This paper proposes a novel solution to spam detection inspired by a model of the adaptive immune system known as the crossregulation model. We report on the testing of a preliminary algorithm on six e-mail corpora. We also compare our results statically and dynamically with those obtained by the Naive Bayes classifier and another binary classification method we developed previously for biomedical text-mining applications. We show that the cross-regulation model is competitive against those and thus promising as a bio-inspired algorithm for spam detection in particular, and binary classification in general.

The paper introduces the notion of off-line justification for Answer Set Programming (ASP). Justifications provide a graph-based explanation of the truth value of an atom w.r.t. a given answer set. The paper extends also this notion to provide justification of atoms during the computation of an answer set (on-line justification), and presents an integration of on-line justifications within the computation model of Smodels. Off-line and on-line justifications provide useful tools to enhance understanding of ASP, and they offer a basic data structure to support methodologies and tools for debugging answer set programs. A preliminary implementation has been developed in ASP-PROLOG. (To appear in Theory and Practice of Logic Programming (TPLP))

To appear in Theory and Practice of Logic Programming (TPLP) This paper develops a declarative language, P-log, that combines logical and probabilistic arguments in its reasoning. Answer Set Prolog is used as the logical foundation, while causal Bayes nets serve as a probabilistic foundation. We give several nontrivial examples and illustrate the use of P-log for knowledge representation and updating of knowledge. We argue that our approach to updates is more appealing than existing approaches. We give sufficiency conditions for the coherency of P-log programs and show that Bayes nets can be easily mapped to coherent P-log programs.

This philosophical paper explores the relation between modern scientific simulations and the future of the universe. We argue that a simulation of an entire universe will result from future scientific activity. This requires us to tackle the challenge of simulating open-ended evolution at all levels in a single simulation. The simulation should encompass not only biological evolution, but also physical evolution (a level below) and cultural evolution (a level above). The simulation would allow us to probe what would happen if we would "replay the tape of the universe" with the same or different laws and initial conditions. We also distinguish between real-world and artificial-world modelling. Assuming that intelligent life could indeed simulate an entire universe, this leads to two tentative hypotheses. Some authors have argued that we may already be in a simulation run by an intelligent entity. Or, if such a simulation could be made real, this would lead to the production of a new universe. This last direction is argued with a careful speculative philosophical approach, emphasizing the imperative to find a solution to the heat death problem in cosmology. The reader is invited to consult Annex 1 for an overview of the logical structure of this paper. -- Keywords: far future, future of science, ALife, simulation, realization, cosmology, heat death, fine-tuning, physical eschatology, cosmological natural selection, cosmological artificial selection, artificial cosmogenesis, selfish biocosm hypothesis, meduso-anthropic principle, developmental singularity hypothesis, role of intelligent life.

Shapley's impossibility result indicates that the two-person bargaining problem has no non-trivial ordinal solution with the traditional game-theoretic bargaining model. Although the result is no longer true for bargaining problems with more than two agents, none of the well known bargaining solutions are ordinal. Searching for meaningful ordinal solutions, especially for the bilateral bargaining problem, has been a challenging issue in bargaining theory for more than three decades. This paper proposes a logic-based ordinal solution to the bilateral bargaining problem. We argue that if a bargaining problem is modeled in terms of the logical relation of players' physical negotiation items, a meaningful bargaining solution can be constructed based on the ordinal structure of bargainers' preferences. We represent bargainers' demands in propositional logic and bargainers' preferences over their demands in total preorder. We show that the solution satisfies most desirable logical properties, such as individual rationality (logical version), consistency, collective rationality as well as a few typical game-theoretic properties, such as weak Pareto optimality and contraction invariance. In addition, if all players' demand sets are logically closed, the solution satisfies a fixed-point condition, which says that the outcome of a negotiation is the result of mutual belief revision. Finally, we define various decision problems in relation to our bargaining model and study their computational complexity.

We investigate the computational complexity of testing dominance and consistency in CP-nets. Previously, the complexity of dominance has been determined for restricted classes in which the dependency graph of the CP-net is acyclic. However, there are preferences of interest that define cyclic dependency graphs; these are modeled with general CP-nets. In our main results, we show here that both dominance and consistency for general CP-nets are PSPACE-complete. We then consider the concept of strong dominance, dominance equivalence and dominance incomparability, and several notions of optimality, and identify the complexity of the corresponding decision problems. The reductions used in the proofs are from STRIPS planning, and thus reinforce the earlier established connections between both areas.

