We consider the problem of using a factor model we call {\em spike-and-slab sparse coding} (S3C) to learn features for a classification task. The S3C model resembles both the spike-and-slab RBM and sparse coding. Since exact inference in this model is intractable, we derive a structured variational inference procedure and employ a variational EM training algorithm. Prior work on approximate inference for this model has not prioritized the ability to exploit parallel architectures and scale to enormous problem sizes. We present an inference procedure appropriate for use with GPUs which allows us to dramatically increase both the training set size and the amount of latent factors. We demonstrate that this approach improves upon the supervised learning capabilities of both sparse coding and the ssRBM on the CIFAR-10 dataset. We evaluate our approach's potential for semi-supervised learning on subsets of CIFAR-10. We demonstrate state-of-the art self-taught learning performance on the STL-10 dataset and use our method to win the NIPS 2011 Workshop on Challenges In Learning Hierarchical Models' Transfer Learning Challenge.

Some aspects of the result of applying unit resolution on a cnf formula can be formalized as functions with domain a set of partial truth assignments. We are interested in two ways for computing such functions, depending on whether the result is the production of the empty clause or the assignment of a variable with a given truth value. We show that these two models can compute the same functions with formulae of polynomially related sizes, and we explain how this result is related to the cnf encoding of Boolean constraints.

The paper presents an ant colony optimization metaheuristic for collaborative planning. Collaborative planning is used to coordinate individual plans of self-interested decision makers with private information in order to increase the overall benefit of the coalition. The method consists of a new search graph based on encoded solutions. Distributed and private information is integrated via voting mechanisms and via a simple but effective collaborative local search procedure. The approach is applied to a distributed variant of the multi-level lot-sizing problem and evaluated by means of 352 benchmark instances from the literature. The proposed approach clearly outperforms existing approaches on the sets of medium and large sized instances. While the best method in the literature so far achieves an average deviation from the best known non-distributed solutions of 46 percent for the set of the largest instances, for example, the presented approach reduces the average deviation to only 5 percent.

Expert systems use human knowledge often stored as rules within the computer to solve problems that generally would entail human intelligence. Today, with information systems turning out to be more pervasive and with the myriad advances in information technologies, automating computer fault diagnosis is becoming so fundamental that soon every enterprise has to endorse it. This paper proposes an expert system called Expert PC Troubleshooter for diagnosing computer problems. The system is composed of a user interface, a rule-base, an inference engine, and an expert interface. Additionally, the system features a fuzzy-logic module to troubleshoot POST beep errors, and an intelligent agent that assists in the knowledge acquisition process. The proposed system is meant to automate the maintenance, repair, and operations (MRO) process, and free-up human technicians from manually performing routine, laborious, and timeconsuming maintenance tasks. As future work, the proposed system is to be parallelized so as to boost its performance and speed-up its various operations.

The interactive partially observable Markov decision process (I-POMDP) is a recently developed framework which extends the POMDP to the multi-agent setting by including agent models in the state space. This paper argues for formulating the problem of an agent learning interactively from a human teacher as an I-POMDP, where the agent \emph{programming} to be learned is captured by random variables in the agent's state space, all \emph{signals} from the human teacher are treated as observed random variables, and the human teacher, modeled as a distinct agent, is explicitly represented in the agent's state space. The main benefits of this approach are: i. a principled action selection mechanism, ii. a principled belief update mechanism, iii. support for the most common teacher \emph{signals}, and iv. the anticipated production of complex beneficial interactions. The proposed formulation, its benefits, and several open questions are presented.

In this paper we study the covering numbers of the space of convex and uniformly bounded functions in multi-dimension. We find optimal upper and lower bounds for the $\epsilon$-covering number of $\C([a, b]^d, B)$, in the $L_p$-metric, $1 \le p < \infty$, in terms of the relevant constants, where $d \geq 1$, $a < b \in \mathbb{R}$, $B>0$, and $\C([a,b]^d, B)$ denotes the set of all convex functions on $[a, b]^d$ that are uniformly bounded by $B$. We summarize previously known results on covering numbers for convex functions and also provide alternate proofs of some known results. Our results have direct implications in the study of rates of convergence of empirical minimization procedures as well as optimal convergence rates in the numerous convexity constrained function estimation problems.

