One of the greatest obstacles in the adoption of deep neural networks for new applications is that training the network typically requires a large number of manually labeled training samples. We empirically investigate the scenario where one has access to large amounts of unlabeled data but require labeling only a single prototypical sample per class in order to train a deep network (i.e., one-shot semi-supervised learning). Specifically, we investigate the recent results reported in FixMatch for one-shot semi-supervised learning to understand the factors that affect and impede high accuracies and reliability for one-shot semi-supervised learning of Cifar-10. For example, we discover that one barrier to one-shot semi-supervised learning for high-performance image classification is the unevenness of class accuracy during the training. These results point to solutions that might enable more widespread adoption of one-shot semi-supervised training methods for new applications.

We propose learning discrete structured representations from unlabeled data by maximizing the mutual information between a structured latent variable and a target variable. Calculating mutual information is intractable in this setting. Our key technical contribution is an adversarial objective that can be used to tractably estimate mutual information assuming only the feasibility of cross entropy calculation. We develop a concrete realization of this general formulation with Markov distributions over binary encodings. We report critical and unexpected findings on practical aspects of the objective such as the choice of variational priors. We apply our model on document hashing and show that it outperforms current best baselines based on discrete and vector quantized variational autoencoders. It also yields highly compressed interpretable representations.

US healthcare officials are working tirelessly to deliver coronavirus test results in a timely manner, but the process includes getting tested, having the sample processed and then delivering the results. Now, a scientist has developed new technology that can produce a diagnosis in just a matter of seconds and with 98 percent accuracy. Barath Narayanan, a scientist at the University of Dayton Research Institute, has designed a specific software code that can detect the disease just by scanning chest X-rays. The process uses a deep learning algorithm that was trained using scans of those with and without the disease in order to search searches for markings associated with coronavirus. A scientist has developed new technology that can produce a diagnosis in just a matter of seconds and with 98 percent accuracy.

NASA has released a detailed plan for an'Artemis Base Camp' that will be home to first woman and next man on the moon in 2024. The 13-page document highlights elements such as a terrain vehicle for transporting the astronauts around the landing zone, a permanent habit and a mobility platform to travel across the lunar surface. The plans suggest a crew of four astronauts would call the moon home for a week at a time, but also describes accommodations with water, waste disposal systems and radiation shields if their time is extended. The Artemis mission will use the moon as its stepping stone, allowing the crew to test robots and other technologies before exploring farther into the solar system, with Mars being their next stop. NASA has released a detailed plan for an'Artemis Base Camp' that will be home to first woman and next man on the moon in 2024.

ECMWF is organising a series of seminars given by international experts to explore aspects of the use of machine learning in weather prediction and climate studies. The first will take place on 28 April and will be live-streamed. Sherman Lo and Ritabrata Dutta from the University of Warwick will present a statistical methodology to predict precipitation at 0.1 resolution using lower-resolution model fields of air temperature, geopotential, specific humidity, total column water vapour and wind velocity. On 9 June, Annalisa Bracco from the School of Earth and Atmospheric Sciences at the Georgia Institute of Technology will talk about spatiotemporal complexity and time-dependent networks in mid- to late Holocene simulations. In subsequent seminars, Maxime Taillardat (Météo-France) will present examples of operational ensemble post-processing using machine learning; Alberto Arribas (UK Met Office) will talk about work at the Met Office Informatics Lab; and Nal Kalchbrenner (Google) will talk about now-casting applications at Google.

Since the corona erupted into our world, research institutes and governments have released many databases publicly to allow research groups (and independent individuals) to analyze the data around the corona's spread. These databases are scattered under numerous initiatives and sources. The purpose of this blog is to organize all the major open databases and data initiatives around the world. Feel free to add it in the comments or through this form. In response to the COVID-19 pandemic, the White House and a coalition of leading research groups have prepared the COVID-19 Open Research Dataset (CORD-19).

Generative Adversarial Networks (GANs) have gained significant attention in recent years, with particularly impressive applications highlighted in computer vision. In this work, we present a Mixture Density Conditional Generative Adversarial Model (MD-CGAN), where the generator is a Gaussian mixture model, with a focus on time series forecasting. Compared to examples in vision, there have been more limited applications of GAN models to time series. We show that our model is capable of estimating a probabilistic posterior distribution over forecasts and that, in comparison to a set of benchmark methods, the MD-CGAN model performs well, particularly in situations where noise is a significant in the time series. Further, by using a Gaussian mixture model that allows for a flexible number of mixture coefficients, the MD-CGAN offers posterior distributions that are non-Gaussian.

The global expansion of maritime activities and the development of the Automatic Identification System (AIS) have driven the advances in maritime monitoring systems in the last decade. Monitoring vessel behavior is fundamental to safeguard maritime operations, protecting other vessels sailing the ocean and the marine fauna and flora. Given the enormous volume of vessel data continually being generated, real-time analysis of vessel behaviors is only possible because of decision support systems provided with event and anomaly detection methods. However, current works on vessel event detection are ad-hoc methods able to handle only a single or a few predefined types of vessel behavior. Most of the existing approaches do not learn from the data and require the definition of queries and rules for describing each behavior. In this paper, we discuss challenges and opportunities in classical machine learning and deep learning for vessel event and anomaly detection. We hope to motivate the research of novel methods and tools, since addressing these challenges is an essential step towards actual intelligent maritime monitoring systems.

A lot of effort is currently made to provide methods to analyze and understand deep neural network impressive performances for tasks such as image or text classification. These methods are mainly based on visualizing the important input features taken into account by the network to build a decision. However these techniques, let us cite LIME, SHAP, Grad-CAM, or TDS, require extra effort to interpret the visualization with respect to expert knowledge. In this paper, we propose a novel approach to inspect the hidden layers of a fitted CNN in order to extract interpretable linguistic objects from texts exploiting classification process. In particular, we detail a weighted extension of the Text Deconvolution Saliency (wTDS) measure which can be used to highlight the relevant features used by the CNN to perform the classification task. We empirically demonstrate the efficiency of our approach on corpora from two different languages: English and French. On all datasets, wTDS automatically encodes complex linguistic objects based on co-occurrences and possibly on grammatical and syntax analysis.

Satirical news detection is an important yet challenging task to prevent spread of misinformation. Many feature based and end-to-end neural nets based satirical news detection systems have been proposed and delivered promising results. Existing approaches explore comprehensive word features from satirical news articles, but lack semantic metrics using word vectors for tweet form satirical news. Moreover, the vagueness of satire and news parody determines that a news tweet can hardly be classified with a binary decision, that is, satirical or legitimate. To address these issues, we collect satirical and legitimate news tweets, and propose a semantic feature based approach. Features are extracted by exploring inconsistencies in phrases, entities, and between main and relative clauses. We apply game-theoretic rough set model to detect satirical news, in which probabilistic thresholds are derived by game equilibrium and repetition learning mechanism. Experimental results on the collected dataset show the robustness and improvement of the proposed approach compared with Pawlak rough set model and SVM.