The optimal line found is not guaranteed to be the line of best fit. Convergence to the line of best fit depends on the number of iterations, batch size, learning rate, and loss function. It is always good practice to observe the loss function over time as it can help you troubleshoot problems or hyperparameter changes.
How it works...
Get TensorFlow Machine Learning Cookbook - Second Edition now with the O’Reilly learning platform.
O’Reilly members experience books, live events, courses curated by job role, and more from O’Reilly and nearly 200 top publishers.
