Hi Luke, the thing is that it’s normal behavior for neural networks, since optimization process is basically stochastic. You can help it a bit with fixing a random seed + you have to run training several times and check mean and standard deviation of your loss

Co-founder of consulting firm Neurons Lab and advisor to AI products builders. On Medium, I write about proven strategies for achieving ML technology leadership

Get the Medium app

A button that says 'Download on the App Store', and if clicked it will lead you to the iOS App store
A button that says 'Get it on, Google Play', and if clicked it will lead you to the Google Play store