Maintaining data warehouses and ETL processes is becoming increasingly difficult. For this reason, we introduce a similarity measure on ETL processes, based on the edit distance of a graph, which models the process. We show both the exact way how to calculate it and heuristic approaches to compute the estimated similarity more quickly. We propose methods to improve graph edit distance based on the assumption that the ETL process model is a directed acyclic graph.
In this paper we present a cryptographic protocol for a seller - buyer problem and in particular we prove that non-emptiness of a semi-commutative set defined by mappings involved in the protocol is a decidable problem.
In this note we present theory which facilitates the use of Conley index algorithms for cubical multivalued maps constructed from maximal dimensional cubes in the setting when cubes of arbitrary dimension are permitted.
Independent Component Analysis (ICA) is a method for searching the linear transformation that minimizes the statistical dependence between its components. Most popular ICA methods use kurtosis as a metric of independence (non-Gaussianity) to maximize, such as FastICA and JADE. However, their assumption of fourth-order moment (kurtosis) may not always be satisfied in practice. One of the possible solution is to use third-order moment (skewness) instead of kurtosis, which was applied in ICA_SG and EcoICA. In this paper we present a competitive approach to ICA based on the Split Generalized Gaussian distribution (SGGD), which is well adapted to heavy-tailed as well as asymmetric data. Consequently, we obtain a method which works better than the classical approaches, in both cases: heavy tails and non-symmetric data
. One of the most important optimization tasks in the industry at the current time is the object packing problem. Although several methods have been developed for the purpose of solving it, they are usually only able to optimize placement locally and as such are heavily dependent on the choice of the initial setting – hence the need for trying out multiple possible starting points, which impacts algorithm running time. In this paper we present a neural network-based model which provides sensible starting points in a linear time.
Schedae Informaticae » 2018 » Volume 27 » Traffic Signal Settings Optimization Using Gradient Descent A A A
The article introduces a new set of Polish word embeddings, built using KGR10 corpus, which contains more than 4 billion words. These embeddings are evaluated in the problem of recognition of temporal expressions (timexes) for the Polish language. We described the process of KGR10 corpus creation and a new approach to the recognition problem using Bidirectional Long-Short Term Memory (BiLSTM) network with additional CRF layer, where specific embeddings are essential. We presented experiments and conclusions drawn from them.
Infinite length of trajectories is an almost universal assumption in the theoretical foundations of reinforcement learning. In practice learning occurs on finite trajectories. In this paper we examine a specific result of this disparity, namely a strong bias of the time-bounded Every-visit Monte Carlo value estimator. This manifests as a vastly different learning dynamic for algorithms that use value predictors, including encouraging or discouraging exploration. We investigate these claims theoretically for a one dimensional random walk, and empirically on a number of simple environments. We use GAE as an algorithm involving a value predictor and evolution strategies as a reference point.
Schedae Informaticae » 2018 » Volume 27 » Image Inpainting with Gradient Attention A A A
Schedae Informaticae » 2018 » Volume 27 » On Some Goodness of Fit Tests for Normality Based on the Optimal Transport Distance A A A
In this paper, we propose a simple, fast and easy to implement algorithm LOSSGRAD (locally optimal step-size in gradient descent), which automatically modifies the step-size in gradient descent during neural networks training. Given a function f, a point x, and the gradient ∇_x f of f, we aim to find the step-size h which is (locally) optimal, i.e. satisfies: h=arg min_t ≥ 0 f(x-t ∇_x f). Making use of quadratic approximation, we show that the algorithm satisfies the above assumption. We experimentally show that our method is insensitive to the choice of initial learning rate while achieving results comparable to other methods.
In this paper we discuss a class of AutoEncoder based generative models based on one dimensional sliced approach. The idea is based on the reduction of the discrimination between samples to one-dimensional case. Our experiments show that methods can be divided into two groups. First consists of methods which are a modification of standard normality tests, while the second is based on classical distances between samples. It turns out that both groups are correct generative models, but the second one gives a slightly faster decrease rate of Fréchet Inception Distance (FID).
Neural networks are prone to adversarial attacks. In general, such attacks deteriorate the quality of the input by either slightly modifying most of its pixels, or by occluding it with a patch. In this paper, we propose a method that keeps the image unchanged and only adds an adversarial framing on the border of the image. We show empirically that our method is able to successfully attack state-of-the-art methods on both image and video classification problems. Notably, the proposed method results in a universal attack which is very fast at test time. Source code can be found at github.com/zajaczajac/adv_framing.
Regularizing the gradient norm of the output of a neural network with respect to its inputs is a powerful technique, rediscovered several times. This paper presents evidence that gradient regularization can consistently improve classification accuracy on vision tasks, using modern deep neural networks, especially when the amount of training data is small. We introduce our regularizers as members of a broader class of Jacobian-based regularizers. We demonstrate empirically on real and synthetic data that the learning process leads to gradients controlled beyond the training points, and results in solutions that generalize well.
Schedae Informaticae » 2016 » Volume 25 » Towards Learning Word Representation A A A
Schedae Informaticae » 2016 » Volume 25 » Misclassification-Driven Sample Relabeling for Supervised Kernel Principal Component Analysis A A A
