KI - Künstliche Intelligenz manuscript No. (will be inserted by the editor) Abstract Artificial neural networks are simple and efficient machine learning tools. Defined originally in the traditional setting of simple vector data, neural network models have evolved to address more and more difficulties of complex real world problems, ranging from time evolving data to sophisticated data structures such as graphs and functions. This paper summarizes advances on those themes from the last decade, with a focus on results obtained by members of the SAMM team of Université Paris 1. 1 Introduction In many real world applications of machine learning and related techniques, the raw data are not anymore in a standard and simple tabular format in which each object is described by a common and fixed set of numerical attributes. This standard vector model, while useful and efficient, has some obvious limitations: it is limited to numerical attributes, it cannot handle objects with non uniform descriptions (e.g., situations in which some objects have a richer description than others), relations between objects (e.g., persons involved in a social network), etc. In addition, it is quite common for real world applications to have some dynamic aspect in the sense that the data under study are the results of a temporal process. Then, the traditional hypothesis of statistical independence between observations does not hold anymore: new hypothesis and theoretical analysis are needed to justify the mathematical soundness of the machine learning methods in this context.

Agents learning to act autonomously in real-world domains must acquire a model of the dynamics of the domain in which they operate. Learning domain dynamics can be challenging, especially where an agent only has partial access to the world state, and/or noisy external sensors. Even in standard STRIPS domains, existing approaches cannot learn from noisy, incomplete observations typical of real-world domains. We propose a method which learns STRIPS action models in such domains, by decomposing the problem into first learning a transition function between states in the form of a set of classifiers, and then deriving explicit STRIPS rules from the classifiers' parameters. We evaluate our approach on simulated standard planning domains from the International Planning Competition, and show that it learns useful domain descriptions from noisy, incomplete observations.

This paper assumes the hypothesis that human learning is perception based, and consequently, the learning process and perceptions should not be represented and investigated independently or modeled in different simulation spaces. In order to keep the analogy between the artificial and human learning, the former is assumed here as being based on the artificial perception. Hence, instead of choosing to apply or develop a Computational Theory of (human) Perceptions, we choose to mirror the human perceptions in a numeric (computational) space as artificial perceptions and to analyze the interdependence between artificial learning and artificial perception in the same numeric space, using one of the simplest tools of Artificial Intelligence and Soft Computing, namely the perceptrons. As practical applications, we choose to work around two examples: Optical Character Recognition and Iris Recognition. In both cases a simple Turing test shows that artificial perceptions of the difference between two characters and between two irides are fuzzy, whereas the corresponding human perceptions are, in fact, crisp.

This paper suggests a learning-theoretic perspective on how synaptic plasticity benefits global brain functioning. We introduce a model, the selectron, that (i) arises as the fast time constant limit of leaky integrate-and-fire neurons equipped with spiking timing dependent plasticity (STDP) and (ii) is amenable to theoretical analysis. We show that the selectron encodes reward estimates into spikes and that an error bound on spikes is controlled by a spiking margin and the sum of synaptic weights. Moreover, the efficacy of spikes (their usefulness to other reward maximizing selectrons) also depends on total synaptic strength. Finally, based on our analysis, we propose a regularized version of STDP, and show the regularization improves the robustness of neuronal learning when faced with multiple stimuli.

Kernel-based online learning has often shown state-of-the-art performance for many online learning tasks. It, however, suffers from a major shortcoming, that is, the unbounded number of support vectors, making it non-scalable and unsuitable for applications with large-scale datasets. In this work, we study the problem of bounded kernel-based online learning that aims to constrain the number of support vectors by a predefined budget. Although several algorithms have been proposed in literature, they are neither computationally efficient due to their intensive budget maintenance strategy nor effective due to the use of simple Perceptron algorithm. To overcome these limitations, we propose a framework for bounded kernel-based online learning based on an online gradient descent approach. We propose two efficient algorithms of bounded online gradient descent (BOGD) for scalable kernel-based online learning: (i) BOGD by maintaining support vectors using uniform sampling, and (ii) BOGD++ by maintaining support vectors using non-uniform sampling. We present theoretical analysis of regret bound for both algorithms, and found promising empirical performance in terms of both efficacy and efficiency by comparing them to several well-known algorithms for bounded kernel-based online learning on large-scale datasets.

