OpenAI today updated Gym – its system for training intelligent software – so that developers can teach physical robots to hold pens, pick up and move objects, and so on. Gym was launched in 2016, and is a toolkit for teaching programs new tricks, such as playing Atari games and balancing poles, via reinforcement learning (RL). Now, OpenAI has added a bunch of simulated environments designed to train physical robots how to move and interact with things around them albeit in a virtual world. For example, the simulated environments can be used to teach robotic fingers to play an instrument, or pick and lift an object from the table. This is useful for folks interested in rapidly training intelligent robots over thousands of exercises, without having to rig up a relatively slow-moving physical bot, or before they have a chance to get hold of the hardware.

Today's blog post is broken down into three parts. In the first part we'll discuss the origin of the more accurate OpenCV face detectors and where they live inside the OpenCV library. From there I'll demonstrate how you can perform face detection in images using OpenCV and deep learning. I'll then wrap up the blog post discussing how you can apply face detection to video streams using OpenCV and deep learning as well. Back in August 2017, OpenCV 3.3 was officially released, bringing it with it a highly improved "deep neural networks" ( dnn) module.

In two new studies, researchers at UCLA used artificial neural networks to reconstruct a hologram -- not just any hologram, though. Not only is the technique an advancement of holographic technology, but the resulting microscopic images could have fascinating medical applications. In the first study, published in the journal, Light: Science & Applications, researchers used deep learning to create images of biological samples like blood, Pap smears, and other thin tissue samples. The neural network technique proved to be easier and faster than the usual methods used to make holograms, which often require an abundance of physical measurements and computational input. In the second study, the team applied their deep learning framework to improve the resolution and quality of the microscopic images, which could help doctors detect very small abnormalities in a large blood or tissue sample.

In The future of AI and endpoint security, I wrote about the need for more AI at the endpoint to protect end users. But both the nature of endpoints and the science of AI are evolving at such a pace that we need to start thinking about even more advanced solutions. We currently think of endpoints as being PCs and laptops, and occasionally tablets, mobiles and other internet-enabled devices. Get the latest from CSO by signing up for our newsletters. The future of endpoints is bright, with autonomous vehicles and robotics being added to the mix, though with this bright future comes heightened risk.

Customer insight professionals charged with gaining a wider understanding of customers from the growing volumes of structured and unstructured data accruing in real time can benefit greatly from deep learning. This e-guide collates a group of examples of big data technologies in use, such as how Mercedes-AMG Petronas Motorsport are looking to gain an edge on the competition in the Grand Prix season. Also see how big organisations are managing their big data operations and their data analytics programmes and teams through some high profile case studies. You forgot to provide an Email Address. This email address doesn't appear to be valid.

Stochastic gradient descent (SGD) has achieved great success in training deep neural network, where the gradient is computed through back-propagation. However, the back-propagated values of different layers vary dramatically. This inconsistence of gradient magnitude across different layers renders optimization of deep neural network with a single learning rate problematic. We introduce the back-matching propagation which computes the backward values on the layer's parameter and the input by matching backward values on the layer's output. This leads to solving a bunch of least-squares problems, which requires high computational cost. We then reduce the back-matching propagation with approximations and propose an algorithm that turns to be the regular SGD with a layer-wise adaptive learning rate strategy. This allows an easy implementation of our algorithm in current machine learning frameworks equipped with auto-differentiation. We apply our algorithm in training modern deep neural networks and achieve favorable results over SGD.

Flood of information is produced in a daily basis through the global Internet usage arising from the on-line interactive communications among users. While this situation contributes significantly to the quality of human life, unfortunately it involves enormous dangers, since on-line texts with high toxicity can cause personal attacks, on-line harassment and bullying behaviors. This has triggered both industrial and research community in the last few years while there are several tries to identify an efficient model for on-line toxic comment prediction. However, these steps are still in their infancy and new approaches and frameworks are required. On parallel, the data explosion that appears constantly, makes the construction of new machine learning computational tools for managing this information, an imperative need. Thankfully advances in hardware, cloud computing and big data management allow the development of Deep Learning approaches appearing very promising performance so far. For text classification in particular the use of Convolutional Neural Networks (CNN) have recently been proposed approaching text analytics in a modern manner emphasizing in the structure of words in a document. In this work, we employ this approach to discover toxic comments in a large pool of documents provided by a current Kaggle's competition regarding Wikipedia's talk page edits. To justify this decision we choose to compare CNNs against the traditional bag-of-words approach for text analysis combined with a selection of algorithms proven to be very effective in text classification. The reported results provide enough evidence that CNN enhance toxic comment classification reinforcing research interest towards this direction.

Interpreting neural networks is a crucial and challenging task in machine learning. In this paper, we develop a novel framework for detecting statistical interactions captured by a feedforward multilayer neural network by directly interpreting its learned weights. Depending on the desired interactions, our method can achieve significantly better or similar interaction detection performance compared to the state-of-the-art without searching an exponential solution space of possible interactions. We obtain this accuracy and efficiency by observing that interactions between input features are created by the non-additive effect of nonlinear activation functions, and that interacting paths are encoded in weight matrices. We demonstrate the performance of our method and the importance of discovered interactions via experimental results on both synthetic datasets and real-world application datasets.

Traditional methods for assessing illness severity and predicting in-hospital mortality among critically ill patients require manual, time-consuming, and error-prone calculations that are further hindered by the use of static variable thresholds derived from aggregate patient populations. These coarse frameworks do not capture time-sensitive individual physiological patterns and are not suitable for instantaneous assessment of patients' acuity trajectories, a critical task for the ICU where conditions often change rapidly. Furthermore, they are ill-suited to capitalize on the emerging availability of streaming electronic health record data. We propose a novel acuity score framework (DeepSOFA) that leverages temporal patient measurements in conjunction with deep learning models to make accurate assessments of a patient's illness severity at any point during their ICU stay. We compare DeepSOFA with SOFA baseline models using the same predictors and find that at any point during an ICU admission, DeepSOFA yields more accurate predictions of in-hospital mortality.

Deep Neural Networks (DNNs) provide state-of-the-art solutions in several difficult machine perceptual tasks. However, their performance relies on the availability of a large set of labeled training data, which limits the breadth of their applicability. Hence, there is a need for new {\em semi-supervised learning} methods for DNNs that can leverage both (a small amount of) labeled and unlabeled training data. In this paper, we develop a general loss function enabling DNNs of any topology to be trained in a semi-supervised manner without extra hyper-parameters. As opposed to current semi-supervised techniques based on topology-specific or unstable approaches, ours is both robust and general. We demonstrate that our approach reaches state-of-the-art performance on the SVHN ($9.82\%$ test error, with $500$ labels and wide Resnet) and CIFAR10 (16.38% test error, with 8000 labels and sigmoid convolutional neural network) data sets.