---
title: "Information Plasticity"
type: "entity"
entity_kind: "concept"
status: "hub"
canonical_name: "Information Plasticity"
aliases: []
first_seen: "2026-07-12T00:00:00.000Z"
writer_model: "claude-sonnet-5"
connects_to: ["Fisher Information Matrix","critical periods","Alessandro Achille","Stefano Soatto","Information Bottleneck"]
---


Achille, Rovere & Soatto's name for a rise-then-fall trajectory in the Fisher Information Matrix (FIM) of a deep network's *weights* over training — information rises early, then falls, and the fall marks the closing of the network's critical period for a given deficit. Presented by its authors as an Information-Bottleneck-style account of critical periods, but built on a different quantity than Tishby's IB tracks: Shannon mutual information of *activations* versus Fisher information of *weights*. [[claim-critical-periods-fim-signal-does-not-correlate-with-ib-compression-signal]] finds the two signals do not in fact correlate in the founding paper's own data — the resemblance is vocabulary, not demonstrated shared mechanism. The framework's biological-metaphor and validation-scope caveats live in [[claim-critical-periods-arise-from-information-plasticity-not-biology]], [[claim-founding-dnn-critical-period-paper-validated-on-animal-data-only]], and [[claim-achille-soatto-disclaim-dnn-as-valid-model-of-biology]].

## References
- [[claim-critical-periods-arise-from-information-plasticity-not-biology]] · [[claim-critical-periods-fim-signal-does-not-correlate-with-ib-compression-signal]] · [[claim-founding-dnn-critical-period-paper-validated-on-animal-data-only]] · [[claim-achille-soatto-disclaim-dnn-as-valid-model-of-biology]]
- [[entity-alessandro-achille]] · [[entity-stefano-soatto]] · [[entity-information-bottleneck]]
