Your next step
Useful models can be smaller and simpler
Linear models, trees, ensembles, routing, distillation, precision.
Start learningWhat you’ll learn
A simple model can fit a simple task
Recognize a linear model used for a numerical estimate.
About 4 minutes · Open activity
A decision tree follows learned splits
Trace a tree through a small classification example.
About 4 minutes · Open activity
An ensemble combines model outputs
Explain how multiple predictions can be combined.
About 4 minutes · Open activity
A mixture of experts routes computation
Distinguish sparse model routing from several chatbots voting.
About 4 minutes · Open activity
Total parameters and active work differ
Interpret two size numbers for a sparse model.
About 4 minutes · Open activity
Distillation teaches another model from a teacher
Recognize a student model learning from teacher behavior.
About 4 minutes · Open activity
Quantization uses lower-precision numbers
Explain the memory tradeoff of reduced numeric precision.
About 4 minutes · Open activity
Choose the tradeoff for the task
Select a model using supplied quality, delay and resource evidence.
About 4 minutes · Open activity
Choose a model for a small device
Use supplied task results and memory constraints to compare a simple model, a compressed model and a larger remote option without declaring a universal winner.
About 6 minutes · Open activity