README

If you see oscillating training loss, likely the descent steps are bouncing between two "valleys" - try using MomentumOptimizer.
Playing around with the step_size can help avoid non-covergence to nan
The std of the random_normal of the initial weights should be quite small (ex: stddev=0.01)
Also using RMSPropOptimizer really seems to help decrease the obj function (at least, better than the GradientDescent)

Name		Name	Last commit message	Last commit date
Latest commit History 4 Commits
README.md		README.md
multi_dim_linear_regression_example.py		multi_dim_linear_regression_example.py
multi_dim_multi_output_logistic_regression_example.py		multi_dim_multi_output_logistic_regression_example.py
multi_dim_single_output_logistic_regression_example.py		multi_dim_single_output_logistic_regression_example.py
multi_layer_nn_example.py		multi_layer_nn_example.py
one_dim_linear_regression_example.py		one_dim_linear_regression_example.py
simple_divisibilty_prediction.py		simple_divisibilty_prediction.py
utils.py		utils.py

Provide feedback