"Learning seems to rely on prediction error because if the world is exactly as you expected it to be, there is nothing new to learn," Poldrack said.
“学习似乎依赖于预测错误，因为如果这个世界和你预测的一样，那就没什么新东西可学了，”Poldrack说。
It is its capacity to hold error rather than scuttle it that makes the distributed being fertile ground for learning, adaptation, and evolution.
正是其容纳错误而非杜绝错误的能力，使分布式存在成为学习、适应和进化的沃土。
Learning the business of music can be trial and error without the right guidance, and lead to you wasting a lot of time and money.
如果没有正确的引导，学习音乐行业的知识要经过无数次的尝试和失败，既浪费了时间又浪费了金钱。
Modularization of repetitive actions is labor-intensive and error-prone and typically requires learning a new programming language.
重复动作的模块化需要很大的工作量，易于产生错误，且通常需要了解一种新的编程语言。
In both studies, participants remembered the learning context of the target words better if they had been learned through trial-and-error, relative to the errorless condition.
在两个实验中，相比无误学习，通过试误进行词汇学习的被试能更好的回忆目标词的背景。
Learning rules are constructed according to deterministic annealing to optimize classifier parameters, on purpose to reduce classification error and system entropy of the space to be identified.
由确定性退火技术构造学习规则用于优化分类器参数，目的是减少分类误差以及待识别空间的系统熵。
Recent studies tell us that learning is enhanced through trial and error.
近来的研讨成果告诉我们，经过反复的尝试和错误，学习效果能得到加强。
Through adjusting weight, computing error rate and modifying the parameters of hidden nodes, optimal results will be achieved in the learning procedure.
学习过程通过调整权值、计算误差、修正隐层单元的参数，以达到最优结果。
Network structure is adjusted with networks parameter learning, which could reduce error.
在网络参数学习的同时网络结构也在进行调整，使得误差不断减小。
An optimal learning control method for a robot is introduced with acceleration error used to correct the motion of actuators.
为工业机器人提出了一种最优学习控制法。这种控制法用加速度误差校正驱动器运动。
The establishment of mathematical model of PDAG algorithm, with the application of a learning matrix to the error data, proved the stability and convergence of PDAG algorithm in theory.
将学习矩阵作用于误差数据建立PDAG算法的数学模型，从理论上证明了PDAG算法的稳定性和收敛性。
Error analysis may be carried out in order to obtain information on common difficulties in language learning, as an aid to teaching or in the preparation of teaching materials.
进行分析的原因是为了获取有关语言学习者普遍难点的信息，作为教学或准备教学材料的一种辅助方式。
Based on analysing characteristics of error curved surface of the network, the authors have advanced the rapid BP algorithm, which can greatly raise the learning speed.
通过分析网络误差曲面特征，提出了快速BP算法，它可以大幅度地提高学习速度。
The learning of Backpropagation Neural Network (BPNN) aimed at lowering the classification error, usually assuming that all the samples had equal price when misclassifications were made.
传统的反向传播神经网络(BPNN)学习以分类错误最小为目标，通常假定在分类错误时所有样本的代价完全相同。
Then, the feedback error learning is applied to reduce the learning errors.
然后应用反馈误差学习法修正学习误差。
Sometimesthe learning process is by trial and error.
有时，这样的学习过程是要通过反复试验的。
Then some parameters of the controller are modulated by hybrid learning algorithm of ladder descent (LD) and least square error (LSE) so as to attain better control precision.
然后通过梯度下降法和最小二乘法相结合的混合学习算法，对控制器参数进行调整以提高其控制精度。
The paper presents a method of Chinese chunk recognition based on Support Vector Machines (SVM) and transformation-based error-driven learning.
本文研究了一种支持向量机(SVM)和基于转换的错误驱动学习相结合的汉语组块识别方法。
When applying the algorithm to network behavior intelligent learning of intrusion detection system, the error rate is about 10%.
将该算法应用于入侵检测系统的网络行为智能学习，其误报率仅为10%左右。
A periodic mixed adaptive law and an adaptive repetitive learning control one are constructed to ensure the asymptotic convergence of the tracking error in the sense of square error norm.
通过引入参数周期自适应律，设计出的自适应控制策略，使跟踪误差平方在一个周期上的积分范数渐近收敛于零。
They emphasize the importance of learning from this and putting in place system changes to minimize this kind of error.
他们强调了吸取此次教训和进行系统改变以避免类似错误的重要性。
Based on the measurement process and learning of measuring error, a novel method of using the limit point to evaluate the static characteristics of the nonlinear transducer is presented.
基于对测量过程、测量误差的认识，提出了一种利用极限点法评估非线性传感器静态特性的一种新方法。
It has multiple sets of parallel versions, and the results should be using special statistical methods to reduce error and learning effects of testing.
测评结果的评价应使用特殊的统计学方法减少测验误差和练习效应。
This paper classifies patterns by using four-layer BP network and the learning method of error inverse propagation.
文章在深入分析基本BP算法的基础上，采用四层BP网络，利用误差逆传播学习方法实现了对模式的分类。
In the training process, the adaptive learning rate and error batch-mode process are introduced to accelerate the training rate.
在神经网络自学习过程中，引入了自适应学习速率和误差批处理法，加快了学习速度。
This paper proposes a new method for recognizing Chinese time expression based on the heuristic error-driven learning.
本文提出了一种基于启发式错误驱动学习的中文时间表达式识别的新方法。
Based on fuzzy entropy rule and sum-squared error rule, a fuzzy learning method was presented. According to this method, BP neural network was used to model the performance of air-conditioning units.
基于模糊熵准则和误差平方和准则建立了模糊学习算法，基于该模糊学习算法，应用BP神经网络对柜式空调机组的性能进行了模拟。
In the paper, a modified constant modulus algorithm (MCMA) is proposed. The proposed algorithm minimizes a modified error function and the learning-rate is multiplied by received sequences.
采用一种修正恒模算法(MCMA)，该算法使修正的误差函数最小并且自适应学习率由接收序列即时调整。
In the paper, a modified constant modulus algorithm (MCMA) is proposed. The proposed algorithm minimizes a modified error function and the learning-rate is multiplied by received sequences.
采用一种修正恒模算法(MCMA)，该算法使修正的误差函数最小并且自适应学习率由接收序列即时调整。
应用推荐