Library / Computational Thinking DPF
Jump to passage
In this reading

Link to current text

Published source confirmed at last check

Source changed 2026-10-03 08:25:59 UTC · snapshot created 2026-10-03 08:26:43 UTC · last check 2026-10-03 09:10:20 UTC

CMP.7:3 - Forces

ForceWhat must be reconciled
Expressive rules and learnabilityA large rule family can represent more targets while requiring more information or search.
Available feedback and target useRecorded labels or rewards may differ from the response the recipient actually needs.
Fit and generalizationLow loss on used examples leaves questions about unseen cases and changed conditions.
Statistical and computational efficiencyA class can be learnable in principle while obtaining its selected rule remains unaffordable.
Stability and adaptationRetaining past information helps under stable conditions but can obstruct a changed target.
Point prediction and retained ambiguityOne chosen answer is convenient; unresolved alternatives can matter to the next action.