Encog/神经营养保存神经网络 [英] Encog/neuroph save Neural Network

问题描述

我是神经网络领域的新手(说实话我几天前才开始).我想在OCR应用程序中使用神经网络来识别手写文本.

Im new to the Neural Network field(to tell the truth i just started few days back). I want to use neural network in my OCR application to recognize handwritten text.

我想知道的是，在初次训练后是否可以训练网络.换句话说，我将在开始时训练几个字符，但我想稍后在网络中添加更多字符，而又不影响先前训练过的数据的存在. ).如果可能的话，我该如何使用encog完成此操作.

what i want to know is, is it possible to train the network after the initial training. In other words im going to train few characters in the beginning but i want to add more characters to the network later without affecting the existence of the previously trained data.(suppose i've created the neural network with adequate out put neurones for additional characters). If this is possible how can i use encog to get this done.

谢谢

推荐答案

是，不是.如果您训练相同的神经网络来识别新字符，则权重(θ)当然会在各层之间变化以适应新字符.由于您的X/Y值已更改，因此可能还需要更改成本函数以更准确地适应新数据.但是，只要您的错误率在可接受的范围内，就不会有麻烦.

Yes and no. If you train the same neural network to recognize new characters, the weights (θ) will certainly change between the layers to accommodate the new characters. Since your X / Y values have changed, the cost function may also need to change to fit the new data with more accuracy. However as long as your error rate is within acceptable values, you should have no trouble.

另一方面，您可以使用2个神经网络-一个用于初始字符集，另一个用于新字符集. Neuroph允许您将每个神经网络保存到一个文件中，并且可以根据需要加载适当的神经网络.

On the other hand, you could use 2 neural networks - one for your initial set and the other for your new set of characters. Neuroph allows you to save each neural network into a file and you can load the appropriate one based on your needs.

PS:我在这里假设字符是指"A"/"B"/"C"，而不是诸如x1/x2/x3(网络特征)之类的神经网络变量.

PS: I assume here that characters refers to 'A' / 'B' / 'C' and not neural network variables such as x1 / x2 / x3 (characteristics of the network)

这篇关于Encog/神经营养保存神经网络的文章就介绍到这了，希望我们推荐的答案对大家有所帮助，也希望大家多多支持IT屋！