Statistical data analysis and learning in Riemannian orbifolds is motivated by applications, where the data we want to learn on are naturally represented by finite combinatorial structures such as point patterns, trees, and graphs. Examples from structural pattern recognition that learn on structured data include estimating central points of a distribution on graphs such as the mean and median [9, 16, 15, 21], central clustering of graphs [10, 12, 13, 14, 19, 15, 23], learning graph quantization [17], and multilayer perceptrons for graphs [20]. In retrospect, the structure space framework proposed by [18] theoretically justifies the above approaches in the sense that they actually minimize an empirical risk function on structures. Since minimizing an empirical risk function is usually computationally intractable, the ultimate challenge consists in constructing efficient algorithms which are capable to return optimal or at least suboptimal solutions. From the point of view of statistical pattern recognition, however, the ultimate goal is not to determine a good solution of an empirical risk function, but rather to discover the true but unknown structure of the data with respect to its distribution.

Nearly 20% of total energy consumption in the United States is accounted for in heating, ventilation, and air conditioning (HVAC) systems. Smart sensing and adaptive energy management agents can greatly decrease the energy usage of HVAC systems in many building applications, for example by enabling the operator to shut off HVAC to unoccupied rooms. We implement a multimodal sensor agent that is nonintrusive and low-cost, combining information such as motion detection, CO2 reading, sound level, ambient light,and door state sensing. We show that in our live test bed at the USC campus, these sensor agents can be used to accurately estimate the number of occupants in each room using machine learning techniques, and that these techniques can also be applied to predict future occupancy by creating agent models of the occupants. These predictions will be used by control agents to enable the HVAC system increase its efficiency by continuously adapting to occupancy forecasts of each room.

The work presented here involves the design of a Multi Layer Perceptron (MLP) based classifier for recognition of handwritten Bangla alphabet using a 76 element feature set Bangla is the second most popular script and language in the Indian subcontinent and the fifth most popular language in the world. The feature set developed for representing handwritten characters of Bangla alphabet includes 24 shadow features, 16 centroid features and 36 longest-run features. Recognition performances of the MLP designed to work with this feature set are experimentally observed as 86.46% and 75.05% on the samples of the training and the test sets respectively. The work has useful application in the development of a complete OCR system for handwritten Bangla text.

The work presented here involves the design of a Multi Layer Perceptron (MLP) based pattern classifier for recognition of handwritten Bangla digits using a 76 element feature vector. Bangla is the second most popular script and language in the Indian subcontinent and the fifth most popular language in the world. The feature set developed for representing handwritten Bangla numerals here includes 24 shadow features, 16 centroid features and 36 longest-run features. On experimentation with a database of 6000 samples, the technique yields an average recognition rate of 96.67% evaluated after three-fold cross validation of results. It is useful for applications related to OCR of handwritten Bangla Digit and can also be extended to include OCR of handwritten characters of Bangla alphabet.

This paper investigates a new method for improving the learning algorithm of Mixture of Experts (ME) model using a hybrid of Modified Cuckoo Search (MCS) and Conjugate Gradient (CG) as a second order optimization technique. The CG technique is combined with Back-Propagation (BP) algorithm to yield a much more efficient learning algorithm for ME structure. In addition, the experts and gating networks in enhanced model are replaced by CG based Multi-Layer Perceptrons (MLPs) to provide faster and more accurate learning. The CG is considerably depends on initial weights of connections of Artificial Neural Network (ANN), so, a metaheuristic algorithm, the so-called Modified Cuckoo Search is applied in order to select the optimal weights. The performance of proposed method is compared with Gradient Decent Based ME (GDME) and Conjugate Gradient Based ME (CGME) in classification and regression problems. The experimental results show that hybrid MSC and CG based ME (MCS-CGME) has faster convergence and better performance in utilized benchmark data sets.