How to train a Regression model for single input and multiple output?

问题

I have trained a regression model that approximates the weights for the equation : Y = R+B+G For this, I provide pre-determined values of R, B and G and Y, as training data and after training the model, the model is successfully able to predict the value of Y for given values of R, B and G. I used a neural network with 3 inputs, 1 dense layer (hidden layer) with 2 neurons and the output layer (output) with a single neuron.

    hidden = tf.keras.layers.Dense(units=2, input_shape=[3])
    output = tf.keras.layers.Dense(units=1)

But, I need to implement the inverse of this. i.e., I need to train a model that takes in value of Y and predicts values of R, B and G that corrspond to that value of Y. I have just learnt that regression is all about a single output. So, I am unable to think of a solution and the path to it. Kindly Help.
(P.S Is it possible to use the model that I have already trained, to do this? I mean, once, the weights have been determined for R, B and G, is it possible to manipulate the model to use these weights to map Y to R, B and G?)

回答1:

Here is an example to start solving your problem using neural network in tensorflow.

import numpy as np
from tensorflow.python.keras.layers import Input, Dense
from tensorflow.python.keras.models import Model

X=np.random.random(size=(100,1))
y=np.random.randint(0,100,size=(100,3)).astype(float)   #Regression

input1 = Input(shape=(1,))
l1 = Dense(10, activation='relu')(input1)
l2 = Dense(50, activation='relu')(l1)
l3 = Dense(50, activation='relu')(l2)
out = Dense(3)(l3)

model = Model(inputs=input1, outputs=[out])
model.compile(
    optimizer='adam',
    loss=['mean_squared_error']
    )

history = model.fit(X, [y], epochs=10, batch_size=64)

来源：https://stackoverflow.com/questions/58037682/how-to-train-a-regression-model-for-single-input-and-multiple-output