The use of deep neural networks (DNNs) in safety-critical applications like mobile health and autonomous driving is challenging due to numerous model-inherent shortcomings. These shortcomings are diverse and range from a lack of generalization over insufficient interpretability to problems with malicious inputs. Cyber-physical systems employing DNNs are therefore likely to suffer from safety concerns. In recent years, a zoo of state-of-the-art techniques aiming to address these safety concerns has emerged. This work provides a structured and broad overview of them. We first identify categories of insufficiencies to then describe research activities aiming at their detection, quantification, or mitigation. Our paper addresses both machine learning experts and safety engineers: The former ones might profit from the broad range of machine learning topics covered and discussions on limitations of recent methods. The latter ones might gain insights into the specifics of modern ML methods. We moreover hope that our contribution fuels discussions on desiderata for ML systems and strategies on how to propel existing approaches accordingly.

We present the Zero Resource Speech Challenge 2021, which asks participants to learn a language model directly from audio, without any text or labels. The challenge is based on the Libri-light dataset, which provides up to 60k hours of audio from English audio books without any associated text. We provide a pipeline baseline system consisting on an encoder based on contrastive predictive coding (CPC), a quantizer ($k$-means) and a standard language model (BERT or LSTM). The metrics evaluate the learned representations at the acoustic (ABX discrimination), lexical (spot-the-word), syntactic (acceptability judgment) and semantic levels (similarity judgment). We present an overview of the eight submitted systems from four groups and discuss the main results.

Table Structure Recognition is an essential part of end-to-end tabular data extraction in document images. The recent success of deep learning model architectures in computer vision remains to be non-reflective in table structure recognition, largely because extensive datasets for this domain are still unavailable while labeling new data is expensive and time-consuming. Traditionally, in computer vision, these challenges are addressed by standard augmentation techniques that are based on image transformations like color jittering and random cropping. As demonstrated by our experiments, these techniques are not effective for the task of table structure recognition. In this paper, we propose TabAug, a re-imagined Data Augmentation technique that produces structural changes in table images through replication and deletion of rows and columns. It also consists of a data-driven probabilistic model that allows control over the augmentation process. To demonstrate the efficacy of our approach, we perform experimentation on ICDAR 2013 dataset where our approach shows consistent improvements in all aspects of the evaluation metrics, with cell-level correct detections improving from 92.16% to 96.11% over the baseline.

This paper studies linear convergence of the subspace constrained mean shift (SCMS) algorithm, a well-known algorithm for identifying a density ridge defined by a kernel density estimator. By arguing that the SCMS algorithm is a special variant of a subspace constrained gradient ascent (SCGA) algorithm with an adaptive step size, we derive linear convergence of such SCGA algorithm. While the existing research focuses mainly on density ridges in the Euclidean space, we generalize density ridges and the SCMS algorithm to directional data. In particular, we establish the stability theorem of density ridges with directional data and prove the linear convergence of our proposed directional SCMS algorithm.

Prediction of diabetes and its various complications has been studied in a number of settings, but a comprehensive overview of problem setting for diabetes prediction and care management has not been addressed in the literature. In this document we seek to remedy this omission in literature with an encompassing overview of diabetes complication prediction as well as situating this problem in the context of real world healthcare management. We illustrate various problems encountered in real world clinical scenarios via our own experience with building and deploying such models. In this manuscript we illustrate a Machine Learning (ML) framework for addressing the problem of predicting Type 2 Diabetes Mellitus (T2DM) together with a solution for risk stratification, intervention and management. These ML models align with how physicians think about disease management and mitigation, which comprises these four steps: Identify, Stratify, Engage, Measure.

Over the last years, machine learning techniques have been applied to more and more application domains, including software engineering and, especially, software quality assurance. Important application domains have been, e.g., software defect prediction or test case selection and prioritization. The ability to predict which components in a large software system are most likely to contain the largest numbers of faults in the next release helps to better manage projects, including early estimation of possible release delays, and affordably guide corrective actions to improve the quality of the software. However, developing robust fault prediction models is a challenging task and many techniques have been proposed in the literature. Closely related to estimating defect-prone parts of a software system is the question of how to select and prioritize test cases, and indeed test case prioritization has been extensively researched as a means for reducing the time taken to discover regressions in software. In this survey, we discuss various approaches in both fault prediction and test case prioritization, also explaining how in recent studies deep learning algorithms for fault prediction help to bridge the gap between programs' semantics and fault prediction features. We also review recently proposed machine learning methods for test case prioritization (TCP), and their ability to reduce the cost of regression testing without negatively affecting fault detection capabilities.

In many urban areas, traffic load and noise pollution are constantly increasing. Automated systems for traffic monitoring are promising countermeasures, which allow to systematically quantify and predict local traffic flow in order to to support municipal traffic planning decisions. In this paper, we present a novel open benchmark dataset, containing 2.5 hours of stereo audio recordings of 4718 vehicle passing events captured with both high-quality sE8 and medium-quality MEMS microphones. This dataset is well suited to evaluate the use-case of deploying audio classification algorithms to embedded sensor devices with restricted microphone quality and hardware processing power. In addition, this paper provides a detailed review of recent acoustic traffic monitoring (ATM) algorithms as well as the results of two benchmark experiments on vehicle type classification and direction of movement estimation using four state-of-the-art convolutional neural network architectures.

With current AI technologies, harm done by AIs is limited to power that we put directly in their control. As said in [59], "For Narrow AIs, safety failures are at the same level of importance as in general cybersecurity, but for AGI it is fundamentally different." Despite AGI (artificial general intelligence) still being well out of reach, the nature of AI catastrophes has already changed in the past two decades. Automated systems are now not only malfunctioning in isolation, they are interacting with humans and with each other in real time. This shift has made traditional systems analysis more difficult, as AI has more complexity and autonomy than software has before. In response to this, we analyze how risks associated with complex control systems have been managed historically and the patterns in contemporary AI failures to what kinds of risks are created from the operation of any AI system. We present a framework for analyzing AI systems before they fail to understand how they change the risk landscape of the systems they are embedded in, based on conventional system analysis and open systems theory as well as AI safety principles. Finally, we present suggested measures that should be taken based on an AI system's properties. Several case studies from different domains are given as examples of how to use the framework and interpret its results.

"The biology of mind bridges the sciences -- concerned with the natural world -- and the humanities -- concerned with the meaning of human experience." Welcome to Part 3 of this new series exploring artificial general intelligence (AGI). If you missed Part 1 or Part 2, check them out; part 1 covers what AGI is, and part 2 is a brief overview of cognitive science for AI folk. This week we will introduce important concepts in philosophy of mind that I think every computer scientist, AI/ML researcher, or AGI enthusiast should know. The concept of minds--their nature, their implementation, their applications, etc.--are of huge interests to AGI researchers, and even anyone remotely interested in AI; arguably, this is the entire job of an AI/AGI researcher: creating artificial minds (some are just more narrow then others).

The following paper represents the beginning of a long and productive line of work on robust statistics in high dimensions. While robust statistics has long been studied, going back at least to Tukey,6 the recent revival centers on algorithmic questions that were largely unaddressed by the earlier statistical work. Robust statistics centers on the question of how to extract information from data that may have been corrupted in some way. The most common form of robustness, also considered here, is robust to outliers: some fraction of the data has been removed and replaced with arbitrary, erroneous points. A familiar instance of robust statistics is using the median instead of the mean, since the median is less sensitive to extreme points, while in contrast a single overly large value could completely skew the mean.