Reference library
Turing Computability with Neural Nets
Paper summary
Constructs a finite recurrent sigmoidal neural network capable of simulating a universal Turing machine without higher-order connections. The proof intentionally separates computability from training and practical implementation.
Relevance to the project
Supports a simple recurrent computational substrate while clarifying that expressiveness alone does not select F. Analyze precision and discoverability separately.
The ideal construction does not guarantee finite-precision robustness or useful spontaneous computation.
Source record
- Reference ID
- pdf-https-www-sontaglab-org-ftpdir-aml-turing-pdf
- Archived version
- Direct PDF cited in project notes; publication status needs source-specific inspection
- Summary provenance
- reference-library/papers/pdf-https-www-sontaglab-org-ftpdir-aml-turing-pdf/metadata.json · summary
- Review status
- initial orientation summary; not a critical full-paper review
- Reading scope
- Selected abstract/opening and available closing discussion/conclusion passages in the preserved text extract; broader project notes provide context. No reproduction of experiments, exhaustive methods review, or equation/figure audit.