS based method can learn policies for harder tasks that the baseline methods can hardly learn.

Making changes to a program to optimize its performance is an unscalable task that relies entirely upon human intuition and experience. In addition, companies operating at large scale are at a stage where no single individual understands the code controlling its systems, and for this reason, making changes to improve performance can become intractably difficult. In this paper, a learning system is introduced that provides AI assistance for finding recommended changes to a program. Specifically, it is shown how the evaluative feedback, delayed-reward performance programming domain can be effectively formulated via the Monte Carlo tree search (MCTS) framework. It is then shown that established methods from computational games for using learning to expedite tree-search computation can be adapted to speed up computing recommended program alterations. Estimates of expected utility from MCTS trees built for previous problems are used to learn a sampling policy that remains effective across new problems, thus demonstrating transferability of optimization knowledge. This formulation is applied to the Apache Spark distributed computing environment, and a preliminary result is observed that the time required to build a search tree for finding recommendations is reduced by up to a factor of 10x.

Coronavirus disease 2019 (Covid-19) is highly contagious with limited treatment options. Early and accurate diagnosis of Covid-19 is crucial in reducing the spread of the disease and its accompanied mortality. Currently, detection by reverse transcriptase polymerase chain reaction (RT-PCR) is the gold standard of outpatient and inpatient detection of Covid-19. RT-PCR is a rapid method, however, its accuracy in detection is only ~70-75%. Another approved strategy is computed tomography (CT) imaging. CT imaging has a much higher sensitivity of ~80-98%, but similar accuracy of 70%. To enhance the accuracy of CT imaging detection, we developed an open-source set of algorithms called CovidCTNet that successfully differentiates Covid-19 from community-acquired pneumonia (CAP) and other lung diseases. CovidCTNet increases the accuracy of CT imaging detection to 90% compared to radiologists (70%). The model is designed to work with heterogeneous and small sample sizes independent of the CT imaging hardware. In order to facilitate the detection of Covid-19 globally and assist radiologists and physicians in the screening process, we are releasing all algorithms and parametric details in an open-source format. Open-source sharing of our CovidCTNet enables developers to rapidly improve and optimize services, while preserving user privacy and data ownership.

[IMAGE-1] Part of being a music lover is also being a snob, and even though my mind has opened considerably as I've aged, I still remember all the genres I just couldn't give any time to when I was growing up. Southern rock was definitely verboten for much of my life.…

A computer-implemented method is provided for statistical data learning under privacy constraints. The method includes: receiving, by a processor, a plurality of pieces of statistical information relating to a statistical object and aggregating, by the processor, the plurality of pieces of statistical information so as to provide an estimation of the statistical object. Each piece of statistical information includes an uncertainty variable, the uncertainty variable being a value determined from a function having a predetermined mean. The number of pieces of statistical information aggregated is proportional to the reliability of the estimation of the statistical object.

Methods and arrangements for conducting a search using query logs. A query log is consulted and query rewrite rules are learned automatically based on data in the query log. The learning includes obtaining click-through data present in the query log.

A datapath extraction tool uses machine-learning models to selectively classify clusters of cells in an integrated circuit design as either datapath logic or non-datapath logic based on cluster features. A support vector machine and a neural network can be used to build compact and run-time efficient models. A cluster is classified as datapath if both the support vector machine and the neural network indicate that it is datapath-like. The cluster features may include automorphism generators for the cell clusters, or physical information based on the cell locations from a previous (e.g., global) placement, such as a ratio of a total cell area for a given cluster to a half-perimeter of a bounding box for the given cluster.

A handheld electronic device includes a reduced QWERTY keyboard and is enabled with a disambiguation routine that is operable to disambiguate text input. In addition to identifying and outputting representations of language objects that are stored in the memory and that correspond with a text input, the device is able to perform a spell check routine during input of a text entry and to learn and automatically correct mistakes typically made by the particular user.

Smoking cessation lighter is configured for lighting cigarettes for a smoker, and learning software is provided for monitoring smoking behavior of a smoker during a first data collection period and guiding a smoker's smoking cessation by directing the smoker when the smoker is to smoke a cigarette based on data collected during the first data collection period. The learning software monitors user behavior and collects data during use of the lighter by the smoker after the initial data collection period in order to analyze and further guide the smoker based on the smoker's cheating behavior, the smoker's behavior of lighting a cigarette for a friend, and the smoker's behavior of skipping use of the lighter at a time when the smoker has been directed to light a cigarette by the lighter.

