Search results for "Complexity"
showing 10 items of 1094 documents
Convolutional Regression Tsetlin Machine: An Interpretable Approach to Convolutional Regression
2021
The Convolutional Tsetlin Machine (CTM), a variant of Tsetlin Machine (TM), represents patterns as straightforward AND-rules, to address the high computational complexity and the lack of interpretability of Convolutional Neural Networks (CNNs). CTM has shown competitive performance on MNIST, Fashion-MNIST, and Kuzushiji-MNIST pattern classification benchmarks, both in terms of accuracy and memory footprint. In this paper, we propose the Convolutional Regression Tsetlin Machine (C-RTM) that extends the CTM to support continuous output problems in image analysis. C-RTM identifies patterns in images using the convolution operation as in the CTM and then maps the identified patterns into a real…
Low-Rate Reduced Complexity Image Compression using Directionlets
2006
The standard separable two-dimensional (2-D) wavelet transform (WT) has recently achieved a great success in image processing because it provides a sparse representation of smooth images. However, it fails to capture efficiently one-dimensional (1-D) discontinuities, like edges and contours, that are anisotropic and characterized by geometrical regularity along different directions. In our previous work, we proposed a construction of critically sampled perfect reconstruction anisotropic transform with directional vanishing moments (DVM) imposed in the corresponding basis functions, called directionlets. Here, we show that the computational complexity of our transform is comparable to the co…
A Variational Approach for Denoising Hyperspectral Images Corrupted by Poisson Distributed Noise
2014
Poisson distributed noise, such as photon noise is an important noise source in multi- and hyperspectral images. We propose a variational based denoising approach, that accounts the vectorial structure of a spectral image cube, as well as the poisson distributed noise. For this aim, we extend an approach for monochromatic images, by a regularisation term, that is spectrally and spatially adaptive and preserves edges. In order to take the high computational complexity into account, we derive a Split Bregman optimisation for the proposed model. The results show the advantages of the proposed approach compared to a marginal approach on synthetic and real data.
Space-Frequency Quantization using Directionlets
2007
In our previous work we proposed a construction of critically sampled perfect reconstruction transforms with directional vanishing moments (DVMs) imposed in the corresponding basis functions along different directions, called directionlets. Here, we combine the directionlets with the space-frequency quantization (SFQ) image compression method, originally based on the standard two-dimensional (2-D) wavelet transform (WT). We show that our new compression method outperforms the standard SFQ as well as the state-of-the-art compression methods, like SPIHT and JPEG-2000, in terms of the quality of compressed images, especially in a low-rate compression regime. We also show that the order of comp…
Datorzinātne un informācijas tehnoloģijas: Datu bāzes un informācijas sistēmas: doktorantu konsorcijs. Sestā Starptautiskā Baltijas konference Baltic…
2004
The Baltic Conference on Databases and Information Systems is a biannual international forum for technical discussion among researchers and developers of database and information systems. The objective of the conference is to bring together researchers as well as practitioners and PhD students in the field of computing research that will improve the construction of future information systems. On the other hand, the conference is giving opportunities to developers, users and researchers of advanced IS technologies to present their work and to exchange their ideas and at the same time providing a feedback to database community.
BELM: Bayesian Extreme Learning Machine
2011
The theory of extreme learning machine (ELM) has become very popular on the last few years. ELM is a new approach for learning the parameters of the hidden layers of a multilayer neural network (as the multilayer perceptron or the radial basis function neural network). Its main advantage is the lower computational cost, which is especially relevant when dealing with many patterns defined in a high-dimensional space. This brief proposes a bayesian approach to ELM, which presents some advantages over other approaches: it allows the introduction of a priori knowledge; obtains the confidence intervals (CIs) without the need of applying methods that are computationally intensive, e.g., bootstrap…
Moving Learning Machine Towards Fast Real-Time Applications: A High-Speed FPGA-based Implementation of the OS-ELM Training Algorithm
2018
Currently, there are some emerging online learning applications handling data streams in real-time. The On-line Sequential Extreme Learning Machine (OS-ELM) has been successfully used in real-time condition prediction applications because of its good generalization performance at an extreme learning speed, but the number of trainings by a second (training frequency) achieved in these continuous learning applications has to be further reduced. This paper proposes a performance-optimized implementation of the OS-ELM training algorithm when it is applied to real-time applications. In this case, the natural way of feeding the training of the neural network is one-by-one, i.e., training the neur…
An efficient distributed algorithm for generating and updating multicast trees
2006
As group applications are becoming widespread, efficient network utilization becomes a growing concern. Multicast transmission represents a necessary lower network service for the wide diffusion of new multimedia network applications. Multicast transmission may use network resources more efficiently than multiple point-to-point messages; however, creating optimal multicast trees (Steiner Tree Problem in networks) is prohibitively expensive. This paper proposes a distributed algorithm for the heuristic solution of the Steiner Tree Problem, allowing the construction of effective distribution trees using a coordination protocol among the network nodes. Furthermore, we propose a novel distribut…
New separation between $s(f)$ and $bs(f)$
2011
In this note we give a new separation between sensitivity and block sensitivity of Boolean functions: $bs(f)=(2/3)s(f)^2-(1/3)s(f)$.
A Tight Lower Bound on Certificate Complexity in Terms of Block Sensitivity and Sensitivity
2014
Sensitivity, certificate complexity and block sensitivity are widely used Boolean function complexity measures. A longstanding open problem, proposed by Nisan and Szegedy, is whether sensitivity and block sensitivity are polynomially related. Motivated by the constructions of functions which achieve the largest known separations, we study the relation between 1-certificate complexity and 0-sensitivity and 0-block sensitivity. Previously the best known lower bound was $C_1(f)\geq \frac{bs_0(f)}{2 s_0(f)}$, achieved by Kenyon and Kutin. We improve this to $C_1(f)\geq \frac{3 bs_0(f)}{2 s_0(f)}$. While this improvement is only by a constant factor, this is quite important, as it precludes achi…