Abstract
Deep neural networks (DNNs) are powerful computational models, which generate complex, high-level representations that were missing in previous models of human cognition. By studying these high-level representations, psychologists can now gain new insights into the nature and origin of human high-level vision, which was not possible with traditional handcrafted models. Abandoning DNNs would be a huge oversight for psychological sciences.
Original language | English |
---|---|
Article number | e414 |
Journal | Behavioral and Brain Sciences |
Volume | 46 |
DOIs | |
State | Published - 6 Dec 2023 |
All Science Journal Classification (ASJC) codes
- Neuropsychology and Physiological Psychology
- Physiology
- Behavioral Neuroscience