We present a method for the reconstruction of networks, based on the order of nodes visited by a stochastic branching process. Our algorithm reconstructs a network of minimal size that ensures consistency with the data. Crucially, we show that global consistency with the data can be achieved through purely local considerations, inferring the neighbourhood of each node in turn. The optimisation problem solved for each individual node can be reduced to a Set Covering Problem, which is known to be NP-hard but can be approximated well in practice. We then extend our approach to account for noisy data, based on the Minimum Description Length principle. We demonstrate our algorithms on synthetic data, generated by an SIR-like epidemiological model.

We introduce a framework for representing a variety of interesting problems as inference over the execution of probabilistic model programs. We represent a "solution" to such a problem as a guide program which runs alongside the model program and influences the model program's random choices, leading the model program to sample from a different distribution than from its priors. Ideally the guide program influences the model program to sample from the posteriors given the evidence. We show how the KL- divergence between the true posterior distribution and the distribution induced by the guided model program can be efficiently estimated (up to an additive constant) by sampling multiple executions of the guided model program. In addition, we show how to use the guide program as a proposal distribution in importance sampling to statistically prove lower bounds on the probability of the evidence and on the probability of a hypothesis and the evidence. We can use the quotient of these two bounds as an estimate of the conditional probability of the hypothesis given the evidence. We thus turn the inference problem into a heuristic search for better guide programs.

Standard hybrid learners that use domain knowledge require stronger knowledge that is hard and expensive to acquire. However, weaker domain knowledge can benefit from prior knowledge while being cost effective. Weak knowledge in the form of feature relative importance (FRI) is presented and explained. Feature relative importance is a real valued approximation of a feature's importance provided by experts. Advantage of using this knowledge is demonstrated by IANN, a modified multilayer neural network algorithm. IANN is a very simple modification of standard neural network algorithm but attains significant performance gains. Experimental results in the field of molecular biology show higher performance over other empirical learning algorithms including standard backpropagation and support vector machines. IANN performance is even comparable to a theory refinement system KBANN that uses stronger domain knowledge. This shows Feature relative importance can improve performance of existing empirical learning algorithms significantly with minimal effort.

Model selection in clustering requires (i) to specify a suitable clustering principle and (ii) to control the model order complexity by choosing an appropriate number of clusters depending on the noise level in the data. We advocate an information theoretic perspective where the uncertainty in the measurements quantizes the set of data partitionings and, thereby, induces uncertainty in the solution space of clusterings. A clustering model, which can tolerate a higher level of fluctuations in the measurements than alternative models, is considered to be superior provided that the clustering solution is equally informative. This tradeoff between \emph{informativeness} and \emph{robustness} is used as a model selection criterion. The requirement that data partitionings should generalize from one data set to an equally probable second data set gives rise to a new notion of structure induced information.

We propose automatically learning probabilistic Hierarchical Task Networks (pHTNs) in order to capture a user's preferences on plans, by observing only the user's behavior. HTNs are a common choice of representation for a variety of purposes in planning, including work on learning in planning. Our contributions are (a) learning structure and (b) representing preferences. In contrast, prior work employing HTNs considers learning method preconditions (instead of structure) and representing domain physics or search control knowledge (rather than preferences). Initially we will assume that the observed distribution of plans is an accurate representation of user preference, and then generalize to the situation where feasibility constraints frequently prevent the execution of preferred plans. In order to learn a distribution on plans we adapt an Expectation-Maximization (EM) technique from the discipline of (probabilistic) grammar induction, taking the perspective of task reductions as productions in a context-free grammar over primitive actions. To account for the difference between the distributions of possible and preferred plans we subsequently modify this core EM technique, in short, by rescaling its input.

Brain-Like Stochastic Search (BLiSS) refers to this task: given a family of utility functions U(u,A), where u is a vector of parameters or task descriptors, maximize or minimize U with respect to u, using networks (Option Nets) which input A and learn to generate good options u stochastically. This paper discusses why this is crucial to brain-like intelligence (an area funded by NSF) and to many applications, and discusses various possibilities for network design and training. The appendix discusses recent research, relations to work on stochastic optimization in operations research, and relations to engineering-based approaches to understanding neocortex.

We consider the empirical risk minimization problem for linear supervised learning, with regularization by structured sparsity-inducing norms. These are defined as sums of Euclidean norms on certain subsets of variables, extending the usual $\ell_1$-norm and the group $\ell_1$-norm by allowing the subsets to overlap. This leads to a specific set of allowed nonzero patterns for the solutions of such problems. We first explore the relationship between the groups defining the norm and the resulting nonzero patterns, providing both forward and backward algorithms to go back and forth from groups to patterns. This allows the design of norms adapted to specific prior knowledge expressed in terms of nonzero patterns. We also present an efficient active set algorithm, and analyze the consistency of variable selection for least-squares linear regression in low and high-dimensional settings.

Paraphrasing methods recognize, generate, or extract phrases, sentences, or longer natural language expressions that convey almost the same information. Textual entailment methods, on the other hand, recognize, generate, or extract pairs of natural language expressions, such that a human who reads (and trusts) the first element of a pair would most likely infer that the other element is also true. Paraphrasing can be seen as bidirectional textual entailment and methods from the two areas are often similar. Both kinds of methods are useful, at least in principle, in a wide range of natural language processing applications, including question answering, summarization, text generation, and machine translation. We summarize key ideas from the two areas by considering in turn recognition, generation, and extraction methods, also pointing to prominent articles and resources.

Grounding is the task of reducing a first-order theory and finite domain to an equivalent propositional theory. It is used as preprocessing phase in many logic-based reasoning systems. Such systems provide a rich first-order input language to a user and can rely on efficient propositional solvers to perform the actual reasoning. Besides a first-order theory and finite domain, the input for grounders contains in many applications also additional data. By exploiting this data, the size of the grounder's output can often be reduced significantly. A common practice to improve the efficiency of a grounder in this context is by manually adding semantically redundant information to the input theory, indicating where and when the grounder should exploit the data. In this paper we present a method to compute and add such redundant information automatically. Our method therefore simplifies the task of writing input theories that can be grounded efficiently by current systems. We first present our method for classical first-order logic (FO) theories. Then we extend it to FO(ID), the extension of FO with inductive definitions, which allows for more concise and comprehensive input theories. We discuss implementation issues and experimentally validate the practical applicability of our method.

Vast amounts of text on the Web are unstructured and ungrammatical, such as classified ads, auction listings, forum postings, etc. We call such text posts. Despite their inconsistent structure and lack of grammar, posts are full of useful information. This paper presents work on semi-automatically building tables of relational information, called reference sets, by analyzing such posts directly. Reference sets can be applied to a number of tasks such as ontology maintenance and information extraction. Our reference-set construction method starts with just a small amount of background knowledge, and constructs tuples representing the entities in the posts to form a reference set. We also describe an extension to this approach for the special case where even this small amount of background knowledge is impossible to discover and use. To evaluate the utility of the machine-constructed reference sets, we compare them to manually constructed reference sets in the context of reference-set-based information extraction. Our results show the reference sets constructed by our method outperform manually constructed reference sets. We also compare the reference-set-based extraction approach using the machine-constructed reference set to supervised extraction approaches using generic features. These results demonstrate that using machine-constructed reference sets outperforms the supervised methods, even though the supervised methods require training data.