From the course: Artificial Intelligence Foundations: Machine Learning

Unlock the full course today

Join today to access over 23,200 courses taught by industry experts.

Understanding learning algorithms and model training

Understanding learning algorithms and model training

From the course: Artificial Intelligence Foundations: Machine Learning

Start my 1-month free trial Buy for my team

Understanding learning algorithms and model training

“

- A machine learning algorithm or learning algorithm for short studies data to find trends and patterns during the training process. During the training process, the machine makes multiple passes or iterations over the training data. These iterations are called epochs. The trends and patterns uncovered by the learning algorithm are stored in a mathematical model or simply called the model. The number of epochs is a critical parameter called a hyperparameter to the training process that can result in a better performing model. Typically, a portion of your dataset, 80% is used for training, and the remaining 20% is reserved for evaluating your model's performance after training completes While training on 80% of the data, a loss function is used to measure how good the model is at predicting the expected value. In simple terms, loss functions measure how far an estimated value is from its actual value. The model makes…

Contents