My friend Robert Burton, a neurologist and author, wanted to share a song with me last year, and sent me a link to an NPR Tiny Desk Concert. "It's wonderful to see truly new and inspiring music," he wrote. I clicked open the link to a band who appeared to have journeyed from their mountain village in Russia to busk for tourists in the city square. Three women wore long white wedding dresses, thick strands of bead necklaces, and Cossack hats that towered from their heads like minarets of black wool. They played, respectively, a cello, djembe drum, and floor tom drum. They were joined by an accordion player who could pass for a bearded hipster from Brooklyn. The accordionist was the first to sing. A bray of syllables erupted from him like an exorcism. A steady drumbeat followed and then the women commanded the singing. Their vocals ranged from yodels to yips, whoops to whispers. At first turbulence reigned, as if the women were singing different songs at each other. But soon their voices blended into a melody that curled like a river.

An essential part of argumentation-based reasoning is to identify arguments in favor and against a statement or query, select the acceptable ones, and then determine whether or not the original statement should be accepted. We present here an abstract framework that considers two independent forms of argument interaction--support and conflict--and is able to represent distinctive information associated with these arguments. This information can enable additional actions such as: (i) a more in-depth analysis of the relations between the arguments; (ii) a representation of the user's posture to help in focusing the argumentative process, optimizing the values of attributes associated with certain arguments; and (iii) an enhancement of the semantics taking advantage of the availability of richer information about argument acceptability. Thus, the classical semantic definitions are enhanced by analyzing a set of postulates they satisfy. Finally, a polynomial-time algorithm to perform the labeling process is introduced, in which the argument interactions are considered.

Effective conservation actions require effective population monitoring. However, accurately counting animals in the wild to inform conservation decision-making is difficult. Monitoring populations through image sampling has made data collection cheaper, wide-reaching and less intrusive but created a need to process and analyse this data efficiently. Counting animals from such data is challenging, particularly when densely packed in noisy images. Attempting this manually is slow and expensive, while traditional computer vision methods are limited in their generalisability. Deep learning is the state-of-the-art method for many computer vision tasks, but it has yet to be properly explored to count animals. To this end, we employ deep learning, with a density-based regression approach, to count fish in low-resolution sonar images. We introduce a large dataset of sonar videos, deployed to record wild mullet schools (Mugil liza), with a subset of 500 labelled images. We utilise abundant unlabelled data in a self-supervised task to improve the supervised counting task. For the first time in this context, by introducing uncertainty quantification, we improve model training and provide an accompanying measure of prediction uncertainty for more informed biological decision-making. Finally, we demonstrate the generalisability of our proposed counting framework through testing it on a recent benchmark dataset of high-resolution annotated underwater images from varying habitats (DeepFish). From experiments on both contrasting datasets, we demonstrate our network outperforms the few other deep learning models implemented for solving this task. By providing an open-source framework along with training data, our study puts forth an efficient deep learning template for crowd counting aquatic animals thereby contributing effective methods to assess natural populations from the ever-increasing visual data.

Concepts similar to emergence have been used since antiquity, but we lack an agreed definition of emergence. Still, emergence has been identified as one of the features of complex systems. Most would agree on the statement "life is complex". Thus, understanding emergence and complexity should benefit the study of living systems. It can be said that life emerges from the interactions of complex molecules. But how useful is this to understand living systems? Artificial life (ALife) has been developed in recent decades to study life using a synthetic approach: build it to understand it. ALife systems are not so complex, be them soft (simulations), hard (robots), or wet (protocells). Then, we can aim at first understanding emergence in ALife, for then using this knowledge in biology. I argue that to understand emergence and life, it becomes useful to use information as a framework. In a general sense, emergence can be defined as information that is not present at one scale but is present at another scale. This perspective avoids problems of studying emergence from a materialistic framework, and can be useful to study self-organization and complexity.

In this paper, we propose a new method to perform data augmentation in a reliable way in the High Dimensional Low Sample Size (HDLSS) setting using a geometry-based variational autoencoder. Our approach combines a proper latent space modeling of the VAE seen as a Riemannian manifold with a new generation scheme which produces more meaningful samples especially in the context of small data sets. The proposed method is tested through a wide experimental study where its robustness to data sets, classifiers and training samples size is stressed. It is also validated on a medical imaging classification task on the challenging ADNI database where a small number of 3D brain MRIs are considered and augmented using the proposed VAE framework. In each case, the proposed method allows for a significant and reliable gain in the classification metrics. For instance, balanced accuracy jumps from 66.3% to 74.3% for a state-of-the-art CNN classifier trained with 50 MRIs of cognitively normal (CN) and 50 Alzheimer disease (AD) patients and from 77.7% to 86.3% when trained with 243 CN and 210 AD while improving greatly sensitivity and specificity metrics.

