如何建立一个将两个数字相乘的神经网络 [英] How to build a Neural Network to multiply two numbers

问题描述

我正在尝试建立一个将两个数字相乘的神经网络.为此，我接受了scikit-learn的帮助.我要一个具有2个隐藏层(5、3)和ReLU作为激活函数的神经网络.

I am trying to build a neural network which would multiply 2 numbers. To do the same, I took help of scikit-learn. I am going for a neural network with 2 hidden layers, (5, 3) and ReLU as my activation function.

我已如下定义我的 MLPRegressor :

X = data.drop('Product', axis=1)
y = data['Product']
X_train, X_test, y_train, y_test = train_test_split(X, y)
scaler = StandardScaler()
scaler.fit(X_train)

X_train = scaler.transform(X_train)
X_test = scaler.transform(X_test)
mlp = MLPRegressor(hidden_layer_sizes=(5, 3), activation="relu", learning_rate="adaptive", max_iter=500000, verbose=True, validation_fraction=0.25)

此处， data 是包含3列，2个随机数和1个Product列的数据框.问题是我得到的损失约为10 ^ 14.在这种情况下，如何减少这种损失，改善模型性能以及所有可能的更改可以帮助我?

Here, data is the dataframe which contains the 3 columns, 2 random numbers and 1 Product column. The issue is the loss that I get is of order 10^14. How do I reduce this loss, improve my model performance and what all possible changes can help me out in this situation?

推荐答案

我不是NN专家.我将对输入进行日志转换，然后将其输入网络，然后对输出进行幂运算.只是一个想法.

I am not an expert in NNs. I would do log-tranform of the inputs, then feed them into a network, then exponetiate the output. Just a thought.

这篇关于如何建立一个将两个数字相乘的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！