Subscribe to the gold package and get unlimited access to Shamra Academy
Register a new userSimulating the Behavior of an Integrate-and-Fire Neuron
محاكاة سلوك خلية عصبونية من النموذج تكامل- إطلاق
1746
0 34
0
(
0
)
Authors
وفاء صالح( باحث )
Created by
Shamra Editor
Ask ChatGPT about the research
يمكن تحليل و معالجة بيانات صور الفيديو من خلال العديد من الطرق. يكشف هذا البحث إلى أي مدى يمكن أن تكون الخلية العصبونية النابضة Spiking Neuron المصممة وفق النموذج Hodgkin-Huxley ملائمة لهذه المهمة. ستناقِش عمليات المحاكاة الموثقة في هذا البحث استجابة الخلايا العصبونية من النموذج تكامل- إطلاق لتيارات الدخل الثابتة و المتغيرة و المدخلات المقادة بكثافة البكسل. و بشكل عام تستخدم برمجيات التطبيق المصمم 64 خلية عصبونية نابضة تعمل بشكل مستقل حيث تقوم هذه الخلايا العصبونية بمعالجة بيانات الصورة المأخوذة كل 25 ميلي ثانية. تم اختبار العصبونات المصممة على 100 صورة تتضمن حالات مختلفة من الإضاءة و الإشباع اللوني و التباين, و أظهرت النتائج أن الخلية العصبونية من النموذج تكامل – إطلاق حساسة للتغيرات في كثافة البكسل إذا تم اختيار بارامتراتها بشكل جيد, مما يجعل استخدام شبكة عصبونية من هذه العصبونات أمراً مناسباً في بعض التطبيقات مثل Saliency Maps و التي تعتمد بشكل كبير على قيم الكثافة لمجموعة من البكسلات.
Video image data can be analyzed and processed in many ways. This research explores the extent at which spiking neurons, which are designed along the Hodgkin-Huxley model, are suitable for this task. The simulations reported in this research consider integrate-and-fire neurons constant and alternating input currents, as well as pixel-intensity driven inputs. Currently, the simulation software employs 64 independently operating spiking neurons that process image data taken every 25 ms. In order to define the response of these neurons, the experiments were done on 100 digital images which include different illuminations, contrast, and saturation situations. The results show that the integrate-and-fire-neuron is highly sensitive to the changes in the intensity of pixels if its parameters are properly set. So in many applications, such as "Saliency Maps", which highly depend on the intensity values of a set of pixels, a neural network made of this neuron will perfectly fit.
References used
LIN, I-JONG, and S. Y. KUNG., “Video Object Extraction and Representation: Theory and Ap-plications” , Boston, MA: Kluwer Academic, 2000
HANJALIC, A., “Content-based Analysis of Digital Video”, Boston: Kluwer Academic, 2004
WEN, ZHEN, and THOMAS S. HUANG, “3D Face Processing: Modeling, Analysis, and Synthesis”, Boston: Kluwer Academic, 2004
http://en.wikipedia.org/wiki/Biological_neuron_model, downloaded at 17/1/2013
S. KOSLOW and S. SUBRAMANIAM, EDS, “Electrophysiological Models In: Databasing the Brain: From Data to Knowledge”, Wiley, New York, Nelson, M.E., 2004
rate research
Read More
In the present paper, we study the effect of both morphology and
compatibilization on the reaction to fire of blends of recycled
poly(ethylene terephthalate) (PET) with recycled polycarbonate (PC).
The quick consuming of products and the strong competition
between producers caused to increase the complexity of products, so
the digital factory became a need between design and producing
actually to achieve a production system with a shorter ti
me and
optimal design and parameters without engineering modifications.
This research offering a reference model basing on a complete
framework between the engineering applications to build a
computational model with a single core based on the integration
between three dimensions modeling and automation of application
for digital factory concept, to optimize the design of achieving the
ideal execution of actual production system. Where we achieved the
control of three-dimensional computer model according to process
automation exactly as in actual through integrating tools, where the
percentage of exact between the real factory and digital factory was
83% by using the time of process as the main factor for comparison
in this evaluation.
integrate Lists Data Frames
integrate Lists Data Frames
integrate Lists Data Frames
integrate Lists Data Frames
Recent studies indicate that NLU models are prone to rely on shortcut features for prediction, without achieving true language understanding. As a result, these models fail to generalize to real-world out-of-distribution data. In this work, we show t
hat the words in the NLU training set can be modeled as a long-tailed distribution. There are two findings: 1) NLU models have strong preference for features located at the head of the long-tailed distribution, and 2) Shortcut features are picked up during very early few iterations of the model training. These two observations are further employed to formulate a measurement which can quantify the shortcut degree of each training sample. Based on this shortcut measurement, we propose a shortcut mitigation framework LGTR, to suppress the model from making overconfident predictions for samples with large shortcut degree. Experimental results on three NLU benchmarks demonstrate that our long-tailed distribution explanation accurately reflects the shortcut learning behavior of NLU models. Experimental analysis further indicates that LGTR can improve the generalization accuracy on OOD data, while preserving the accuracy on in-distribution data.
This paper presents structural
analysis in using ANSYS programme for modeling of heat load then
comparison between the analytical results and experimental results is
performed .
Log in to be able to interact and post comments
comments
Fetching comments
Sign in to be able to follow your search criteria
