Tensor by Tensor

02.22 · UNIT 06 · Sequence models and memory · Lab

Lab: train a gated sequence predictor

A gated sequence lab tests whether controlled memory helps a prediction task.

PLAIN-LANGUAGE INTRODUCTION

The idea

A gated sequence lab tests whether controlled memory helps a prediction task.

A worked example

For inputs [1,0,1], an illustrative gated model keeps hidden states [0.2,0.15,0.4] and predicts target 1 with score 0.8.

The input

Training sequences, targets, and initial hidden states.

The result

Predictions, losses, and held-out measurements.

Why you use it

The lab connects gate equations to training and evaluation.

A limit to remember

One correct sequence does not prove that the model learned the rule.

Check your understanding

  1. Use sequence [1,0,1] with target 1. Keep its order unchanged.
  2. The shown hidden states [0.2,0.15,0.4] are plausible illustrative outputs. They are separate from the earlier plain RNN rule.
  3. Suppose the output score is 0.8. Compare it with the target using the chosen loss.
  4. Train on training sequences. Select settings with validation data. Report final held-out results separately.
  5. Common mistake: checking only training sequences can hide poor performance on unseen sequences.
Open the detailed notes ↗