Combining the concepts of individual and group fairness, we search for discrimination by matching individuals in different protected groups to each other, and comparing their classifier outcomes. Specifically, we formulate a GAN-based approximation of the optimal transport mapping, and use it to translate the distribution of one protected group to that of another, returning pairs of in-distribution samples that statistically correspond to one another. We then define the flipset: the set of individuals whose classifier output changes post-translation, which intuitively corresponds to the set of people who were harmed because of their protected group membership. To shed light on why the model treats a given subgroup differently, we introduce the transparency report: a ranking of features that are most associated with the model's behavior on the flipset. We show that this provides a computationally inexpensive way to identify subgroups that are harmed by model discrimination, including in cases where the model satisfies population-level group fairness criteria.

Artificial neural network training with stochastic gradient descent can be destabilized by "bad batches" with high losses. This is often problematic for training with small batch sizes, high order loss functions or unstably high learning rates. To stabilize learning, we have developed adaptive learning rate clipping (ALRC) to limit backpropagated losses to a number of standard deviations above their running means. ALRC is designed to complement existing learning algorithms: Our algorithm is computationally inexpensive, can be applied to any loss function or batch size, is robust to hyperparameter choices and does not affect backpropagated gradient distributions. Experiments with CIFAR-10 supersampling show that ALCR decreases errors for unstable mean quartic error training while stable mean squared error training is unaffected. We also show that ALRC decreases unstable mean squared errors for partial scanning transmission electron micrograph completion. Our source code is publicly available at https://github.com/Jeffrey-Ede/ALRC

As the capabilities and pervasiveness of machine learning (ML) and artificial intelligence (AI) increasingly affect society, there is increasing concern about the safety of such systems, i.e. the potential of accidental harm from implementation errors and unintended consequences in ML algorithms. As a result, there has been increasing interest in the nascent field of AI safety [1, 2, 3, 4, 5, 6], which seeks to understand and solve the technical challenges in developing and deploying AI that does what it is intended to do. The purpose of this chapter is to explore how the study of AI safety intersects with that of evolutionary computation (EC), to both highlight an exciting and important set of safety problems within EC, and to suggest that evolution and EC have important insights that could benefit the general study of AI safety. To frame the problem of AI safety, we adopt the framework of Amodei et al. [1], which defines AI safety as concerned with accidents in ML systems, and defines five problems within three broad categories of issues: (1) specifying the wrong objective function, (2) making safe and efficient use of a true but expensive objective (e.g.

In the last five years, private companies, research institutions as well as public sector organisations have issued principles and guidelines for ethical AI, yet there is debate about both what constitutes "ethical AI" and which ethical requirements, technical standards and best practices are needed for its realization. To investigate whether a global agreement on these questions is emerging, we mapped and analyzed the current corpus of principles and guidelines on ethical AI. Our results reveal a global convergence emerging around five ethical principles (transparency, justice and fairness, non-maleficence, responsibility and privacy), with substantive divergence in relation to how these principles are interpreted; why they are deemed important; what issue, domain or actors they pertain to; and how they should be implemented. Our findings highlight the importance of integrating guideline-development efforts with substantive ethical analysis and adequate implementation strategies.

Deep learning based data-driven approaches have been successfully applied in various image understanding applications ranging from object recognition, semantic segmentation to visual question answering. However, the lack of knowledge integration as well as higher-level reasoning capabilities with the methods still pose a hindrance. In this work, we present a brief survey of a few representative reasoning mechanisms, knowledge integration methods and their corresponding image understanding Figure 1: The diagram shows the information hierarchy for applications developed by various groups images and the knowledge associated with each level of information. of researchers, approaching the problem from a variety of angles. Furthermore, we discuss upon key efforts on integrating external knowledge with neural paper is to present a survey of recent works (including a few networks. Taking cues from these efforts, we of our works) in image understanding where knowledge and conclude by discussing potential pathways to improve reasoning plays an important role.

