← Back to article

Equation 11 · The Hardest Unsolved Problems in Small and On-Device AI

What does this equation mean?

FiF_i

Read the formula alongside the article passage below. Each part has a deeper page with its role in the equation, the supporting passage and nearby citations.

the computing and storing. Read the equation part by part below; each part has a contextual explanation and a link to its mathematical background.

Read it piece by piece

FiF_i

Symbol F_i

the computing and storing.

Understand this part →

subscript

subscript

The lower label selects a particular version, component, or indexed member of the quantity. For example, x₀ and xₜ can be values at different positions.

Understand this part →

How to interpret it

Read this expression with the definitions, units, and assumptions supplied by the article.

What the article says around this equation

One standard mitigation is regularization: penalize the optimizer for moving parameters that mattered to earlier tasks. The best-known form estimates a per-parameter importance weight — commonly the diagonal of the Fisher information, FiF_i — from the old task, and adds it to the new loss:

Read the equation in its article →

Sources cited in the article section

These citations give research context. Read each source to check which claims it supports.

Return to The Hardest Unsolved Problems in Small and On-Device AI

Browse the mathematical compendium →