Closed joelowj closed 5 years ago
89a605c74889d1202dac1794444fbec3d42aaab4, Tobit Model Weights & Tobit Model: loss, standard error, L1 error has been cleared.
It seems that the r square coefficient approach for Neural Network with Non-Linear Data did not clear the grader.
36468806b9fc30a4cf39cc0e6517fd2986c0ad59, Neural Network with Non-Linear Data has been cleared. I have changed the approached from using
u = tf.reduce_sum(tf.square(output - y)) v = tf.reduce_sum(tf.square(tf.reduce_mean(y) - y)) r_square_coefficient = 1 - (u / v)
to just evaluation the test accuracy on loss which was defined to be loss = tf.reduce_mean(tf.square(output - y)). The solution obtained was acc_test = 0.041695457.
Current submissions
Tobit Model Weights 20/20 Tobit Model: loss, standard error, L1 error . 20/20 Linear Regression with non-linear data 20/20 Linear Regression Model Score 20/20 Neural Network with Non-Linear Data 20/20
My implementation for Neural Network with Non-Linear Data did not clear the grader. Feel free to start a discussion if you managed to clear the grader or have an even better implementation.