Throughout the last years, machine learning techniques have been broadly encouraged in the context of deep learning architectures. An interesting algorithm denoted as Restricted Boltzmann Machine relies on energy- and probabilistic-based nature to tackle with the most diverse applications, such as classification, reconstruction, and generation of images and signals. Nevertheless, one can see they are not adequately renowned when compared to other well-known deep learning techniques, e.g., Convolutional Neural Networks. Such behavior promotes the lack of researches and implementations around the literature, coping with the challenge of sufficiently comprehending these energy-based systems. Therefore, in this paper, we propose a Python-inspired framework in the context of energy-based architectures, denoted as Learnergy. Essentially, Learnergy is built upon PyTorch for providing a more friendly environment and a faster prototyping workspace, as well as, possibility the usage of CUDA computations, speeding up their computational time.

The goal of this challenge is to test the potential of Reinforcement Learning (RL) to control electrical power transmission, in the most cost-effective manner, while keeping people and equipment safe from harm. Solving this challenge may have very positive impacts on society, as governments move to decarbonize the electricity sector and to electrify other sectors, to help reach IPCC climate goals. Existing software, computational methods and optimal powerflow solvers are not adequate for real-time network operations on short temporal horizons in a reasonable computational time. With recent changes in electricity generation and consumption patterns, system operation is moving to become more of a stochastic rather than a deterministic control problem. In order to overcome these complexities, new computational methods are required. The intention of this challenge is to explore RL as a solution method for electricity network control. There may be under-utilized, cost-effective flexibility in the power network that RL techniques can identify and capitalize on, that human operators and traditional solution techniques are unaware of or unaccustomed to. An RL agent that can act in conjunction, or in parallel with human network operators, will optimize grid security and reliability, allowing more renewable resources to be connected while minimizing the cost and maintaining supply to customers, and preventing damage to electrical equipment. Another aim of the project is to broaden the audience for the problem of electricity network control and to foster collaboration between experts in both the power systems community and the wider RL/ML community.

The ominous spread of coronavirus has bolstered the case for such advances as telemedicine; drones; artificial intelligence/machine learning; Big Data; and more flexible regulation of health care personnel and institutions. During a social conversation via FaceTime, her grandson, a physician, realized Mom was in the early stages of septic shock. A day's delay in treatment might have proven fatal. Similar tales emerge from professional telemedicine doctors. The advantages of telemedicine for, say, a migrant worker family on a remote ranch whose child becomes ill in the wee hours.

We present a novel framework that can combine multi-domain learning (MDL), data imputation (DI) and multi-task learning (MTL) to improve performance for classification and regression tasks in different domains. The core of our method is an adversarial autoencoder that can: (1) learn to produce domain-invariant embeddings to reduce the difference between domains; (2) learn the data distribution for each domain and correctly perform data imputation on missing data. For MDL, we use the Maximum Mean Discrepancy (MMD) measure to align the domain distributions. For DI, we use an adversarial approach where a generator fill in information for missing data and a discriminator tries to distinguish between real and imputed values. Finally, using the universal feature representation in the embeddings, we train a classifier using MTL that given input from any domain, can predict labels for all domains. We demonstrate the superior performance of our approach compared to other state-of-art methods in three distinct settings, DG-DI in image recognition with unstructured data, MTL-DI in grade estimation with structured data and MDMTL-DI in a selection process using mixed data.

In multi-stage processes, decisions occur in an ordered sequence of stages. Early stages usually have more observations with general information (easier/cheaper to collect), while later stages have fewer observations but more specific data. This situation can be represented by a dual funnel structure, in which the sample size decreases from one stage to the other while the information increases. Training classifiers in this scenario is challenging since information in the early stages may not contain distinct patterns to learn (underfitting). In contrast, the small sample size in later stages can cause overfitting. We address both cases by introducing a framework that combines adversarial autoencoders (AAE), multi-task learning (MTL), and multi-label semi-supervised learning (MLSSL). We improve the decoder of the AAE with an MTL component so it can jointly reconstruct the original input and use feature nets to predict the features for the next stages. We also introduce a sequence constraint in the output of an MLSSL classifier to guarantee the sequential pattern in the predictions. Using real-world data from different domains (selection process, medical diagnosis), we show that our approach outperforms other state-of-the-art methods.

Machine-learning (ML) models are increasingly used today in making decisions that affect real people's lives, and, because of that, there is a huge need to ensure that the models and their decisions are interpretable by their human users. Motivated by this need, there has bee a lot of interest recently in the ML community in studying Interpretable models [18]. There is currently no consensus on what interpretability means, and no benchmarks for evaluating interpretability [5, 10]. The only consensus is that simpler models such as linear regression or decision trees are considered more interpretable than complex models like, say, deep neural nets. However, two general principles for approaching interpretability have emerged in the literature that are relevant to our paper.

"The funny thing about life is that it's temporary; that is to say, temporary in the'temporal' sense of the word, meaning that all living things and all that we do are subject to the precepts and effects of time." Many organisms perform best at certain hours of the day. The slug species Arion subfuscus, living in almost total darkness, knowing nothing about the Gregorian calendar, lays its eggs between the last week of August and the first week of September.1 Bees forage for nectar, knowing the best times to visit the best fields and the exact timing of nectar secretions for individual species of flowers. In the mid-20th century, the Austrian Nobel laureate Karl von Frisch provided enormous insights on honeybee communication and foraging time. He discovered that bees have internal clocks that tell them not only where the nectar is to be found but also precisely when that food will be ready. "I know of no other living creature," he wrote in his book on bee language, "that learns so easily as the bee when, according to its'internal clock,' to come to the table."2 Even without a light clue, the plants were able to tell time.

Machine learning in finance may work magic, even though there is no magic behind it (well, maybe just a little bit). Still, the success of machine learning project depends more on building efficient infrastructure, collecting suitable datasets, and applying the right algorithms. Machine learning is making significant inroads in the financial services industry. Let's see why financial companies should care, what solutions they can implement with AI and machine learning, and how exactly they can apply this technology. We can define machine learning (ML) as a subset of data science that uses statistical models to draw insights and make predictions. The chart below explains how AI, data science, and machine learning are related.

Machine learning applications in the legal field are numerous and diverse. In order to make contribution to both the machine learning community and the legal community, we have made efforts to create a model compatible with the classification of text sequences, valuing the interpretability of the results. The purpose of this paper is to classify legal proceedings in three possible status classes, which are (i) archived proceedings, (ii) active proceedings and (iii) suspended proceedings. Our approach is composed by natural language processing, supervised and unsupervised deep learning models and performed remarkably well in the classification task. Furthermore we had some insights regarding the patterns learned by the neural network applying tools to make the results more interpretable.

Recommender systems (RS) are increasingly present in our daily lives, especially since the advent of Big Data, which allows for storing all kinds of information about users' preferences. Personalized RS are successfully applied in platforms such as Netflix, Amazon or YouTube. However, they are missing in gastronomic platforms such as TripAdvisor, where moreover we can find millions of images tagged with users' tastes. This paper explores the potential of using those images as sources of information for modeling users' tastes and proposes an image-based classification system to obtain personalized recommendations, using a convolutional autoencoder as feature extractor. The proposed architecture will be applied to TripAdvisor data, using users' reviews that can be defined as a triad composed by a user, a restaurant, and an image of it taken by the user. Since the dataset is highly unbalanced, the use of data augmentation on the minority class is also considered in the experimentation. Results on data from three cities of different sizes (Santiago de Compostela, Barcelona and New York) demonstrate the effectiveness of using a convolutional autoencoder as feature extractor, instead of the standard deep features computed with convolutional neural networks.