Given i.i.d. observations of a random vector $X \in \mathbb{R}^p$, we study the problem of estimating both its covariance matrix $\Sigma^*$, and its inverse covariance or concentration matrix {$\Theta^* = (\Sigma^*)^{-1}$.} We estimate $\Theta^*$ by minimizing an $\ell_1$-penalized log-determinant Bregman divergence; in the multivariate Gaussian case, this approach corresponds to $\ell_1$-penalized maximum likelihood, and the structure of $\Theta^*$ is specified by the graph of an associated Gaussian Markov random field. We analyze the performance of this estimator under high-dimensional scaling, in which the number of nodes in the graph $p$, the number of edges $s$ and the maximum node degree $d$, are allowed to grow as a function of the sample size $n$. In addition to the parameters $(p,s,d)$, our analysis identifies other key quantities covariance matrix $\Sigma^*$; and (b) the $\ell_\infty$ operator norm of the sub-matrix $\Gamma^*_{S S}$, where $S$ indexes the graph edges, and $\Gamma^* = (\Theta^*)^{-1} \otimes (\Theta^*)^{-1}$; and (c) a mutual incoherence or irrepresentability measure on the matrix $\Gamma^*$ and (d) the rate of decay $1/f(n,\delta)$ on the probabilities $ \{|\hat{\Sigma}^n_{ij}- \Sigma^*_{ij}| > \delta \}$, where $\hat{\Sigma}^n$ is the sample covariance based on $n$ samples. Our first result establishes consistency of our estimate $\hat{\Theta}$ in the elementwise maximum-norm. This in turn allows us to derive convergence rates in Frobenius and spectral norms, with improvements upon existing results for graphs with maximum node degrees $d = o(\sqrt{s})$. In our second result, we show that with probability converging to one, the estimate $\hat{\Theta}$ correctly specifies the zero pattern of the concentration matrix $\Theta^*$.

This paper examines from an experimental perspective random forests, the increasingly used statistical method for classification and regression problems introduced by Leo Breiman in 2001. It first aims at confirming, known but sparse, advice for using random forests and at proposing some complementary remarks for both standard problems as well as high dimensional ones for which the number of variables hugely exceeds the sample size. But the main contribution of this paper is twofold: to provide some insights about the behavior of the variable importance index based on random forests and in addition, to propose to investigate two classical issues of variable selection. The first one is to find important variables for interpretation and the second one is more restrictive and try to design a good prediction model. The strategy involves a ranking of explanatory variables using the random forests score of importance and a stepwise ascending variable introduction strategy.

Regression is a very important method in engineering and science for the estimation of the dependencies between two or more variables on the basis of some given sample points. The best known regression method is certainly the parametric regression technique after Legendre and Gauss, which minimizes the squared error between a model - often a polynom - and the samples. The least squares method is fast and well suitable for strongly linearly correlated data, but seldom appropriate for high-dimensional problems with difficult, unknown, and nonlinear dependencies. For these problems, nonparametric regression techniques - like kernel or Nadaraya-Watson regression methods - are more suitable (Nadaraya [1964], Watson [1964]).

We present exact algorithms for identifying deterministic-actions' effects and preconditions in dynamic partially observable domains. They apply when one does not know the action model(the way actions affect the world) of a domain and must learn it from partial observations over time. Such scenarios are common in real world applications. They are challenging for AI tasks because traditional domain structures that underly tractability (e.g., conditional independence) fail there (e.g., world features become correlated). Our work departs from traditional assumptions about partial observations and action models. In particular, it focuses on problems in which actions are deterministic of simple logical structure and observation models have all features observed with some frequency. We yield tractable algorithms for the modified problem for such domains. Our algorithms take sequences of partial observations over time as input, and output deterministic action models that could have lead to those observations. The algorithms output all or one of those models (depending on our choice), and are exact in that no model is misclassified given the observations. Our algorithms take polynomial time in the number of time steps and state features for some traditional action classes examined in the AI-planning literature, e.g., STRIPS actions. In contrast, traditional approaches for HMMs and Reinforcement Learning are inexact and exponentially intractable for such domains. Our experiments verify the theoretical tractability guarantees, and show that we identify action models exactly. Several applications in planning, autonomous exploration, and adventure-game playing already use these results. They are also promising for probabilistic settings, partially observable reinforcement learning, and diagnosis.