http://chineseinput.net/에서 pinyin(병음)방식으로 중국어를 변환할 수 있습니다.
변환된 중국어를 복사하여 사용하시면 됩니다.
Are the long–short term memory and convolution neural networks really based on biological systems?
David Balderas Silva,Pedro Ponce Cruz,Arturo Molina Gutierrez 한국통신학회 2018 ICT Express Vol.4 No.2
In general, it is not a simple task to predict sequences or classify images, and it is even more problematic when both are combined. Nevertheless, biological systems can easily predict sequences and are good at image recognition. For these reasons Long–Short Term Memory and Convolutional Neural Networks were created and were based on the memory and visual systems. These algorithms have shown great properties and shown certain resemblance, yet they are still not the same as their biological counterpart. This article reviews the biological bases and compares them.
Guillermo Kemper,David Ponce,Joel Telles,Christian del Carpio 대한전기학회 2019 Journal of Electrical Engineering & Technology Vol.14 No.6
The detection of the engine rotational speed in revolutions per minute (RPM) is of great importance to estimate the speed of boats. This value can be obtained from the fundamental frequency component of acquired sonar signals. However, detection can often be seriously afected by noise and distortion introduced by the underwater environment. Several methods have been proposed for fundamental component detection, but they do not specifcally take advantage of the passive sonar signal characteristics to improve the performance of the process. In this context, the proposed algorithm uses DEMON processing applied to wavelets packets subbands to exploit the characterization of the sonar signal in the time and frequency domains. The algorithm involves signal segmentation, wavelet packet decomposition, subband envelope cross-correlation and fundamental component detection from the power spectrum. The method was applied in passive sonar signals acquired in navigation and also obtained by simulation. The performance of the proposed algorithm was evaluated with signals of diferent SNR values that were also corrupted by a simulated multipath underwater channel. The signals were evaluated by both the experienced sonar operators and the proposed algorithm. The results obtained were very satisfactory for RPM detection and are detailed at the end of this document.
R. Vahdati, Ali,Weissmann, John David,Timmermann, Axel,Ponce de Leó,n, Marcia S.,Zollikofer, Christoph P.E. Pergamon Press 2019 Quaternary science reviews Vol.221 No.-
<P><B>Abstract</B></P> <P>Understanding Late Pleistocene human dispersals from Africa requires understanding a multifaceted problem with factors varying in space and time, such as climate, ecology, human behavior, and population dynamics. To understand how these factors interact to affect human survival and dispersal, we have developed a realistic agent-based model that includes geographic features, climate change, and time-varying vegetation and food resources. To enhance computational efficiency, we further apply machine learning algorithms. Our approach is new in that it is designed to systematically evaluate a large-scale agent-based model, and identify its key parameters and sensitivities. Results show that parameter interactions are the major source in generating variability in human dispersal and survival/extinction scenarios. In realistic scenarios with geographical features and time-evolving climatic conditions, random fluctuations become a major source of variability in arrival times and success. Furthermore, parameter settings as different as 92% of maximum possible difference, and occupying more than 30% of parameter space can result in similar dispersal scenarios. This suggests that historical contingency (similar causes – different effects) and equifinality (different causes – similar effects) are primary constituents of human dispersal scenarios. While paleoanthropology, archaeology and paleogenetics now provide insights into patterns of human dispersals at an unprecedented level of detail, elucidating the causes underlying these patterns remains a major challenge.</P>