Today's high performance deep artificial neural networks (ANNs) rely heavily on parameter optimization, which is sequential in nature and even with a powerful GPU, would have taken weeks to train them up for solving challenging tasks [22]. HMAX [17] has demonstrated that a simple high performing network could be obtained without heavy optimization. In this paper, we had improved on the existing...

Here we modify the HMAX object recognition system of Serre et al. with an end-stopped filter to try and improve the accuracy of the model and to further the parallels in the algorithm to the actual processing of the visual cortex for learning object representations.

The image logs interpretation from two wells in a fold hosting a west Iranian oil field located in the Dezful Embayment, SW Iran reveal the occurrence of two major systems of natural fractures. In the central part of the fold, the fold-related fractures include two sets of fractures trending N53°E and N34°E. In the eastern and also curved part of the fold, the strike of open fractures varies fr...

1. We hypothesize that flowering phenology correlates with plant height growth pattern and that the pattern is associated with functional traits including maximum plant height (Hmax), RGR, stem tissue mass density (SD), hollow ratio (proportion of central hollow of stem cross-sectional area) and leafmass per area (LMA) in grassland herbaceous species. 2. We investigated plant height growth traj...

در این مقاله یک مدل ریاضی برای مسئله سیستم تولیدی همکارانه ساخت بر اساس سفارش با رعایت انصاف تخصیص بار‌های تولید طراحی شده است. اهداف اصلی مدل، کمینه‌سازی هزینه‌‌های کل و حداکثر استفاده از منابع به‌منظور عادلانه شرایط عدم­قطعیت کنترل پارامتر‌های غیرقطعی روش برنامه‌ریزی فازی ‌شده نتایج نشان می‌دهد افزایش نرخ عدم‌قطعیت، می­یابد. ازآنجاکه ظرفیت کارخانه‌ها ثابت است، مقدار تقاضا، هر کارخانه نیز می­ی...