Modifying convolutional neural networks enables untrained AI to mimic human brain activity, rivaling trained systems.
Key Details
- 1Johns Hopkins research shows biologically inspired AI architectures can simulate human brain patterns before training.
- 2Convolutional architectures, when tweaked, better align with patterns seen in human and primate brains than other models.
- 3Transformers and fully connected networks showed little change in brain-like activity when similarly modified.
- 4Untrained CNNs matched the brain-similarity of conventional trained AI, which usually require massive datasets.
- 5Findings published in Nature Machine Intelligence highlight the importance of architecture over traditional data-heavy training.
Why It Matters
This research challenges prevailing AI paradigms by emphasizing architectural design over large-scale data training, suggesting a pathway toward more efficient, brain-like AI systems. For radiology and imaging AI, biologically aligned models could improve interpretability, reduce resource requirements, and lead to smarter diagnostic tools.
Source
EurekAlert
Related News
•EurekAlert
AI-Driven CT Imaging Predicts Cardiac Events in Large UK Cohort
An AI tool analyzing CCTA images can predict future cardiovascular events and death in patients with suspected stable coronary artery disease.
•EurekAlert
AI Tool from UCLA Targets Undiagnosed Alzheimer's and Diagnostic Disparity
UCLA researchers developed an AI model using EHR data to better detect undiagnosed Alzheimer's disease, especially in underrepresented groups.
•EurekAlert
AI Multimodal Models Improve Breast Cancer Recurrence Risk Prediction
Initial results from an ECOG-ACRIN and Caris Life Sciences collaboration show AI-driven multimodal models can more accurately predict recurrence risk in early-stage breast cancer.