Thu Apr 25 10:49:08 2019

regression_1d:
  python version: 3.6.8
  keras version: 2.2.4
  Neural network to solve a 1d regression problem.
  The data is read from external files.
(100, 2)
(10, 2)
[0.598499 0.60241  0.528659] [-0.40407  -0.542388  1.06106 ]
[2.03206 2.44061 2.37146] [1.3084  1.27157 2.95062]

Training:

step 0: training cost = 16.0363
step 10: training cost = 8.91028
step 20: training cost = 5.00258
step 30: training cost = 2.85581
step 40: training cost = 1.6733
step 50: training cost = 1.0194
step 60: training cost = 0.655792
step 70: training cost = 0.451981
step 80: training cost = 0.336455
step 90: training cost = 0.269957
step 100: training cost = 0.230891

Testing:


10/10 [==============================] - 0s 1ms/step
Test cost: 0.1439816951751709
Weights =  [[1.2397591]]
Bias =  [1.8072875]

  Graphics saved as "regression_1d.png"

regression_1d:
  Normal end of execution.
Thu Apr 25 10:49:16 2019