Logistic regression training
First, you'll learn about the loss function for our machine learning classifier and implement it in TensorFlow. Then, we'll quickly train the model by evaluating the right TensorFlow node. Finally, we'll verify that our model is reasonably accurate and the weights make sense.
Developing the loss function
Optimizing our model really means minimizing how wrong we are. With our labels in one-hot style, it's easy to compare these with the class probabilities predicted by the model. The categorical
cross_entropy function is a formal way to measure this. While the exact statistics are beyond the scope of this course, you can think of it as punishing the model for more for less accurate predictions. To compute it, we multiply ...