A model aircraft control and receiving device in a housing, comprising an electronic, gyroscopic multi-axis programmable flight attitude controller, having control inputs for a plurality of control channels and inputs for gyroscope signals, wherein the flight attitude controller provides at least one input for a receiver module disposed inside or outside of the housing of the flight attitude controller. The device may be used in a method for controlling and stabilizing a model helicopter, wherein the control comprises a self-learning function and/or the control comprises a coupling of the tail controller to the swashplate controller and/or the control comprises a stopping support function.

A learning toy that includes a frame and a plurality of blocks. Each block includes a different color on each face with a first face having a first color and a second face having a second color. Additionally, four different colors are separately assigned to each of the remaining faces and the color assignments vary between at least two blocks of the plurality of blocks. The plurality of blocks allow for consistency and variability. Consistency comes from the colors assigned to two faces staying the same between blocks and the variability comes from the colors assigned to remaining four faces varying between some blocks.

A drive system for a mobile machine is disclosed. The drive system may have a travel speed sensor, at least one traction device speed sensor, and a controller in communication with the travel speed sensor and the at least one traction device speed sensor. The controller may be configured to determine a slip value associated with a traction device of the mobile machine based on signals generated by the travel speed sensor and the at least one traction device speed sensor, and determine a torque output value of the mobile machine. The control may also be configured to make a comparison of the slip value and the torque output value with a pull-slip curve stored in memory, and selectively update the pull-slip curve based on the comparison.

An improved learning aid in the form of a book, the book includes a front cover, a back cover, and a plurality of pages intermediate the front cover and the back cover. The plurality of pages, front cover, and back cover are conventionally bound together along one longitudinal side by a binding means. The back cover includes an outer side disposed with a plurality of sections. Each of the sections printed text framed by a text identification and sequence indicator, wherein the printed text is a complete reproduction of the text printed on a particular numbered page of the plurality of pages of the book.

A computerized-social network provides a community of users with features and tools facilitating an immersive, collaborative environment where users can learn a language or help others learn a language. One user (user A) can view another user's (user B) Web page or document and make suggestions or comments for selected content on that Web page. These suggestions are linked specifically to the selected content. User B can review the suggestions, and accept or reject the suggestions by user A and others.

More than a month since officials closed schools due to Covid-19, California leaders said a two-week blitz led by First Partner Jennifer Siebel Newsom has brought in 70,000 computers and other devices that will be distributed to needy students this week. Gov. Gavin Newsom has stressed the importance of distance learning and education multiple times during the past month—even talking about helping his own children with school work.…

A method and system for teaching oneself to learn to play a string instrument and master it by analyzing one's real-time hand/finger movement/technique/form, enabling oneself to progress and correct one's own mistakes simultaneously. In one aspect, a system for learning to play a string instrument is provided that includes a simulation instrument that includes a plurality of strings, wherein at least one of the strings includes at least one-touch sensing sensor thereon in communication with at least one processor to receive a signal from the at least one touch-sensing sensor and determine therefrom when and where on the at least one string a user applies pressure to the at least one string.

Luis Suarez is set to learn his fate today as his lawyer claimed calls for the Uruguay striker to face a lengthy ban for biting Giorgio Chiellini were part of an Anglo-Italian conspiracy.

If you do not want to spend every day doing the same thing, we have just the job for you!

by Mike Vimpany

I spent a lot of time watching myself mix while editing my Mixing in REAPER Vol 1 video series. I’ve learned quite a bit from…

In this first part of a series of podcasts, Khalfan Bin Dhaher introduces us to the Swift Playgrounds app for the iPad, and takes us through the first lesson.
Swift Playgrounds is an app made by Apple for the iPad, designed to get people, young and old, started in coding in a fun and engaging manner.
If not already installed on your iPad, you can get it here on the App Store.

IN this podcast, Khalfan Bin Dhaher brings us part two of his three part series on learning to code with Swift Playgrounds from a VoiceOver user's perspective.

Part 3 of Khalfan Bin Dhaher's series on the Swift Playgrounds app, a fun and engaging way to learn to code on your iPad, with great VoiceOver accessibility.

