Hutter's universal artificial intelligence (AI) showed how to define future AI systems by mathematical equations. Here we adapt those equations to define a self-modeling framework, where AI systems learn models of their own calculations of future values. Hutter discussed the possibility that AI agents may maximize rewards by corrupting the source of rewards in the environment. Here we propose a way to avoid such corruption in the self-modeling framework. This paper fits in the context of my book Ethical Artificial Intelligence.

Given the fast rise of increasingly autonomous artificial agents and robots, a key acceptability criterion will be the possible moral implications of their actions. In particular, intelligent persuasive systems (systems designed to influence humans via communication) constitute a highly sensitive topic because of their intrinsically social nature. Still, ethical studies in this area are rare and tend to focus on the output of the required action. Instead, this work focuses on the persuasive acts themselves (e.g. “is it morally acceptable that a machine lies or appeals to the emotions of a person to persuade her, even if for a good end?”). Exploiting a behavioral approach, based on human assessment of moral dilemmas – i.e. without any prior assumption of underlying ethical theories – this paper reports on a set of experiments. These experiments address the type of persuader (human or machine), the strategies adopted (purely argumentative, appeal to positive emotions, appeal to negative emotions, lie) and the circumstances. Findings display no differences due to the agent, mild acceptability for persuasion and reveal that truth-conditional reasoning (i.e. argument validity) is a significant dimension affecting subjects’ judgment. Some implications for the design of intelligent persuasive systems are discussed.

Coding values (or preferences) directly into an artificial agent is a very challenging task, while value selection (or value-learning, or value-loading) allows agents to learn values from their programmers, other humans or their environments in an interactive way. However, there is a conflict between agents learning their future values and following their current values, which motivates agents to manipulate the value selection process. This paper establishes the conditions under which motivated value selection is an issue for some types of agents, and presents an example of an `indifferent' agent that avoids it entirely. This poses and solves an issue which has not to the author's knowledge been formally addressed in the literature.

Algorithm selection (AS) techniques — which involve choosing from a set of algorithms the one expected to solve a given problem instance most efficiently — have substantially improved the state-of-the-art in solving many prominent AI problems, such as SAT, CSP, ASP, MAXSAT, and QBF.Although several AS procedures have been introduced,not too surprisingly, none of them dominates all others across all AS scenarios.Furthermore, these procedures have parameters whose optimal values vary across AS scenarios.This holds specifically for the machine learning techniques that form the core of current AS proceduresand for their hyperparameters. Therefore, to successfully apply AS to new problems, algorithms and benchmark sets, two questions need to be answered:(i) how to select an AS approach and (ii) how to set its parameters effectively.We address both of these problems simultaneously by using automated algorithm configuration.Specifically, we demonstrate that we can use algorithm configurators to automatically configure clasp folio 2,which implements a large variety of different AS approaches and their respective parameters in a single highly parameterized algorithm framework.We demonstrate that this approach, dubbed auto folio, can significantly improve the performance of clasp folio 2 on 11 out of the 12 scenarios from the Algorithm Selection Library and leads to new state-of-the-art algorithm selectors for 8 of these scenarios.

We study optimal estimation for sparse principal component analysis when the number of non-zero elements is small but on the same order as the dimension of the data. We employ approximate message passing (AMP) algorithm and its state evolution to analyze what is the information theoretically minimal mean-squared error and the one achieved by AMP in the limit of large sizes. For a special case of rank one and large enough density of non-zeros Deshpande and Montanari [1] proved that AMP is asymptotically optimal. We show that both for low density and for large rank the problem undergoes a series of phase transitions suggesting existence of a region of parameters where estimation is information theoretically possible, but AMP (and presumably every other polynomial algorithm) fails. The analysis of the large rank limit is particularly instructive.

