Fact check
“The decoder has two branches: one predicts image structure and the other predicts image content.”
Reasoning
The MIT Technology Review article states that the brain decoder consists of two branches: one predicts the structure of an image (e.g., colors and layout) and the other predicts its content (e.g., objects like bananas). This directly matches the claim.
On confidence: The provided source explicitly describes the decoder as having two branches—one for predicting image structure and another for predicting image content.
Important context
The description refers to a specific AI brain‑decoder used to reconstruct visual experiences from fMRI data, not to all decoders in general.
Evidence
Supporting (1)
- Tier 1 — Primary sourceAn AI “mind-reading” tool can reconstruct what you’re looking at based on a brain scan | MIT Technology Review
high-resolution fMRI scanner. Crucially, their “brain decoder” has two branches—one to predict the structure of an image (where the colors are, for instance) and a second to predict its content (for example, a bunch of bananas on a plate).…
Limitations
The verification is limited to the information presented in the cited article; no additional sources were consulted. No independent origin corroborated this claim, so it cannot be verified and confidence cannot be high.
- Last verified:
- Oct 1, 2026, 12:22 PM CDT
- Pipeline:
- 2.1.0
- Claim type:
- Factual
Where this claim appeared
An AI “mind-reading” tool can reconstruct what you’re looking at based on a brain scanMIT Technology Review · Jessica Hamzelou