NEURAL-NETWORKS-EXPLAINED4 MIN READ
Sort Data, Parameters, and Hyperparameters
Distinguish training data, learned parameters, and human-chosen hyperparameters in neural-network training.
Sort each neural-network term by the lever it represents. Training data Learned parameters Hyperparameters Labeled customer examples used to teach the model No examples from enterprise customers in the training set Weights connecting one layer to the next Bias terms adjusted by the optimizer Learning rate chosen before or during training Dropout or regularization strength Number of epochs to train Refund cases mislabeled as no-refund
Read the full lesson
Sign up free — one personalized lesson every day, matched to your role and goals.
Already have an account? Sign in