In a deterministic world, a planning agent can be certain of the consequences of its planned sequence of actions. Not so, however, in dynamic, stochastic domains where Markov decision processes are commonly used. Unfortunately these suffer from the `curse of dimensionality': if the state space is a Cartesian product of many small sets (`dimensions'), planning is exponential in the number of those dimensions. Our new technique exploits the intuitive strategy of selectively ignoring various dimensions in different parts of the state space. The resulting non-uniformity has strong implications, since the approximation is no longer Markovian, requiring the use of a modified planner. We also use a spatial and temporal proximity measure, which responds to continued planning as well as movement of the agent through the state space, to dynamically adapt the abstraction as planning progresses. We present qualitative and quantitative results across a range of experimental domains showing that an agent exploiting this novel approximation method successfully finds solutions to the planning problem using much less than the full state space. We assess and analyse the features of domains which our method can exploit.

Relational data representations have become an increasingly important topic due to the recent proliferation of network datasets (e.g., social, biological, information networks) and a corresponding increase in the application of statistical relational learning (SRL) algorithms to these domains. In this article, we examine a range of representation issues for graph-based relational data. Since the choice of relational data representation--for the nodes, links, and features--can dramatically affect the capabilities of SRL algorithms, we survey approaches and opportunities for relational representation transformation designed to improve the performance of these algorithms. This leads us to introduce an intuitive taxonomy for data representation transformations in relational domains that incorporates link transformation and node transformation as symmetric representation tasks. In particular, the transformation tasks for both nodes and links include (i) predicting their existence, (ii) predicting their label or type, (iii) estimating their weight or importance, and (iv) systematically constructing their relevant features. We motivate our taxonomy through detailed examples and use it to survey and compare competing approaches for each of these tasks. We also discuss general conditions for transforming links, nodes, and features. Finally, we highlight challenges that remain to be addressed.

Informledge System (ILS) is a knowledge network with autonomous nodes and intelligent links that integrate and structure the pieces of knowledge. In this paper, we aim to put forward the link dynamics involved in intelligent processing of information in ILS. There has been advancement in knowledge management field which involve managing information in databases from a single domain. ILS works with information from multiple domains stored in distributed way in the autonomous nodes termed as Knowledge Network Node (KNN). Along with the concept under consideration, KNNs store the processed information linking concepts and processors leading to the appropriate processing of information.

We consider infinite-horizon $\gamma$-discounted Markov Decision Processes, for which it is known that there exists a stationary optimal policy. We consider the algorithm Value Iteration and the sequence of policies $\pi_1,...,\pi_k$ it implicitely generates until some iteration $k$. We provide performance bounds for non-stationary policies involving the last $m$ generated policies that reduce the state-of-the-art bound for the last stationary policy $\pi_k$ by a factor $\frac{1-\gamma}{1-\gamma^m}$. In particular, the use of non-stationary policies allows to reduce the usual asymptotic performance bounds of Value Iteration with errors bounded by $\epsilon$ at each iteration from $\frac{\gamma}{(1-\gamma)^2}\epsilon$ to $\frac{\gamma}{1-\gamma}\epsilon$, which is significant in the usual situation when $\gamma$ is close to 1. Given Bellman operators that can only be computed with some error $\epsilon$, a surprising consequence of this result is that the problem of "computing an approximately optimal non-stationary policy" is much simpler than that of "computing an approximately optimal stationary policy", and even slightly simpler than that of "approximately computing the value of some fixed policy", since this last problem only has a guarantee of $\frac{1}{1-\gamma}\epsilon$.