Kim Manley Ort shares her approach to contemplative photography including exercises you can try using your camera or smartphone. We also discuss the challenges of sharing photos on social media and why they’re worth navigating. Excerpt from her book Adventures in Seeing: How the Camera Teaches You to Pause, Focus, and Connect with Life : “Learn to trust and honor your unique way of seeing and share it with the world. Our world needs people who pause before reacting, who focus on what’s really happening, see the possibilities, and then act from this place. It needs people who don’t feel helpless, who don’t rush to judgment or dismiss people or situations as unworthy of attention. The world needs you to see this way and your camera or smartphone can lead the way.” Follow Kim: KimManleyOrt.com Workshops, on-demand email courses, and retreats Monthly newsletter Instagram Resources that came up in our conversation: Digital Minimalism: Choosing a Focused Life in a Noisy World ( library ) by

Faces of the relatives gathered outside the White Star Line’s Southampton offices were etched with anguish and despair. Dan Kerins retells the story of when the tragic Titanic news broke

Serato has announced that its Serato Play DJ software is available for free during the month of May. You can get started right away with Serato Play, even if you’re not sure how. Serato has tutorials to help you navigate any questions, plus TIDAL and Soundcloud streaming integration into the software to get you started […]

The post Learn to DJ for free with Serato Play appeared first on rekkerd.org.

Emkay Global expects PVR and Inox Leisure to post steep year-on-year drop in revenues at 19 per cent and 24 per cent, respectively.

FMCG major Hindustan Unilever on Thursday reported a decline of 3.93 per cent in consolidated profit to Rs 1,512 crore for the fourth quarter, impacted by the coronavirus crisis from mid-March.

Bernice Hausman is chair of the Department of Humanities in the Penn State College of Medicine. She’s recognized for her research on vaccines and breastfeeding, including why both can be controversial in the United States. She has written several books, most recently "Anti/Vax: Reframing the Vaccination Controversy," which was published last year. WPSU's Anne Danahy spoke with Hausman about what we can learn from past vaccine controversies about the COVID-19 epidemic.

Most consumer durables companies in India rely on imported components. Poor input supplies since January and later closure of factories, malls, shops and offices due to the lockdown hit consumer demand badly.

Coronavirus has highlighted the digital divide among low-income as well as rural students. Schools that don’t send students home with laptops rushed them equipment so they could do their homework online. School administrators say some parents claim to have internet access, but it may only be through a phone plan. Districts have distributed hot spots for families without a plan or where service is undependable. Particularly in rural communities like Montmorency, reliable internet connectivity is a major hurdle. Montmorency is a K-8 district in Whiteside County with around 230 students. Alex Moore is the superintendent. “On a good day, I get four megabytes per second download speed, so I knew that was going to be an issue. About half of our families probably have decent internet,” said Moore. Even that “good day” download speed doesn’t meet the FCC’s minimum recommendation for e-learning. For many younger students, remote learning has to be pencil and paper. Schools like Somonauk set up

AS Scotland’s National Dance Company, Scottish Ballet aims to bring the benefits and joy of dance to everyone.

New era, same old Kash Farooq. The Glasgow bantamweight may be preparing to enter the latest phase of what has already been a hugely successful boxing career but there is little chance of him ever becoming complacent. It’s just not in his mindset.

Schools are closed, and Zoom is the new classroom for thousands of Bay Area students. We'll discuss how local school districts are handling distance learning, get tips from teachers and hear about what we can do to create equitable learning experiences for all. We'll also get a update on the lastest local pandemic developments and hear a specially composed reflection on life in the coronavirus era by Bay Area novelist Vanessa Hua. And we want to hear from you. Call us during the show with your questions and experiences: 866-798-TALK or send an email anytime to cityvisions@kalw.org . Wednesday, April 15 at 9 PM. Guests : Erin Allday , health reporter, San Francisco Chronicle Peter Chin-Hong , professor of medicine and infectious diseases specialist, UCSF JC Farr , principal, Tamalpais High School in Marin County Lisa Kelly , 6th grade English teacher at the Life Academy in Oakland Jill Tucker, K-12 education reporter, San Francisco Chronicle Vanessa Hua , novelist whose books include

Educators, parents and students are all struggling to find their way through distance learning, but the challenges can be even greater for special education students.