Artificial Intelligence (AI) can augment and sometimes even replace human cognition. Inspired by efforts to value human agency alongside productivity, we discuss the benefits of solving Citizen Science (CS) tasks with Hybrid Intelligence (HI), a synergetic mixture of human and artificial intelligence. Currently there is no clear framework or methodology on how to create such an effective mixture. Due to the unique participant-centered set of values and the abundance of tasks drawing upon both human common sense and complex 21st century skills, we believe that the field of CS offers an invaluable testbed for the development of HI and human-centered AI of the 21st century, while benefiting CS as well. In order to investigate this potential, we first relate CS to adjacent computational disciplines. Then, we demonstrate that CS projects can be grouped according to their potential for HI-enhancement by examining two key dimensions: the level of digitization and the amount of knowledge or experience required for participation. Finally, we propose a framework for types of human-AI interaction in CS based on established criteria of HI. This "HI lens" provides the CS community with an overview of several ways to utilize the combination of AI and human intelligence in their projects. It also allows the AI community to gain ideas on how developing AI in CS projects can further their own field.

We present PyTorch Geometric Temporal a deep learning framework combining state-of-the-art machine learning algorithms for neural spatiotemporal signal processing. The main goal of the library is to make temporal geometric deep learning available for researchers and machine learning practitioners in a unified easy-to-use framework. PyTorch Geometric Temporal was created with foundations on existing libraries in the PyTorch eco-system, streamlined neural network layer definitions, temporal snapshot generators for batching, and integrated benchmark datasets. These features are illustrated with a tutorial-like case study. Experiments demonstrate the predictive performance of the models implemented in the library on real world problems such as epidemiological forecasting, ridehail demand prediction and web-traffic management. Our sensitivity analysis of runtime shows that the framework can potentially operate on web-scale datasets with rich temporal features and spatial structure.

TOKYO – April 22, 2021 – According to research findings by NTT DATA, senior financial services executives overwhelmingly agree that implementing Artificial Intelligence (AI) will be the key competitive driver of success over the next few years. In fact, 83% agree that AI is creating new ways to differentiate offerings and win customers, driven by access to unique data sets; however, obstacles remain and adoption lags. Respondents report technology implementation (55%), creating new business startup culture in an established business (51%), and organizational skill changes (43%) are all top AI challenges to implementing personalized proactive services. Despite these very real obstacles, financial institutions (FIs) must find a way to overcome them. Especially considering the COVID-19 pandemic, consumers are increasingly looking to digital finance solutions and apps that anticipate their needs and proactively offer financial guidance.

The L3DAS21 Challenge is aimed at encouraging and fostering collaborative research on machine learning for 3D audio signal processing, with particular focus on 3D speech enhancement (SE) and 3D sound localization and detection (SELD). Alongside with the challenge, we release the L3DAS21 dataset, a 65 hours 3D audio corpus, accompanied with a Python API that facilitates the data usage and results submission stage. Usually, machine learning approaches to 3D audio tasks are based on single-perspective Ambisonics recordings or on arrays of single-capsule microphones. We propose, instead, a novel multichannel audio configuration based multiple-source and multiple-perspective Ambisonics recordings, performed with an array of two first-order Ambisonics microphones. To the best of our knowledge, it is the first time that a dual-mic Ambisonics configuration is used for these tasks. We provide baseline models and results for both tasks, obtained with state-of-the-art architectures: FaSNet for SE and SELDNet for SELD. This report is aimed at providing all needed information to participate in the L3DAS21 Challenge, illustrating the details of the L3DAS21 dataset, the challenge tasks and the baseline models.

The underspecification of most machine learning pipelines means that we cannot rely solely on validation performance to assess the robustness of deep learning systems to naturally occurring distribution shifts. Instead, making sure that a neural network can generalize across a large number of different situations requires to understand the specific way in which it solves a task. In this work, we propose to study this problem from a geometric perspective with the aim to understand two key characteristics of neural network solutions in underspecified settings: how is the geometry of the learned function related to the data representation? And, are deep networks always biased towards simpler solutions, as conjectured in recent literature? We show that the way neural networks handle the underspecification of these problems is highly dependent on the data representation, affecting both the geometry and the complexity of the learned predictors. Our results highlight that understanding the architectural inductive bias in deep learning is fundamental to address the fairness, robustness, and generalization of these systems.