Artificial general intelligence (AGI) refers to research aimed at tackling the full problem of artificial intelligence, that is, create truly intelligent agents. This sets it apart from most AI research which aims at solving relatively narrow domains, such as character recognition, motion planning, or increasing player satisfaction in games. But how do we know when an agent is truly intelligent? A common point of reference in the AGI community is Legg and Hutter's formal definition of universal intelligence, which has the appeal of simplicity and generality but is unfortunately incomputable. Games of various kinds are commonly used as benchmarks for "narrow" AI research, as they are considered to have many important properties. We argue that many of these properties carry over to the testing of general intelligence as well. We then sketch how such testing could practically be carried out. The central part of this sketch is an extension of universal intelligence to deal with finite time, and the use of sampling of the space of games expressed in a suitably biased game description language.

We present an application focused on the design of resilient long-reach passive optical networks. We specifically consider dual-parented networks whereby each customer must be connected to two metro sites via local exchange sites. An important property of such a placement is resilience to single metro node failure. The objective of the application is to determine the optimal position of a set of metro nodes such that the total optical fibre length is minimized. We prove that this problem is NP-Complete. We present two alternative combinatorial optimisation approaches to finding an optimal metro node placement using: a mixed integer linear programming (MIP) formulation of the problem; and, a hybrid approach that uses clustering as a preprocessing step. We consider a detailed case-study based on a network for Ireland. The hybrid approach scales well and finds solutions that are close to optimal, with a runtime that is two orders-of-magnitude better than the MIP model.

In this paper, we propose a novel policy iteration method, called dynamic policy programming (DPP), to estimate the optimal policy in the infinite-horizon Markov decision processes. We prove the finite-iteration and asymptotic l\infty-norm performance-loss bounds for DPP in the presence of approximation/estimation error. The bounds are expressed in terms of the l\infty-norm of the average accumulated error as opposed to the l\infty-norm of the error in the case of the standard approximate value iteration (AVI) and the approximate policy iteration (API). This suggests that DPP can achieve a better performance than AVI and API since it averages out the simulation noise caused by Monte-Carlo sampling throughout the learning process. We examine this theoretical results numerically by com- paring the performance of the approximate variants of DPP with existing reinforcement learning (RL) methods on different problem domains. Our results show that, in all cases, DPP-based algorithms outperform other RL methods by a wide margin.

We study a class of regularization methods used to learn a linear function from a finite set of examples. The regularizer is expressed as an infimum convolution which involves a set M of linear transformations (see equation (1) below). As we shall see, this regularizer generalizes, depending on the choice of the set M, the regularizers used by several learning algorithms, such as ridge regression, the Lasso, the group Lasso [22], multiple kernel learning [10], the group Lasso with overlap [6], and the regularizers in [16]. We give a bound on the Rademacher average of the linear function class associated with this regularizer. The result matches existing bounds in the above mentioned cases but also admits a novel, dimension free interpretation.

We consider the problem of fully unsupervised learning of grammatical (part-of-speech) categories from unlabeled text. The standard maximum-likelihood hidden Markov model for this task performs poorly, because of its weak inductive bias and large model capacity. We address this problem by refining the model and modifying the learning objective to control its capacity via para- metric and non-parametric constraints. Our approach enforces word-category association sparsity, adds morphological and orthographic features, and eliminates hard-to-estimate parameters for rare words. We develop an efficient learning algorithm that is not much more computationally intensive than standard training. We also provide an open-source implementation of the algorithm. Our experiments on five diverse languages (Bulgarian, Danish, English, Portuguese, Spanish) achieve significant improvements compared with previous methods for the same task.

Robots operating in domestic environments generally need to interact with articulated objects, such as doors, cabinets, dishwashers or fridges. In this work, we present a novel, probabilistic framework for modeling articulated objects as kinematic graphs. Vertices in this graph correspond to object parts, while edges between them model their kinematic relationship. In particular, we present a set of parametric and non-parametric edge models and how they can robustly be estimated from noisy pose observations. We furthermore describe how to estimate the kinematic structure and how to use the learned kinematic models for pose prediction and for robotic manipulation tasks. We finally present how the learned models can be generalized to new and previously unseen objects. In various experiments using real robots with different camera systems as well as in simulation, we show that our approach is valid, accurate and efficient. Further, we demonstrate that our approach has a broad set of applications, in particular for the emerging fields of mobile manipulation and service robotics.

The Blogs dataset is a subset of Recent years have resulted in several well motivated the Blogs06 [16] collection of blog posts from 06/12/2005 and carefully described studies coping with the problem to 21/02/2006. Only posts attracting more than 100 of opinion formation and its spreading [1]. This kind of comments were extracted, as these apparently initialised research usually aimed at qualitative descriptions of some non-trivial discussions. Both datasets have similar structures.

In order to give appropriate semantics to qualitative conditionals of the form "if A then normally B", ordinal conditional functions (OCFs) ranking the possible worlds according to their degree of plausibility can be used. An OCF accepting all conditionals of a knowledge base R can be characterized as the solution of a constraint satisfaction problem. We present a high-level, declarative approach using constraint logic programming techniques for solving this constraint satisfaction problem. In particular, the approach developed here supports the generation of all minimal solutions; these minimal solutions are of special interest as they provide a basis for model-based inference from R.

Statistical relational learning techniques have been successfully applied in a wide range of relational domains. In most of these applications, the human designers capitalized on their background knowledge by following a trial-and-error trajectory, where relational features are manually defined by a human engineer, parameters are learned for those features on the training data, the resulting model is validated, and the cycle repeats as the engineer adjusts the set of features. This paper seeks to streamline application development in large relational domains by introducing a light-weight approach that efficiently evaluates relational features on pieces of the relational graph that are streamed to it one at a time. We evaluate our approach on two social media tasks and demonstrate that it leads to more accurate models that are learned faster.

In this paper we present a proposal for a knowledge-based programming environment. In such an environment, declarative background knowledge, procedures, and concrete data are represented in suitable languages and combined in a flexible manner. This leads to a highly declarative programming style. We illustrate our approach on an example and report about our prototype implementation.