Sequential decision making in the presence of uncertainty and stochastic dynamics gives rise to distributions over state/action trajectories in reinforcement learning (RL) and optimal control problems. This observation has led to a variety of connections between RL and inference in probabilistic graphical models (PGMs). Here we explore a different dimension to this relationship, examining reinforcement learning using the tools and abstractions of statistical physics. The central object in the statistical physics abstraction is the idea of a partition function $\mathcal{Z}$, and here we construct a partition function from the ensemble of possible trajectories that an agent might take in a Markov decision process. Although value functions and $Q$-functions can be derived from this partition function and interpreted via average energies, the $\mathcal{Z}$-function provides an object with its own Bellman equation that can form the basis of alternative dynamic programming approaches. Moreover, when the MDP dynamics are deterministic, the Bellman equation for $\mathcal{Z}$ is linear, allowing direct solutions that are unavailable for the nonlinear equations associated with traditional value functions. The policies learned via these $\mathcal{Z}$-based Bellman updates are tightly linked to Boltzmann-like policy parameterizations. In addition to sampling actions proportionally to the exponential of the expected cumulative reward as Boltzmann policies would, these policies take entropy into account favoring states from which many outcomes are possible.

In LMMS has two useful properties: 1) uses contextual particular, it focuses on polysemous words which word embeddings to produce sense embeddings, have been hard to represent as embeddings due and 2) covers a large set of over 117K to the meaning conflation deficiency (Camacho-senses from WordNet 3.0. The first property allows Collados and Pilehvar, 2018). The task's objective for comparing precomputed sense embeddings is to detect if target words occurring in a pair of against contextual word embeddings generated sentences carry the same meaning.

Trajectory replanning for quadrotors is essential to enable fully autonomous flight in unknown environments. Hierarchical motion planning frameworks, which combine path planning with path parameterization, are popular due to their time efficiency. However, the path planning cannot properly deal with non-static initial states of the quadrotor, which may result in non-smooth or even dynamically infeasible trajectories. In this paper, we present an efficient kinodynamic replanning framework by exploiting the advantageous properties of the B-spline, which facilitates dealing with the non-static state and guarantees safety and dynamical feasibility. Our framework starts with an efficient B-spline-based kinodynamic (EBK) search algorithm which finds a feasible trajectory with minimum control effort and time. To compensate for the discretization induced by the EBK search, an elastic optimization (EO) approach is proposed to refine the control point placement to the optimal location. Systematic comparisons against the state-of-the-art are conducted to validate the performance. Comprehensive onboard experiments using two different vision-based quadrotors are carried out showing the general applicability of the framework.

In Reinforcement Learning we look for meaning in the flow of input/output information. If we do not find meaning, the information flow is not more than noise to us. Before we are able to find meaning, we should first learn how to discover and identify objects. What is an object? In this article we will demonstrate that an object is an event-driven model. These models are a generalization of action-driven models. In Markov Decision Process we have an action-driven model which changes its state at each step. The advantage of event-driven models is their greater sustainability as they change their states only upon the occurrence of particular events. These events may occur very rarely, therefore the state of the event-driven model is much more predictable.

Liquidation is the process of selling a large number of shares of one stock sequentially within a given time frame, taking into consideration the costs arising from market impact and a trader's risk aversion. The main challenge in optimizing liquidation is to find an appropriate modeling system that can incorporate the complexities of the stock market and generate practical trading strategies. In this paper, we propose to use multi-agent deep reinforcement learning model, which better captures high-level complexities comparing to various machine learning methods, such that agents can learn how to make the best selling decisions. First, we theoretically analyze the Almgren and Chriss model and extend its fundamental mechanism so it can be used as the multi-agent trading environment. Our work builds the foundation for future multi-agent environment trading analysis. Secondly, we analyze the cooperative and competitive behaviours between agents by adjusting the reward functions for each agent, which overcomes the limitation of single-agent reinforcement learning algorithms. Finally, we simulate trading and develop an optimal trading strategy with practical constraints by using a reinforcement learning method, which shows the capabilities of reinforcement learning methods in solving realistic liquidation problems.