We consider the inverse reinforcement learning problem, that is, the problem of learning from, and then predicting or mimicking a controller based on state/action data. We propose a statistical model for such data, derived from the structure of a Markov decision process. Adopting a Bayesian approach to inference, we show how latent variables of the model can be estimated, and how predictions about actions can be made, in a unified framework. A new Markov chain Monte Carlo (MCMC) sampler is devised for simulation from the posterior distribution. This step includes a parameter expansion step, which is shown to be essential for good convergence properties of the MCMC sampler. As an illustration, the method is applied to learning a human controller.

Compressed sensing (CS) is an important theory for sub-Nyquist sampling and recovery of compressible data. Recently, it has been extended by Pham and Venkatesh to cope with the case where corruption to the CS data is modeled as impulsive noise. The new formulation, termed as robust CS, combines robust statistics and CS into a single framework to suppress outliers in the CS recovery. To solve the newly formulated robust CS problem, Pham and Venkatesh suggested a scheme that iteratively solves a number of CS problems, the solutions from which converge to the true robust compressed sensing solution. However, this scheme is rather inefficient as it has to use existing CS solvers as a proxy. To overcome limitation with the original robust CS algorithm, we propose to solve the robust CS problem directly in this paper and drive more computationally efficient algorithms by following latest advances in large-scale convex optimization for non-smooth regularization. Furthermore, we also extend the robust CS formulation to various settings, including additional affine constraints, $\ell_1$-norm loss function, mixed-norm regularization, and multi-tasking, so as to further improve robust CS. We also derive simple but effective algorithms to solve these extensions. We demonstrate that the new algorithms provide much better computational advantage over the original robust CS formulation, and effectively solve more sophisticated extensions where the original methods simply cannot. We demonstrate the usefulness of the extensions on several CS imaging tasks.

This paper considers the stability of online learning algorithms and its implications for learnability (bounded regret). We introduce a novel quantity called {\em forward regret} that intuitively measures how good an online learning algorithm is if it is allowed a one-step look-ahead into the future. We show that given stability, bounded forward regret is equivalent to bounded regret. We also show that the existence of an algorithm with bounded regret implies the existence of a stable algorithm with bounded regret and bounded forward regret. The equivalence results apply to general, possibly non-convex problems. To the best of our knowledge, our analysis provides the first general connection between stability and regret in the online setting that is not restricted to a particular class of algorithms. Our stability-regret connection provides a simple recipe for analyzing regret incurred by any online learning algorithm. Using our framework, we analyze several existing online learning algorithms as well as the "approximate" versions of algorithms like RDA that solve an optimization problem at each iteration. Our proofs are simpler than existing analysis for the respective algorithms, show a clear trade-off between stability and forward regret, and provide tighter regret bounds in some cases. Furthermore, using our recipe, we analyze "approximate" versions of several algorithms such as follow-the-regularized-leader (FTRL) that requires solving an optimization problem at each step.

In this paper, first we present a new explanation for the relation between logical circuits and artificial neural networks, logical circuits and fuzzy logic, and artificial neural networks and fuzzy inference systems. Then, based on these results, we propose a new neuro-fuzzy computing system which can effectively be implemented on the memristor-crossbar structure. One important feature of the proposed system is that its hardware can directly be trained using the Hebbian learning rule and without the need to any optimization. The system also has a very good capability to deal with huge number of input-out training data without facing problems like overtraining.

Given the limited performance of 2D cellular automata in terms of space when the number of documents increases and in terms of visualization clusters, our motivation was to experiment these cellular automata by increasing the size to view the impact of size on quality of results. The representation of textual data was carried out by a vector model whose components are derived from the overall balancing of the used corpus, Term Frequency Inverse Document Frequency (TF-IDF). The WorldNet thesaurus has been used to address the problem of the lemmatization of the words because the representation used in this study is that of the bags of words. Another independent method of the language was used to represent textual records is that of the n-grams. Several measures of similarity have been tested. To validate the classification we have used two measures of assessment based on the recall and precision (f-measure and entropy). The results are promising and confirm the idea to increase the dimension to the problem of the spatiality of the classes. The results obtained in terms of purity class (i.e. the minimum value of entropy) shows that the number of documents over longer believes the results are better for 3D cellular automata, which was not obvious to the 2D dimension. In terms of spatial navigation, cellular automata provide very good 3D performance visualization than 2D cellular automata.

Object recognition is an important task in image processing and computer vision. This paper presents a perfect method for object recognition with full boundary detection by combining affine scale invariant feature transform (ASIFT) and a region merging algorithm. ASIFT is a fully affine invariant algorithm that means features are invariant to six affine parameters namely translation (2 parameters), zoom, rotation and two camera axis orientations. The features are very reliable and give us strong keypoints that can be used for matching between different images of an object. We trained an object in several images with different aspects for finding best keypoints of it. Then, a robust region merging algorithm is used to recognize and detect the object with full boundary in the other images based on ASIFT keypoints and a similarity measure for merging regions in the image. Experimental results show that the presented method is very efficient and powerful to recognize the object and detect it with high accuracy.

We apply the spike-and-slab Restricted Boltzmann Machine (ssRBM) to texture modeling. The ssRBM with tiled-convolution weight sharing (TssRBM) achieves or surpasses the state-of-the-art on texture synthesis and inpainting by parametric models. We also develop a novel RBM model with a spike-and-slab visible layer and binary variables in the hidden layer. This model is designed to be stacked on top of the TssRBM. We show the resulting deep belief network (DBN) is a powerful generative model that improves on single-layer models and is capable of modeling not only single high-resolution and challenging textures but also multiple textures.

Most optimization problems in real life applications are often highly nonlinear. Local optimization algorithms do not give the desired performance. So, only global optimization algorithms should be used to obtain optimal solutions. This paper introduces a new nature-inspired metaheuristic optimization algorithm, called Hoopoe Heuristic (HH). In this paper, we will study HH and validate it against some test functions. Investigations show that it is very promising and could be seen as an optimization of the powerful algorithm of cuckoo search. Finally, we discuss the features of Hoopoe Heuristic and propose topics for further studies.

There are several contexts of non-monotonic reasoning where a priority between rules is established whose purpose is preventing conflicts. One formalism that has been widely employed for non-monotonic reasoning is the sceptical one known as Defeasible Logic. In Defeasible Logic the tool used for conflict resolution is a preference relation between rules, that establishes the priority among them. In this paper we investigate how to modify such a preference relation in a defeasible logic theory in order to change the conclusions of the theory itself. We argue that the approach we adopt is applicable to legal reasoning where users, in general, cannot change facts or rules, but can propose their preferences about the relative strength of the rules. We provide a comprehensive study of the possible combinatorial cases and we identify and analyse the cases where the revision process is successful. After this analysis, we identify three revision/update operators and study them against the AGM postulates for belief revision operators, to discover that only a part of these postulates are satisfied by the three operators.

This paper argues that the problem of identity is a critical challenge in agents which are able to reason about stories. The Xapagy architecture has been built from scratch to perform narrative reasoning and relies on a somewhat unusual approach to represent instances and identity. We illustrate the approach by a representation of the story of Little Red Riding Hood in the architecture, with a focus on the problem of identity raised by the narrative.