A fundamental challenge in calcium imaging has been to infer the timing of action potentials from the measured noisy calcium fluorescence traces. We systematically evaluate a range of spike inference algorithms on a large benchmark dataset recorded from varying neural tissue (V1 and retina) using different calcium indicators (OGB-1 and GCamp6). We show that a new algorithm based on supervised learning in flexible probabilistic models outperforms all previously published techniques, setting a new standard for spike inference from calcium signals. Importantly, it performs better than other algorithms even on datasets not seen during training. Future data acquired in new experimental conditions can easily be used to further improve its spike prediction accuracy and generalization performance. Finally, we show that comparing algorithms on artificial data is not informative about performance on real population imaging data, suggesting that a benchmark dataset may greatly facilitate future algorithmic developments.

Mixture modelling involves explaining some observed evidence using a combination of probability distributions. The crux of the problem is the inference of an optimal number of mixture components and their corresponding parameters. This paper discusses unsupervised learning of mixture models using the Bayesian Minimum Message Length (MML) criterion. To demonstrate the effectiveness of search and inference of mixture parameters using the proposed approach, we select two key probability distributions, each handling fundamentally different types of data: the multivariate Gaussian distribution to address mixture modelling of data distributed in Euclidean space, and the multivariate von Mises-Fisher (vMF) distribution to address mixture modelling of directional data distributed on a unit hypersphere. The key contributions of this paper, in addition to the general search and inference methodology, include the derivation of MML expressions for encoding the data using multivariate Gaussian and von Mises-Fisher distributions, and the analytical derivation of the MML estimates of the parameters of the two distributions. Our approach is tested on simulated and real world data sets. For instance, we infer vMF mixtures that concisely explain experimentally determined three-dimensional protein conformations, providing an effective null model description of protein structures that is central to many inference problems in structural bioinformatics. The experimental results demonstrate that the performance of our proposed search and inference method along with the encoding schemes improve on the state of the art mixture modelling techniques.

Efficiently querying Description Logic (DL) ontologies is becoming a vital task in various data-intensive DL applications. Considered as a basic service for answering object queries over DL ontologies, instance checking can be realized by using the most specific concept (MSC) method, which converts instance checking into subsumption problems. This method, however, loses its simplicity and efficiency when applied to large and complex ontologies, as it tends to generate very large MSC's that could lead to intractable reasoning. In this paper, we propose a revision to this MSC method for DL SHI, allowing it to generate much simpler and smaller concepts that are specific-enough to answer a given query. With independence between computed MSC's, scalability for query answering can also be achieved by distributing and parallelizing the computations. An empirical evaluation shows the efficacy of our revised MSC method and the significant efficiency achieved when using it for answering object queries.

This article proposes a solution to the problem of obtaining plausibility information, which is necessary to perform belief revision: given a sequence of revisions, together with their results, derive a possible initial order that has generated them; this is different from the usual assumption of starting from an all-equal initial order and modifying it by a sequence of revisions. Four semantics for iterated revision are considered: natural, restrained, lexicographic and reinforcement. For each, a necessary and sufficient condition to the existence of an order generating a given history of revisions and results is proved. Complexity is proved coNP complete in all cases but one (reinforcement revision with unbounded sequence length).

Finding satisfying assignments for the variables involved in a set of constraints can be cast as a (bounded) model generation problem: search for (bounded) models of a theory in some logic. The state-of-the-art approach for bounded model generation for rich knowledge representation languages like ASP and FO(.) and a CSP modeling language such as Zinc, is ground-and-solve: reduce the theory to a ground or propositional one and apply a search algorithm to the resulting theory. An important bottleneck is the blow-up of the size of the theory caused by the grounding phase. Lazily grounding the theory during search is a way to overcome this bottleneck. We present a theoretical framework and an implementation in the context of the FO(.) knowledge representation language. Instead of grounding all parts of a theory, justifications are derived for some parts of it. Given a partial assignment for the grounded part of the theory and valid justifications for the formulas of the non-grounded part, the justifications provide a recipe to construct a complete assignment that satisfies the non-grounded part. When a justification for a particular formula becomes invalid during search, a new one is derived; if that fails, the formula is split in a part to be grounded and a part that can be justified. Experimental results illustrate the power and generality of this approach.