AI Information Bottleneck & Latent Abstraction Visualizer

Scenario & Controls

Domain Preset

Latent Bottleneck Size 4

Noise Filter Threshold 0.65

Input Noise Level 0.35

Raw Feature Matrix (64-dim Input Sample)

Neural Abstraction Flow (Input → Filter → Latent → Reconstruction) Active Flow

IB Diagnostics

Input Shannon Entropy 5.82 bits Raw uncompressed noise content

Latent Info Retention 64.2% Target concept signals preserved

Discarded Noise Ratio 72.8% Redundant & jitter paths pruned

Concept Classification Acc 94.1% Downstream task invariance score

Node & Vector Inspector Hover or Click Node

[System Ready] Hover over network nodes in the flow visualization above to inspect individual feature activation vectors, cosine similarity scores, and local Shannon entropy decay.

Core Principle: Information Discarding

The Essence of AI: Real-world inputs are saturated with high-dimensional noise. Neural networks do not retain raw inputs; they systematically discard unnecessary information (Information Bottleneck Principle: min I(X;Z) s.t. max I(Z;Y)).

By shrinking the central layer (Latent Bottleneck), the network forces high-frequency noise and background clutter to drop out, distilling invariant topological concepts.