1,721,096 research outputs found
Application of Neural Autoassociators to Short Testing of Refrigerators
No full textThis paper describes an industrial application of neural networks which proved to be very successful and which is currently working on one assembly line with the perspective of a future expansion to other production plants. The task is the quality control in the production of refrigerators, detecting possible defects that can lead either to a real malfunction or even to a degradation of their performance. The testing phase was required to be accomplished in a short time with respect to a complete testing in order to avoid delays in the production process. Moreover the requirements for the testing system included an easy extension to different products, a good detection of the malfunctioning equipment and a simple use for the personnel.
The system is based on a classifier realized with neural autoassociators. This approach allows us to build easily a model of the standard functional equipment, which satisfies the product requirements, by learning from examples. The neural autoassociator can learn to recognize functional devices only from positive samples, but in order to improve its recognition performance the learning algorithm can be extended easily to take into account also negative examples. Thus, the performance of the classifier can be improved by collecting the samples on which it produced a wrong or an ambiguous result and by adding these new examples to the learning set that is used to refine the classifier
A Semi-supervised Document Clustering Algorithm based on EM
No full textDocument clustering is a very hard task in automatic text processing since it requires extracting regular patterns from a document collection without a priori knowledge on the category structure. This task can be difficult also for humans because many different but valid partitions may exist for the same collection. Moreover, the lack of information about categories makes it difficult to apply effective feature selection techniques to reduce the noise in the representation of texts. Despite these intrinsic difficulties, text clustering is an important task for Web search applications in which huge collections or quite long query result lists must be automatically organized. Semi-supervised clustering lies in between automatic categorization and auto-organization. It is assumed that the supervisor is not required to specify a set of classes, but only to provide a set of texts grouped by the criteria to be used, to organize the collection. In this paper, we present a novel algorithm for clustering text documents which exploits the EM algorithm together with a feature selection technique based on information gain. The experimental results show that only very few documents are needed to initialize the clusters and that the algorithm is able to properly extract the regularities hidden in a huge unlabeled collection
On a Convex Logic Fragment for Learning and Reasoning
Full text linkIn this paper we introduce the convex fragment of Lukasiewicz Logic and discuss its possible applications in different learning schemes. Indeed, the provided theoretical results are highly general, because they can be exploited in any learning framework involving logical constraints. The method is of particular interest since the fragment guarantees to deal with convex constraints, which are shown to be equivalent to a set of linear constraints. Within this framework, we are able to formulate learning with kernel machines as well as collective classification as a quadratic programming problem
Inductive inference from noisy examples: The rule-noise dilemma and the hybrid finite state filter
No full textRecently, it has been shown that recurrent neural networks can be used as adaptive neural parsers. Given a set of positive and negative examples, picked up from a given language, adaptive neural parsers can effectively be trained to recognize its grammar. Many efforts have been focused on regular languages for which the continuous computation can be approximated by the set of transition rules of a finite state machine.
In this paper we face the problem of inferring grammars from positive and negative examples that, however, may be corrupted by a noise that simply changes the membership of the strings. We propose using second-order recurrent networks and suggest a training algorithm, referred to as HFF (hybrid Finite state Filter), based on a parsimony principle that penalizes the development of complex rules
Neural computation, social networks, and topological spectra
No full textThis paper emphasizes some intriguing links between neural computation on graphical domains and social networks, like those used in nowadays search engines to score the page authority. It is pointed out that the introduction of web domains creates a unified mathematical framework for these computational schemes. It is shown that one of the major limitations of currently used connectionist models, namely their scarce ability to capture the topological features of patterns, can be effectively faced by computing the node rank according to social-based computation, like Google's PageRank. The main contribution of the paper is the introduction of a novel graph spectral notion, which can be naturally used for the graph isomorphism problem. In particular, a class of graphs is introduced for which the problem is proven to be polynomial. It is also pointed out that the derived spectral representations can be nicely combined with learning, thus opening the doors to many applications typically faced within the framework of neural computation
The Decoupling Network Assumptions for Optimal Learning in Recurrent Neural Networks
No full textMany researchers have recently focused their efforts on devising efficient algorithms, mainly based on optimization schemes, for learning the weights of recurrent neural networks. Like for feedforward networks, however, these learning algorithms may get stuck in local minima during gradient descent, thus discovering sub-optimal solutions. In this paper, we give sufficient conditions which guarantee local minima free error surfaces. Moreover, we provide an example which shows the constructive role of the proposed theory in designing networks suitable for solving a given task
Neural network training as a dissipative process
No full textThis paper analyzes the practical issues and reports some results on a theory in which learning is modeled as a continuous temporal process driven by laws describing the interactions of intelligent agents with their own environment. The classic regularization framework is paired with the idea of temporal manifolds by introducing the principle of least cognitive action, which is inspired by the related principle of mechanics. The introduction of the counterparts of the kinetic and potential energy leads to an interpretation of learning as a dissipative process. As an example, we apply the theory to supervised learning in neural networks and show that the corresponding Euler–Lagrange differential equations can be connected to the classic gradient descent algorithm on the supervised pairs. We give preliminary experiments to confirm the soundness of the theory
Does Terminal Attractor Guarantee Global Convergence?
No full textRecently, two new learning algoriths, called TABP and HTABP and based on the properties of terminal attractors, have been proposed. These algorithms were claimed to perform global optimization of the cost in finite time, provided that a null solution exists. In this paper, we prove that, unfortunately, there are no theoretical guarantees that a global solution will be reached, unless the learning process begins in the domain of attraction of the global minimum. When a local minimum basin is entered, quite random jumps in the weight space take place, that may led to cycles. Moreover, when approaching local minima, overflow errors may also occur that force the learning to stop. Finally, particular care must be taken in order to avoid numerical problems that may occur even when approaching the global minimum
Semi-supervised active learning in graphical domains
No full textIn a traditional machine learning task, the goal is training a classifier using only labeled data (data feature/label pairs) in order to be able to generalize on completely new data to be labeled by the classifier. Unluckily in many cases it is difficult, expensive or time consuming to obtain the labeled instances needed for training, also because we usually require a human supervisor to annotate lots of data to collect a significant training set. Moreover, in many cases we are not interested in generalization to any unseen example, but we just require to discover labels for a large quantity of unlabeled, but already available, data by using a small subset of labeled data. If the given scenario involves both these conditions, a semi-supervised learning algorithm can be exploited as a solution for the classification problem. Semi-supervised learning algorithms combine a large amount of unlabeled data and a available small set of labeled data, to build a reliable classifier. It is particularly interesting to focus on a sub-class of semi- supervised learning algorithms, that is graph-based semi-supervised learning. In this framework we represent data as a graph where the nodes represent the la- beled and unlabeled examples in the dataset, and the edges are added according to a given similarity relationship between pairs of examples
- …
