The study of the social impact of automated decision making has focused largely on issues of fairness at the point of decision, evaluating the fairness (with respect to a population) of a sequence or pipeline of decisions, or examining the dynamics of a game between the decision-maker and the decision subject. What is missing from this study is an examination of precarity: a term coined by Judith Butler to describe an unstable state of existence in which negative decisions can have ripple effects on one's well-being. Such ripple effects are not captured by changes in income or wealth alone or by one decision alone. To study precarity, we must reorient our frame of reference away from the decision-maker and towards the decision subject; away from aggregates of decisions over a population and towards aggregates of decisions (for an individual) over time. An individual who lives with higher precarity is more affected and less able to recover by the same negative decision than another with low precarity. Thus including only the direct impact of a single decision or a few decisions is insufficient to judge if that system was fair. However, precarity is not an attribute of an individual; it is a result of being subject to greater risks and fewer supports, in addition to starting off at a less secure position. Precarity is impacted by racism, sexism, ableism, heterosexism, and other systems of oppression, and an individual's intersectional identity may put one at greater risk in society, subject to a lower income for the same job, less able to build wealth even at the same income level, and less able to recover from harm.

During the first weeks of February, we asked recipients of our Data and AI Newsletters to participate in a survey on AI adoption in the enterprise. We were interested in answering two questions. First, we wanted to understand how the use of AI grew in the past year. We were also interested in the practice of AI: how developers work, what techniques and tools they use, what their concerns are, and what development practices are in place. The most striking result is the sheer number of respondents. In our 2020 survey, which reached the same audience, we had 1,239 responses. This year, we had a total of 5,154. After eliminating 1,580 respondents who didn't complete the survey, we're left with 3,574 responses--almost three times as many as last year.

In this paper, we present a new objective prediction model for synthetic speech naturalness. It can be used to evaluate Text-To-Speech or Voice Conversion systems and works language independently. The model is trained end-to-end and based on a CNN-LSTM network that previously showed to give good results for speech quality estimation. We trained and tested the model on 16 different datasets, such as from the Blizzard Challenge and the Voice Conversion Challenge. Further, we show that the reliability of deep learning-based naturalness prediction can be improved by transfer learning from speech quality prediction models that are trained on objective POLQA scores. The proposed model is made publicly available and can, for example, be used to evaluate different TTS system configurations.

Currently, the most widespread neural network architecture for training language models is the so called BERT which led to improvements in various NLP tasks. In general, the larger the number of parameters in a BERT model, the better the results obtained in these NLP tasks. Unfortunately, the memory consumption and the training duration drastically increases with the size of these models, though. In this article, we investigate various training techniques of smaller BERT models and evaluate them on five public German NER tasks of which two are introduced by this article. We combine different methods from other BERT variants like ALBERT, RoBERTa, and relative positional encoding. In addition, we propose two new fine-tuning techniques leading to better performance: CSE-tagging and a modified form of LCRF. Furthermore, we introduce a new technique called WWA which reduces BERT memory usage and leads to a small increase in performance.

Deep probabilistic generative models have achieved incredible success in many fields of application. Among such models, variational autoencoders (VAEs) have proved their ability in modeling a generative process by learning a latent representation of the input. In this paper, we propose a novel VAE defined in the quaternion domain, which exploits the properties of quaternion algebra to improve performance while significantly reducing the number of parameters required by the network. The success of the proposed quaternion VAE with respect to traditional VAEs relies on the ability to leverage the internal relations between quaternion-valued input features and on the properties of second-order statistics which allow to define the latent variables in the augmented quaternion domain. In order to show the advantages due to such properties, we define a plain convolutional VAE in the quaternion domain and we evaluate its performance with respect to its real-valued counterpart on the CelebA face dataset.

Vulnerability detection has always been the most important task in the field of software security. With the development of technology, in the face of massive source code, automated analysis and detection of vulnerabilities has become a current research hotspot. For special text files such as source code, using some of the hottest NLP technologies to build models and realize the automatic analysis and detection of source code has become one of the most anticipated studies in the field of vulnerability detection. This article does a brief survey of some recent new documents and technologies, such as CodeBERT, and summarizes the previous technologies.

It is known that the human visual system performs a hierarchical information process in which early vision cues (or primitives) are fused in the visual cortex to compose complex shapes and descriptors. While different aspects of the process have been extensively studied, as the lens adaptation or the feature detection, some other,as the feature fusion, have been mostly left aside. In this work we elaborate on the fusion of early vision primitives using generalizations of the Choquet integral, and novel aggregation operators that have been extensively studied in recent years. We propose to use generalizations of the Choquet integral to sensibly fuse elementary edge cues, in an attempt to model the behaviour of neurons in the early visual cortex. Our proposal leads to a full-framed edge detection algorithm, whose performance is put to the test in state-of-the-art boundary detection datasets.

Monocular 3D object detection is an important task for autonomous driving considering its advantage of low cost. It is much more challenging compared to conventional 2D case due to its inherent ill-posed property, which is mainly reflected on the lack of depth information. Recent progress on 2D detection offers opportunities to better solving this problem. However, it is non-trivial to make a general adapted 2D detector work in this 3D task. In this technical report, we study this problem with a practice built on fully convolutional single-stage detector and propose a general framework FCOS3D. Specifically, we first transform the commonly defined 7-DoF 3D targets to image domain and decouple it as 2D and 3D attributes. Then the objects are distributed to different feature levels with the consideration of their 2D scales and assigned only according to the projected 3D-center for training procedure. Furthermore, the center-ness is redefined with a 2D Guassian distribution based on the 3D-center to fit the 3D target formulation. All of these make this framework simple yet effective, getting rid of any 2D detection or 2D-3D correspondence priors. Our solution achieves 1st place out of all the vision-only methods in the nuScenes 3D detection challenge of NeurIPS 2020. Code and models are released at https://github.com/open-mmlab/mmdetection3d.

Teamwork isn't just a human characteristic: Colonies of army ants will form living'scaffolding' to protect members from falling. The insects are blind and have no designated leader but, according to new research, they're able to use simple behavioral rules to develop these safety structures without the need for direct communication. Once a scaffold was built, worker ants were almost 100 percent protected from falling off steep inclines. Understanding how they design such complex structures could help engineers development self-healing materials and swarm robotics, researchers said. Army ants in Central American rainforests will build scaffolds out of their body to help them traverse steep terrain.

Recent machine-learning approaches to deterministic search and domain-independent planning employ policy learning to speed up search. Unfortunately, when attempting to solve a search problem by successively applying a policy, no guarantees can be given on solution quality. The problem of how to effectively use a learned policy within a bounded-suboptimal search algorithm remains largely as an open question. In this paper, we propose various ways in which such policies can be integrated into Focal Search, assuming that the policy is a neural network classifier. Furthermore, we provide mathematical foundations for some of the resulting algorithms. To evaluate the resulting algorithms over a number of policies with varying accuracy, we use synthetic policies which can be generated for a target accuracy for problems where the search space can be held in memory. We evaluate our focal search variants over three benchmark domains using our synthetic approach, and on the 15-puzzle using a neural network learned using 1.5 million examples. We observe that \emph{Discrepancy Focal Search}, which we show expands the node which maximizes an approximation of the probability that its corresponding path is a prefix of an optimal path, obtains, in general, the best results in terms of runtime and solution quality.