36What are active learning and semi-supervised learning, and when do you use them?▼mediumGoogleAmazonMeta1 replies◆ premiumLabels are the expensive bottleneck in ML, and these two techniques attack it from different angles. The signal is knowing active learning chooses what to label while semi-supervised uses unlabeled data directly. Here is the answer.Open full answer →
62What is weak supervision, and how do you train models with noisy or programmatic labels?▼mediumGoogleAmazonSnorkel2 replies◆ premiumHand-labeling at scale is the bottleneck. Weak supervision generates labels programmatically instead, and the signal is whether you can explain how a label model denoises conflicting sources into probabilistic labels. Here is the answer.Open full answer →
74What is positive-unlabeled (PU) learning, and when do you need it?▼hardAmazonGoogleMeta1 replies◆ premiumMany real problems give you confirmed positives but never confirmed negatives, only unlabeled data. The shortcut everyone reaches for quietly biases the model. The signal is naming the regime and its fix. Here is the answer.Open full answer →
