Classifiers that achieve demographic balance by explicitly using protected attributes such as race or gender are often politically or culturally controversial due to their lack of individual fairness, i.e. individuals with similar qualifications will receive different outcomes. Individually and group fair decision criteria can produce counter-intuitive results, e.g. that the optimal constrained boundary may reject intuitively better candidates due to demographic imbalance in similar candidates. Both approaches can be seen as introducing individual resentment, where some individuals would have received a better outcome if they either belonged to a different demographic class and had the same qualifications, or if they remained in the same class but had objectively worse qualifications (e.g. lower test scores). We show that both forms of resentment can be avoided by using monotonically constrained machine learning models to create individually fair, demographically balanced classifiers.

While deep learning models become more widespread, their ability to handle unseen data and generalize for any scenario is yet to be challenged. In medical imaging, there is a high heterogeneity of distributions among images based on the equipment that generate them and their parametrization. This heterogeneity triggers a common issue in machine learning called domain shift, which represents the difference between the training data distribution and the distribution of where a model is employed. A high domain shift tends to implicate in a poor performance from models. In this work, we evaluate the extent of domain shift on three of the largest datasets of chest radiographs. We show how training and testing with different datasets (e.g. training in ChestX-ray14 and testing in CheXpert) drastically affects model performance, posing a big question over the reliability of deep learning models.

User simulators are essential for training reinforcement learning (RL) based dialog models. However, building a good user simulator that models real user behaviors is challenging. We propose a method of standardizing user simulator building that can be used by the community to compare dialog system quality using the same set of user simulators fairly. We present implementations of six user simulators trained with different dialog planning and generation methods. We then calculate a set of automatic metrics to evaluate the quality of these simulators both directly and indirectly. We also ask human users to assess the simulators directly and indirectly by rating the simulated dialogs and interacting with the trained systems. This paper presents a comprehensive evaluation framework for user simulator study and provides a better understanding of the pros and cons of different user simulators, as well as their impacts on the trained systems. 1 1 Introduction Reinforcement Learning has gained more and more attention in dialog system training because it treats the dialog planning as a sequential decision problem and focuses on long-term rewards (Su et al., 2017). However, RL requires interaction with the environment, and obtaining real human users to interact with the system is both time-consuming and labor-intensive. Therefore, building user simulators to interact with the system before deployment to real users becomes an economical choice (Williams et al., 2017; Li et al., 2016). But the performance of the user simulator has a direct impact on the trained RL policy.* Equal contribution. 1 The code and data are released at https://github.

W e present a systematic study of biases in natural language generation (NLG) by analyzing text generated from prompts that contain mentions of different demographic groups. In this work, we introduce the notion of the regard towards a demographic, use the varying levels of regard towards different demographics as a defining metric for bias in NLG, and analyze the extent to which sentiment scores are a relevant proxy metric for regard. To this end, we collect strategically-generated text from language models and manually annotate the text with both sentiment and regard scores. Additionally, we build an automatic regard classifier through transfer learning, so that we can analyze biases in unseen text. Together, these methods reveal the extent of the biased nature of language model generations. Our analysis provides a study of biases in NLG, bias metrics and correlated human judgments, and empirical evidence on the usefulness of our annotated dataset.

Reasoning over plots by question answering (QA) is a challenging machine learning task at the intersection of vision, language processing, and reasoning. Existing synthetic datasets (FigureQA, DVQA) do not model variability in data labels, real-valued data, or complex reasoning questions. Consequently, proposed models for these datasets do not fully address the challenge of reasoning over plots. We propose PlotQA with 8.1 million question-answer pairs over 220,000 plots with data from real-world sources and questions based on crowd-sourced question templates. 26% of the questions in PlotQA have answers that are not in a fixed vocabulary, requiring reasoning capabilities. Analysis of existing models on PlotQA reveals that a hybrid model is required: Specific questions are answered better by choosing the answer from a fixed vocabulary or by extracting it from a predicted bounding box in the plot, while other questions are answered with a table question-answering engine which is fed with a structured table extracted by visual element detection. For the latter, we propose the VOES pipeline and combine it with SAN-VQA to form a hybrid model SAN-VOES. On the DVQA dataset, SAN-VOES model has an accuracy of 58%, significantly improving on highest reported accuracy of 46%. On the PlotQA dataset, SAN-VOES has an accuracy of 54%, which is the highest amongst all the models we trained. Analysis of each module in the VOES pipeline reveals that further improvement in accuracy requires more accurate visual element detection.

