Training ialah proses mengajar model ML daripada data (mempelajari corak, melaraskan parameter), manakala inference ialah menggunakan model yang telah dilatih untuk membuat ramalan pada data baharu. Ia adalah fasa yang berbeza dengan ciri dan kos yang berbeza.
Training vs inference
TRAINING → teaching the model (the LEARNING phase):
→ feed lots of DATA → the model adjusts its parameters to learn patterns
→ computationally EXPENSIVE (lots of data, compute, time — e.g. training an LLM costs
huge resources); done once (or periodically to update)
→ produces a trained MODEL
INFERENCE → using the trained model (the PREDICTION phase):
→ give the trained model NEW input → it produces an output (prediction/generation)
→ much CHEAPER/faster than training (a single forward pass); done MANY times (every
time you use the model)
→ train once (expensive), infer many times (cheaper, in production)
