;The process is repeated a next epoch until the set of conditions are met."/>
OPTIMIZATION OF MODEL GENERATION IN DEEP LEARNING NEURAL NETWORKS USING SMARTER GRADIENT DESCENT CALIBRATION
首页>
外国专利>
OPTIMIZATION OF MODEL GENERATION IN DEEP LEARNING NEURAL NETWORKS USING SMARTER GRADIENT DESCENT CALIBRATION
OPTIMIZATION OF MODEL GENERATION IN DEEP LEARNING NEURAL NETWORKS USING SMARTER GRADIENT DESCENT CALIBRATION
展开▼
机译：基于更智能梯度下降校正的深度学习神经网络模型生成优化
展开▼
页面导航
摘要
著录项
相似文献
摘要
In training a new neural network, batches of the new training dataset are generated. An epoch of batches is passed through the new neural network using an initial weight (θ). An area minimized (Ai) under an error function curve and an accuracy for the epoch are calculated. It is then determined whether a set of conditions are met, where the set of conditions includes whether Ai is less than an average area (A_avg) from a training of an existing neural network and whether the accuracy is within a predetermined threshold. When the set of conditions are not met, a new θ is calculated by modifying a dynamic learning rate (β) by an amount proportional to a ratio of Ai/A_avg and by calculating the new θ using the modified β according to; ]]> ;The process is repeated a next epoch until the set of conditions are met.
展开▼
机译：在训练新的神经网络时，会生成一批新的训练数据集。使用初始权重（θ）通过新的神经网络传递一批时间。计算误差函数曲线下的最小面积（A i ）和时期的精度。然后根据现有神经网络的训练确定是否满足一组条件，其中一组条件包括A i 是否小于平均面积（A_avg）。在预定阈值内。当不满足一组条件时，通过将动态学习率（β）修改为与A i / A_avg之比成比例的量，并使用根据 展开▼
