Information Processing Paradigm
A dominant theoretical framework in cognitive science and AI that draws an analogy between the brain or mind and a computer, holding that cognitive processes are fundamentally operations of encoding, storing, transforming, and retrieving information. This paradigm has significantly influenced the design philosophy of modern deep learning architectures.
Timeline (last 90 days)
The core claim of the article is that the brain does not process information, nor is it a computer.
Current mainstream deep learning architectures (including Transformers and convolutional neural networks) inherit the core assumptions of the information-processing paradigm: information can be encoded as numerical vectors, hierarchically transformed, and read from or written to explicit locations.
Alternative frameworks such as predictive coding, embodied cognition, and active inference have yet to displace the mainstream information-processing paradigm in terms of engineering practicality.
All Facts (3)
The core claim of the article is that the brain does not process information, nor is it a computer.
50%UnverifiedCurrent mainstream deep learning architectures (including Transformers and convolutional neural networks) inherit the core assumptions of the information-processing paradigm: information can be encoded as numerical vectors, hierarchically transformed, and read from or written to explicit locations.
50%UnverifiedAlternative frameworks such as predictive coding, embodied cognition, and active inference have yet to displace the mainstream information-processing paradigm in terms of engineering practicality.
50%