NLP impacts how firms provide products to users, content individuals receive through search and social media, and how While artificial intelligence provides the backbone for many tools individuals interact with news and emails. Despite the growing people use around the world, recent work has brought to attention importance of NLP algorithms in shaping our lives, recently scholars, that the algorithms powering AI are not free of politics, stereotypes, policymakers, and the business community have raised the and bias. While most work in this area has focused on the ways alarm of how gender and racial biases may be baked into these algorithms. in which AI can exacerbate existing inequalities and discrimination, Because they are trained on human data, the algorithms very little work has studied how governments actively shape themselves can replicate implicit and explicit human biases and training data. We describe how censorship has affected the development aggravate discrimination [6, 8, 39]. Additionally, training data that of Wikipedia corpuses, text data which are regularly used over-represents a subset of the population may do a worse job for pre-trained inputs into NLP algorithms. We show that word embeddings at predicting outcomes for other groups in the population [13].

Counterfactual explanations provide a potentially significant solution to the Explainable AI (XAI) problem, but good, native counterfactuals have been shown to rarely occur in most datasets. Hence, the most popular methods generate synthetic counterfactuals using blind perturbation. However, such methods have several shortcomings: the resulting counterfactuals (i) may not be valid data-points (they often use features that do not naturally occur), (ii) may lack the sparsity of good counterfactuals (if they modify too many features), and (iii) may lack diversity (if the generated counterfactuals are minimal variants of one another). We describe a method designed to overcome these problems, one that adapts native counterfactuals in the original dataset, to generate sparse, diverse synthetic counterfactuals from naturally occurring features. A series of experiments are reported that systematically explore parametric variations of this novel method on common datasets to establish the conditions for optimal performance.

Japan's Finance Ministry is promoting a program to introduce artificial intelligence and other cutting-edge technology to help customs agents crack down on increased smuggling of illegal drugs. The program aims to establish the world's most advanced inspection capabilities according to a plan announced by the ministry in June last year. As part of the program, AI-based analysis will be used to sort through huge amounts of data on past cases of unlawful import activity, looking for patterns of false descriptions on such matters as price, quantity and weight of goods on import declarations. The information will help pin down importers who should be watched more closely. To prevent the importing of illegal drugs, the ministry has already started testing a prototype nuclear quadrupole resonance (NQR) device that uses AI to check X-rayed items and identify possible drug smuggling.

Last year Anthony Levandowski pleaded guilty to one count of stealing materials from Google, where he was an engineer for its self-driving car efforts before leaving to found a startup that he sold to Uber. The judge said during his sentencing that his theft of documents and emails constituted the "biggest trade secret crime I have ever seen." Now, on the last day of Donald Trump's administration, Trump issued a series of pardons -- the Department of Justice has more information on how those work here -- and commutations that covered people who worked on his campaign like Steve Bannon and Elliott Broidy, as well as Levandowski. A press release from the White House noted tech billionaires Peter Thiel and Palmer Luckey were among those supporting a pardon for Levandowski, and it makes the claim that this engineer "paid a significant price for his actions and plans to devote his talents to advance the public good." It also noted that his plea covered only a single charge, omitting mention of the 33 charges he'd been indicted on.

Predictions obtained by, e.g., artificial neural networks have a high accuracy but humans often perceive the models as black boxes. Insights about the decision making are mostly opaque for humans. Particularly understanding the decision making in highly sensitive areas such as healthcare or finance, is of paramount importance. The decision-making behind the black boxes requires it to be more transparent, accountable, and understandable for humans. This survey paper provides essential definitions, an overview of the different principles and methodologies of explainable Supervised Machine Learning (SML). We conduct a state-of-the-art survey that reviews past and recent explainable SML approaches and classifies them according to the introduced definitions. Finally, we illustrate principles by means of an explanatory case study and discuss important future directions.