Bushfires pose a significant threat to Australia's regional areas. To minimise risk and increase resilience, communities need robust evacuation strategies that account for people's likely behaviour both before and during a bushfire. Agent-based modelling (ABM) offers a practical way to simulate a range of bushfire evacuation scenarios. However, the ABM should reflect the diversity of possible human responses in a given community. The Belief-Desire-Intention (BDI) cognitive model captures behaviour in a compact representation that is understandable by domain experts. Within a BDI-ABM simulation, individual BDI agents can be assigned profiles that determine their likely behaviour. Over a population of agents their collective behaviour will characterise the community response. These profiles are drawn from existing human behaviour research and consultation with emergency services personnel and capture the expected behaviours of identified groups in the population, both prior to and during an evacuation. A realistic representation of each community can then be formed, and evacuation scenarios within the simulation can be used to explore the possible impact of population structure on outcomes. It is hoped that this will give an improved understanding of the risks associated with evacuation, and lead to tailored evacuation plans for each community to help them prepare for and respond to bushfire.

In critical decision-making scenarios, optimizing accuracy can lead to a biased classifier, hence past work recommends enforcing group-based fairness metrics in addition to maximizing accuracy. However, doing so exposes the classifier to another kind of bias called infra-marginality. This refers to individual-level bias where some individuals/subgroups can be worse off than under simply optimizing for accuracy. For instance, a classifier implementing race-based parity may significantly disadvantage women of the advantaged race. To quantify this bias, we propose a general notion of $\eta$-infra-marginality that can be used to evaluate the extent of this bias. We prove theoretically that, unlike other fairness metrics, infra-marginality does not have a trade-off with accuracy: high accuracy directly leads to low infra-marginality. This observation is confirmed through empirical analysis on multiple simulated and real-world datasets. Further, we find that maximizing group fairness often increases infra-marginality, suggesting the consideration of both group-level fairness and individual-level infra-marginality. However, measuring infra-marginality requires knowledge of the true distribution of individual-level outcomes correctly and explicitly. We propose a practical method to measure infra-marginality, and a simple algorithm to maximize group-wise accuracy and avoid infra-marginality.

The dawn of the 5G era is at hand, and the world is on the cusp of massive change. From the tech sector to the entertainment industry, to politics, medicine and communications -- fifth-generation cellular network technology promises to transform daily life in both tangible and far-reaching ways. Perhaps most importantly, it also holds the potential to create a brighter future for people around the world. Such was the theme of Rakuten CEO Mickey Mikitani's opening keynote address at Rakuten Optimism in Yokohama, Japan last month -- the company's largest-ever group event. Speaking in front of a capacity crowd in a 5000-seat convention hall that held communications, tech, finance and retail industry leaders and business partners, Mikitani described his vision for the impact of 5G on a broad range of fields, including the rise of AI and machine learning, cashless payments, medical advances, the telcomms industry (into which Rakuten will launch the world's first end-to-end cloud-native mobile network later this year) and more.

Ready to make an impact on the global automation revolution? McKinsey Global Institute ranked "automation of knowledge" work as #2 in their top 12 disruptive technologies that will transform life, business, and the global economy. Automation Anywhere is the market leader in driving the adoption of robotic process automation technology across leading Fortune 1000 and other companies across more than 90 countries. At Automation Anywhere, we are passionate in our belief that Digital Colleagues will free people to create, think, discover, and ultimately build great companies. As a Strategic Account Manager you have a proven sales record of successful software sales to the largest Enterprises.

Toby Walsh, a professor at the University of New South Wales in Sydney, is one of Australia's leading experts on artificial intelligence. He and other experts have released a report outlining the promises, and ethical pitfalls, of the country's embrace of A.I. Recently, Dr. Walsh, 55, has been working with the Campaign to Stop Killer Robots, a coalition of scientists and human rights leaders seeking to halt the development of autonomous robotic weapons. We spoke briefly at the annual meeting of the American Association for the Advancement of Science, where he was making a presentation, and then for two hours via telephone. Below is an edited version of those conversations. It happened incrementally, beginning around 2013.