The fact that image datasets are often imbalanced poses an intense challenge for deep learning techniques. In this paper, we propose a method to restore the balance in imbalanced images, by coalescing two concurrent methods, generative adversarial networks (GANs) and capsule network. In our model, generative and discriminative networks play a novel competitive game, in which the generator generates samples towards specific classes from multivariate probabilities distribution. The discriminator of our model is designed in a way that while recognizing the real and fake samples, it is also requires to assign classes to the inputs. Since GAN approaches require fully observed data during training, when the training samples are imbalanced, the approaches might generate similar samples which leading to data overfitting. This problem is addressed by providing all the available information from both the class components jointly in the adversarial training. It improves learning from imbalanced data by incorporating the majority distribution structure in the generation of new minority samples. Furthermore, the generator is trained with feature matching loss function to improve the training convergence. In addition, prevents generation of outliers and does not affect majority class space. The evaluations show the effectiveness of our proposed methodology; in particular, the coalescing of capsule-GAN is effective at recognizing highly overlapping classes with much fewer parameters compared with the convolutional-GAN.

The information bottleneck (IB) principle offers both a mechanism to explain how deep neural networks train and generalize, as well as a regularized objective with which to train models. However, multiple competing objectives have been proposed based on this principle, and the information-theoretic quantities in these objectives are difficult to compute for large deep neural networks. This, in turn, limits their use as a training objective. In this work, we review these quantities, compare and unify previously proposed objectives and relate them to surrogate objectives more friendly to optimization. We find that these surrogate objectives allow us to apply the information bottleneck to modern neural network architectures. We demonstrate our insights on Permutation-MNIST, MNIST and CIFAR10.

Data on transient events, like GRBs, are often contained in large databases of unstructured data from space experiments, merged with potentially large amount of background or simply undesired information. We present a computational formal model to apply techniques of modern computer science -such as Data Mining (DM) and Knowledge Discovering in Databases (KDD)- to a generic, large database derived from a high energy astrophysics experiment. This method is aimed to search, identify and extract expected information, and maybe to discover unexpected information .

In previous work, artificial agents were shown to achieve almost perfect accuracy in referential games where they have to communicate to identify images. Nevertheless, the resulting communication protocols rarely display salient features of natural languages, such as compositionality. In this paper, we propose some realistic sources of pressure on communication that avert this outcome. More specifically, we formalise the principle of least effort through an auxiliary objective. Moreover, we explore several game variants, inspired by the principle of object constancy, in which we alter the frequency, position, and luminosity of the objects in the images. We perform an extensive analysis on their effect through compositionality metrics, diagnostic classifiers, and zero-shot evaluation. Our findings reveal that the proposed sources of pressure result in emerging languages with less redundancy, more focus on high-level conceptual information, and better abilities of generalisation. Overall, our contributions reduce the gap between emergent and natural languages.

Multilingual sequence labeling is a task of predicting label sequences using a single unified model for multiple languages. Compared with relying on multiple monolingual models, using a multilingual model has the benefit of a smaller model size, easier in online serving, and generalizability to low-resource languages. However, current multilingual models still underperform individual monolingual models significantly due to model capacity limitations. In this paper, we propose to reduce the gap between monolingual models and the unified multilingual model by distilling the structural knowledge of several monolingual models (teachers) to the unified multilingual model (student). We propose two novel KD methods based on structure-level information: (1) approximately minimizes the distance between the student's and the teachers' structure level probability distributions, (2) aggregates the structure-level knowledge to local distributions and minimizes the distance between two local probability distributions. Our experiments on 4 multilingual tasks with 25 datasets show that our approaches outperform several strong baselines and have stronger zero-shot generalizability than both the baseline model and teacher models.

Ordinal peer grading has been proposed as a simple and scalable solution for computing reliable information about student performance in massive open online courses. The idea is to outsource the grading task to the students themselves as follows. After the end of an exam, each student is asked to rank -- in terms of quality -- a bundle of exam papers by fellow students. An aggregation rule then combines the individual rankings into a global one that contains all students. We define a broad class of simple aggregation rules, which we call type-ordering aggregation rules, and present a theoretical framework for assessing their effectiveness. When statistical information about the grading behaviour of students is available (in terms of a noise matrix that characterizes the grading behaviour of the average student from a student population), the framework can be used to compute the optimal rule from this class with respect to a series of performance objectives that compare the ranking returned by the aggregation rule to the underlying ground truth ranking. For example, a natural rule known as Borda is proved to be optimal when students grade correctly. In addition, we present extensive simulations that validate our theory and prove it to be extremely accurate in predicting the performance of aggregation rules even when only rough information about grading behaviour (i.e., an approximation of the noise matrix) is available. Both in the application of our theoretical framework and in our simulations, we exploit data about grading behaviour of students that have been extracted from two field experiments in the University of Patras.

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.

Listening to classical music during lectures and throughout the night while sleeping may help us perform better in big exams, a new study suggests. US economics students who listened to Beethoven and Chopin during a lecture and again later in the night performed 18 per cent higher in exams the next day. This compared with a control group of students who were in the same lecture but slept that night with white noise on in the background. Researchers say that classical music activated a process called'targeted memory reactivation' (TMR), when the music stimulates the brain to consolidate memories. The study suggests classical music is the key to strengthening existing memories of lectures during sleep and, as a result, doing better in exams.

The Mayo Clinic in Florida is using self-driving shuttles to ferry coronavirus test from a drive-thru location to its Jacksonville campus. Four vehicles have been making round trips every day since March 30th in a bid to limit exposure and free up medical staff from having to deliver the tests. Healthcare workers place the samples into a secure container and loads it into a van that deliveries it to be processed. The route is isolated from pedestrians and traffic and the van is followed by the Jacksonville Transportation Authority to ensure a safe journey. This is the'first time in history' autonomous vehicles are being used to transport medical supplies.

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.