When you try to train a huge amount of data with limited computer memory, you can separate the whole training set to several batches that can fit into your computer memory. Then you feed these batches to your model one by one. After feeding all batches once, you complete one epoch. To successfully train your model, you need multiple epochs.

Epochs in Machine Learning

Burn-in is an initial phase before normally running your model. The epochs of burn-in is number of epochs to ramp learning rate from either 0 or 1 to your final learning rate. It is helpful to find good embeddings in some cases.

Burn-in in Machine Learning

The author tested 15, 50, and 100 epochs for Poincaré embeddings and chose 100 as the best number to train the model, with epochs of burn-in = 10.

University of Michigan - Ann Arbor

- Learning rate = 0.2
- Number of negative examples = 80 
- Number of epochs = 100
- Epochs of burn-in = 10 
- Number of dimensions = 2, 3, 5, 10, 50, 100

Improved Concept Embeddings for Learning Prerequisite Chains: Model parameters

Löffel, E. P. (2019). Improved Concept Embeddings for Learning Prerequisite Chains

Paper: https://pdfs.semanticscholar.org/6073/0900a80fcee29e9059fd293a1fa38742abf3.pdf

Github: https://github.com/eloffel/improved_embeddings

Learn Before

Related

Learn After