What they did: The SDO instrument in question is known as MEGS-A, and it was designed to keep an eye on ultraviolet radiation levels, which correlate with a ballooning of the Earth's outer atmosphere that can harm satellites in near-Earth orbit. A deep-learning network that researchers at NASA Frontier Development Lab created with help from IBM, SETI, and Nimbix in 2018 may soon replace the failed instrument by inferring what ultraviolet radiation levels that instrument would detect based on what the other instruments on SDO are observing at any given time, NASA AI consultant Graham Mackintosh tells Axios. While NASA isn't yet using the fix operationally, the results are promising, Mackintosh added. What to watch: AI models like this could also be used for other future missions, Mackintosh said. Instead of loading 3 instruments on a satellite to measure different aspects of the space environment, you could potentially launch two and use the data collected to infer the information that would have been measured by a third.

Blockchain and artificial intelligence are two emerging technologies that are quickly bringing about further digitization in the business world. Here are six ways they are changing how businesses operate and will continue to do so for the foreseeable future. One of the advantages of blockchain technology for businesses is that it offers more transparency about shipments and how products move through the supply chain. People cannot edit information once it gets entered into the digital ledger. Then, businesses don't have to worry about potential records tampering.

Unilever is using artificial intelligence to influence more of its marketing, from processing insights to finding influencers. The advertiser has 26 data centers across the globe where scientists are using AI to synthesize insights from a range of sources including social listening, CRM and traditional marketing research. Like other advertisers, Unilever hopes the investments fuel a move away from mass reach channels toward more personalized communications that are also cheaper to produce and localize at scale. Unilever has been using AI and machine learning to sort through structured data within a database for years, but it hasn't been able to do the same for unstructured data until recently. Unstructured data is qualitative, which makes gleaning insights from content such as text, audio, social media and mobile activity harder.

The number of recorded sexual offences involving online dating sites and apps has almost doubled in the last four years, police figures suggest. Offences where a dating site was mentioned in a police report increased from 156 in 2015, to 286 last year, according to figures from 23 of the 43 forces in England and Wales. The Online Dating Association said apps try to protect users from harm. But the National Police Chiefs' Council said firms had a duty to do more. The figures reveal that between 2015 and 2018 there were a total of 2,029 recorded offences - including sexual offences - where an online dating website or app was mentioned in a police report. In 2015, 329 offences were recorded, compared to 658 recorded offences last year.

The behavior of the gradient descent (GD) algorithm is analyzed for a deep neural network model with skip-connections. It is proved that in the over-parametrized regime, for a suitable initialization, with high probability GD can find a global minimum exponentially fast. Generalization error estimates along the GD path are also established. As a consequence, it is shown that when the target function is in the reproducing kernel Hilbert space (RKHS) with a kernel defined by the initialization, there exist generalizable early-stopping solutions along the GD path. In addition, it is also shown that the GD path is uniformly close to the functions given by the related random feature model. Consequently, in this "implicit regularization" setting, the deep neural network model deteriorates to a random feature model. Our results hold for neural networks of any width larger than the input dimension.

Next basket recommendation, which aims to predict the next a few items that a user most probably purchases given his historical transactions, plays a vital role in market basket analysis. From the viewpoint of item, an item could be purchased by different users together with different items, for different reasons. Therefore, an ideal recommender system should represent an item considering its transaction contexts. Existing state-of-the-art deep learning methods usually adopt the static item representations, which are invariant among all of the transactions and thus cannot achieve the full potentials of deep learning. Inspired by the pre-trained representations of BERT in natural language processing, we propose to conduct context-aware item representation for next basket recommendation, called Item Encoder Representations from Transformers (IERT). In the offline phase, IERT pre-trains deep item representations conditioning on their transaction contexts. In the online recommendation phase, the pre-trained model is further fine-tuned with an additional output layer. The output contextualized item embeddings are used to capture users' sequential behaviors and general tastes to conduct recommendation. Experimental results on the Ta-Feng data set show that IERT outperforms the state-of-the-art baseline methods, which demonstrated the effectiveness of IERT in next basket representation.

Robotic systems are ever more capable of automation and fulfilment of complex tasks, particularly with reliance on recent advances in intelligent systems, deep learning and artificial intelligence in general. However, as robots and humans come closer together in their interactions, the matter of interpretability, or explainability of robot decision-making processes for the human grows in importance. A successful interaction and collaboration would only be possible through mutual understanding of underlying representations of the environment and the task at hand. This is currently a challenge in deep learning systems. We present a hierarchical deep reinforcement learning system, consisting of a low-level agent handling the large actions/states space of a robotic system efficiently, by following the directives of a high-level agent which is learning the high-level dynamics of the environment and task. This high-level agent forms a representation of the world and task at hand that is interpretable for a human operator. The method, which we call Dot-to-Dot, is tested on a MuJoCo-based model of the Fetch Robotics Manipulator, as well as a Shadow Hand, to test its performance. Results show efficient learning of complex actions/states spaces by the low-level agent, and an interpretable representation of the task and decision-making process learned by the high-level agent.

End-to-end deep reinforcement learning has enabled agents to learn with little preprocessing by humans. However, it is still difficult to learn stably and efficiently because the learning method usually uses a nonlinear function approximation. Neural Episodic Control (NEC), which has been proposed in order to improve sample efficiency, is able to learn stably by estimating action values using a non-parametric method. In this paper, we propose an architecture that incorporates random projection into NEC to train with more stability. In addition, we verify the effectiveness of our architecture by Atari's five games. The main idea is to reduce the number of parameters that have to learn by replacing neural networks with random projection in order to reduce dimensions while keeping the learning end-to-end.

-- Facial attributes are important since they provide a detailed description and determine the visual appearance of human faces. In this paper, we aim at converting a face image to a sketch while simultaneously generating facial attributes. T o this end, we propose a novel Attribute-Guided Sketch Generative Adversarial Network (ASGAN) which is an end-to-end framework and contains two pairs of generators and discriminators, one of which is used to generate faces with attributes while the other one is employed for image-to-sketch translation. The two generators form a W-shaped network (W-net) and they are trained jointly with a weight-sharing constraint. Additionally, we also propose two novel discriminators, the residual one focusing on attribute generation and the triplex one helping to generate realistic looking sketches. T o validate our model, we have created a new large dataset with 8,804 images, named the Attribute Face Photo & Sketch (AFPS) dataset which is the first dataset containing attributes associated to face sketch images. The experimental results demonstrate that the proposed network (i) generates more photo-realistic faces with sharper facial attributes than baselines and (ii) has good generalization capability on different generative tasks. Recently, there has been a new trend in computer vision to use machines to express the "creativity" of art. Novel and never-seen-before images can be generated by inverting the convolution process in CNN ("upconvolution" or "deconvolution"), which gives such networks the ability to "dream" [23] and to generate images.

In this paper, we propose to apply object detection methods from the vision domain on the speech recognition domain, by treating audio fragments as objects. More specifically, we present SpeechYOLO, which is inspired by the YOLO algorithm for object detection in images. The goal of SpeechYOLO is to localize boundaries of utterances within the input signal, and to correctly classify them. Our system is composed of a convolutional neural network, with a simple least-mean-squares loss function. We evaluated the system on several keyword spotting tasks, that include corpora of read speech and spontaneous speech. Our system compares favorably with other algorithms trained for both localization and classification.