Search results for "Memory"
showing 10 items of 2004 documents
Ranking and unrankingk-ary trees with a 4k –4 letter alphabet
1997
Abstract The problem of the direct generation in A-order of binary trees was stated by Zaks in 1980. In 1988 Roelants van Baronaigien and Ruskey gave a solution for k-ary trees with n internal nodes using an encoding sequence of kn+1 integers between 1 and n. Vajnovszki and Pallo improved this result for binary trees in 1994 using words of length n–1 on a four letter alphabet. Recently Korsh generalized the Vajnovszki and Pallo’s generating algorithm to k-ary trees using an alphabet whose cardinality depends on k but not on n. We give in this paper ranking and unranking algorithms for k-ary trees using the Korsh’s encoding scheme.
The node-depth encoding
2008
The node-depth encoding has elements from direct and indirect encoding for trees which encodes trees by storing the depth of nodes in a list. Node-depth encoding applies specific search operators that is a typical characteristic for direct encodings. An investigation into the bias of the initialization process and the mutation operators of the node-depth encoding shows that the initialization process has a bias to solutions with small depths and diameters, and a bias towards stars. This investigation, also, shows that the mutation operators are unbiased. The performance of node-depth encoding is investigated for the bounded-diameter minimum spanning tree problem. The results are presented f…
Effect of Prime and Target Repetition on Lexical Decision Time
1992
On a prime-target lexical decision task we manipulated the relatedness between prime and target (semantically related or unrelated), the number of repetitions (from 1 to 5), the type of the repeated stimulus (only the prime, only the target, or both), and the stimulus onset asynchrony (within a range of automatic activation from 60 to 400 msec.) to find whether semantic and repetition priming are additive (or interact), and whether there is episodic priming in an automatic, nonconscious way. Analysis showed repetition and semantic priming were additive rather than interactive. No episodic automatic priming was found. Results are discussed in terms of the predictions made from the main theo…
Encoding into Visual Working Memory: Event-Related Brain Potentials Reflect Automatic Processing of Seemingly Redundant Information.
2013
Encoding and maintenance of information in visual working memory in an S1-S2 task with a 1500 ms retention phase were investigated by means of event-related brain potentials (ERPs). Participants were asked to decide whether two visual stimuli were physically identical (identity comparison (IC) task) or belonged to the same set or category of equivalent patterns (category comparison (CC) task). The stimuli differ with regard to two features. (1) Each pattern can belong to a set of either four (ESS 4) or eight (ESS 8) equivalent patterns, mirroring differences in the complexity with regard to the representational structure of each pattern (i.e., equivalence set size (ESS)). (2) The set of pat…
Attention Switching and Multimedia Learning: The Impact of Executive Resources on the Integrative Comprehension of Texts and Pictures
2014
The ability to flexibly allocate attention to goal-relevant information is pivotal for the completion of high-level cognitive processes. For instance, in comprehending illustrated texts, the reader permanently has to switch the attentional focus between the text and the corresponding picture in order to extract relevant information from both sources. Thus, the hypothesis was tested that individuals with a lower switching capacity exhibit a decreased performance in tasks that require the flexible switch of attention between two external representations. Participants read an illustrated text and answered questions that either required the extraction of information from the text alone or from …
Reading Comprehension and Working Memory's Executive Processes: An Intervention Study in Primary School Students
2013
ABSTRA C T Reading comprehension is a highly demanding task that involves the simultaneous process of extracting and constructing meaning in which working memory’s executive processes play a crucial role. In this article, a training program on working memory’s executive processes to improve reading comprehension is presented and empirically tested in two experiments with third-grade primary school students. Experiment 1 showed a greater gain after training the experimental group in contrast to the control group in reading comprehension and intelligence. In experiment 2, we focused on the training processes and compared training results of high and low pretest reading comprehension groups. R…
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…
Comparison of implementations of the lattice-Boltzmann method
2008
AbstractSimplicity of coding is usually an appealing feature of the lattice-Boltzmann method (LBM). Conventional implementations of LBM are often based on the two-lattice or the two-step algorithm, which however suffer from high memory consumption and poor computational performance, respectively. The aim of this work was to identify implementations of LBM that would achieve high computational performance with low memory consumption. Effects of memory addressing schemes were investigated in particular. Data layouts for velocity distribution values were also considered, and they were found to be related to computational performance. A novel bundle data layout was therefore introduced. Address…
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…
Analysis of HMAX Algorithm on Black Bar Image Dataset
2020
An accurate detection and classification of scenes and objects is essential for interacting with the world, both for living beings and for artificial systems. To reproduce this ability, which is so effective in the animal world, numerous computational models have been proposed, frequently based on bioinspired, computational structures. Among these, Hierarchical Max-pooling (HMAX) is probably one of the most important models. HMAX is a recognition model, mimicking the structures and functions of the primate visual cortex. HMAX has already proven its effectiveness and versatility. Nevertheless, its computational structure presents some criticalities, whose impact on the results has never been…