Skip to content
sahil.science
Questions
Papers
Topics
Syntheses
Almanac
About
C⁶
2026
← Questions
Source-derived question
How can deep neural network models serve as testable, end-to-end trainable implementations of cognitive theories?
Algorithms and Data Structures
Cognitive Science
Deep Learning and Neural Networks
Sources that address it
Deep Learning for Cognitive Neuroscience
preprint
Related questions
How do removal and clustering, as two distinct abstraction operations over irrelevant details in symbolic explanations, differ in their effects on human understanding versus cognitive effort?
How does the forgetting-reconstructive hypothesis explain the memory benefits of interleaved practice over blocked practice?
What implications does cross-species evidence for the spacing effect have for designing curriculum learning schedules in machine learning?
Why might spaced presentation of training examples improve generalization in artificial neural networks, not just retention?
Does interleaved practice improve implicit or procedural learning, not just explicit skills?
How can a computational framework for modeling memory decay and retrieval probability be used to derive optimal spaced repetition schedules rather than relying on hand-tuned heuristics?
How can a nondeterministic finite automaton be converted into a deterministic one without losing expressive power?
How can a reaction-diffusion model, building on Turing's 1952 framework, explain the spontaneous emergence of spatial pattern from an initially homogeneous meristem?