Artificial Intelligence (AI) has come to prominence as one of the major components of our society, with applications in most aspects of our lives. In this field, complex and highly nonlinear machine learning models such as ensemble models, deep neural networks, and Support Vector Machines have consistently shown remarkable accuracy in solving complex tasks. Although accurate, AI models often are "black boxes" which we are not able to understand. Relying on these models has a multifaceted impact and raises significant concerns about their transparency. Applications in sensitive and critical domains are a strong motivational factor in trying to understand the behavior of black boxes. We propose to address this issue by providing an interpretable layer on top of black box models by aggregating "local" explanations. We present GLocalX, a "local-first" model agnostic explanation method. Starting from local explanations expressed in form of local decision rules, GLocalX iteratively generalizes them into global explanations by hierarchically aggregating them. Our goal is to learn accurate yet simple interpretable models to emulate the given black box, and, if possible, replace it entirely. We validate GLocalX in a set of experiments in standard and constrained settings with limited or no access to either data or local explanations. Experiments show that GLocalX is able to accurately emulate several models with simple and small models, reaching state-of-the-art performance against natively global solutions. Our findings show how it is often possible to achieve a high level of both accuracy and comprehensibility of classification models, even in complex domains with high-dimensional data, without necessarily trading one property for the other. This is a key requirement for a trustworthy AI, necessary for adoption in high-stakes decision making applications.

We study the impact of fiscal revenue shocks on local fiscal policy. We focus on the very volatile revenues from the immovable property gains tax in the canton of Zurich, Switzerland, and analyze fiscal behavior following large and rare positive and negative revenue shocks. We apply causal machine learning strategies and implement the post-double-selection LASSO estimator to identify the causal effect of revenue shocks on public finances. We show that local policymakers overall predominantly smooth fiscal shocks. However, we also find some patterns consistent with fiscal conservatism, where positive shocks are smoothed, while negative ones are mitigated by spending cuts.

Machine Learning or Artificial Intelligence algorithms have gained considerable scrutiny in recent times owing to their propensity towards imitating and amplifying existing prejudices in society. This has led to a niche but growing body of work that identifies and attempts to fix these biases. A first step towards making these algorithms more fair is designing metrics that measure unfairness. Most existing work in this field deals with either a binary view of fairness (protected vs. unprotected groups) or politically defined categories (race or gender). Such categorization misses the important nuance of intersectionality - biases can often be amplified in subgroups that combine membership from different categories, especially if such a subgroup is particularly underrepresented in historical platforms of opportunity. In this paper, we discuss why fairness metrics need to be looked at under the lens of intersectionality, identify existing work in intersectional fairness, suggest a simple worst case comparison method to expand the definitions of existing group fairness metrics to incorporate intersectionality, and finally conclude with the social, legal and political framework to handle intersectional fairness in the modern context.

Deep-predictive-coding networks (DPCNs) are hierarchical, generative models that rely on feed-forward and feed-back connections to modulate latent feature representations of stimuli in a dynamic and context-sensitive manner. A crucial element of DPCNs is a forward-backward inference procedure to uncover sparse states of a dynamic model, which are used for invariant feature extraction. However, this inference and the corresponding backwards network parameter updating are major computational bottlenecks. They severely limit the network depths that can be reasonably implemented and easily trained. We therefore propose a optimization strategy, with better empirical and theoretical convergence, based on accelerated proximal gradients. We demonstrate that the ability to construct deeper DPCNs leads to receptive fields that capture well the entire notions of objects on which the networks are trained. This improves the feature representations. It yields completely unsupervised classifiers that surpass convolutional and convolutional-recurrent autoencoders and are on par with convolutional networks trained in a supervised manner. This is despite the DPCNs having orders of magnitude fewer parameters.

The right to be forgotten has been legislated in many countries but the enforcement in machine learning would cause unbearable costs: companies may need to delete whole models trained from massive resources because of single individual requests. Existing works propose to remove the influence of the requested datums on the learned models via its influence function which is no longer naturally well-defined in Bayesian inference. To address this problem, this paper proposes a {\it Bayesian inference forgetting} (BIF) framework to extend the applicable domain to Bayesian inference. In the BIF framework, we develop forgetting algorithms for variational inference and Markov chain Monte Carlo. We show that our algorithms can provably remove the influence of single datums on the learned models. Theoretical analysis demonstrates that our algorithms have guaranteed generalizability. Experiments of Gaussian mixture models on the synthetic dataset and Bayesian neural networks on the Fashion-MNIST dataset verify the feasibility of our methods. The source code package is available at \url{https://github.com/fshp971/BIF}.