990 MB

Ctrl+K

2 contributors

CharlesCNorton

neural_reversible: analog read-noise and conductance-mismatch sweeps on the reversible matrix stack. The permutation stays bit-exact through read noise sigma ~ 0.10 (errors at 0.15, where the 0.5-margin error model predicts) and conductance mismatch sigma_G ~ 0.10, the same tolerances neural_matrix8 measures; README states the confirmed tolerance rather than implying it.

79eda78 8 days ago

llm_integration
8-bit threshold-logic CPU family: ternary-weight gate networks from a one-instruction SUBLEQ machine to an RV32IM plus F-subset RISC-V processor that runs stock-compiler C; composed IEEE-754 float pipelines with round-to-nearest-even bit-exact to hardware and metadata-driven verification; fully-wired rv32 datapath, FCVT int/float conversions, single gate-routed CPU runtime, leveled fast evaluation; single-file docs and consolidated machine runtime; strict-ternary build 10 days ago
routing
8-bit threshold-logic CPU family: ternary-weight gate networks from a one-instruction SUBLEQ machine to an RV32IM plus F-subset RISC-V processor that runs stock-compiler C; composed IEEE-754 float pipelines with round-to-nearest-even bit-exact to hardware and metadata-driven verification; fully-wired rv32 datapath, FCVT int/float conversions, single gate-routed CPU runtime, leveled fast evaluation; single-file docs and consolidated machine runtime; strict-ternary build 10 days ago
src
Give neural_attractor and neural_reversible a machine metadata field and eval_all skip entries, so python src/eval_all.py variants/ skips them cleanly instead of erroring (it scores fitness variants and skips standalone machines by that field). README sync: list both new machines in the variant table, intro, and repository layout; correct the standalone-machine count (5->7), the eval_all skip count (four->seven), and the universal-constructor family round-trip (23->26 files, 551->971 MB, both new files codec-verified byte-identical). 8 days ago
tests
Add neural_matrix8 and neural_subleq8io (universal constructor); move dev scripts to tools/ 9 days ago
tools
neural_reversible: analog read-noise and conductance-mismatch sweeps on the reversible matrix stack. The permutation stays bit-exact through read noise sigma ~ 0.10 (errors at 0.15, where the 0.5-margin error model predicts) and conductance mismatch sigma_G ~ 0.10, the same tolerances neural_matrix8 measures; README states the confirmed tolerance rather than implying it. 8 days ago
variants
Give neural_attractor and neural_reversible a machine metadata field and eval_all skip entries, so python src/eval_all.py variants/ skips them cleanly instead of erroring (it scores fitness variants and skips standalone machines by that field). README sync: list both new machines in the variant table, intro, and repository layout; correct the standalone-machine count (5->7), the eval_all skip count (four->seven), and the universal-constructor family round-trip (23->26 files, 551->971 MB, both new files codec-verified byte-identical). 8 days ago
.gitattributes

1.57 kB
8-bit threshold-logic CPU family: ternary-weight gate networks from a one-instruction SUBLEQ machine to an RV32IM plus F-subset RISC-V processor that runs stock-compiler C; composed IEEE-754 float pipelines with round-to-nearest-even bit-exact to hardware and metadata-driven verification; fully-wired rv32 datapath, FCVT int/float conversions, single gate-routed CPU runtime, leveled fast evaluation; single-file docs and consolidated machine runtime; strict-ternary build 10 days ago
.gitignore

41 Bytes
8-bit threshold-logic CPU family: ternary-weight gate networks from a one-instruction SUBLEQ machine to an RV32IM plus F-subset RISC-V processor that runs stock-compiler C; composed IEEE-754 float pipelines with round-to-nearest-even bit-exact to hardware and metadata-driven verification; fully-wired rv32 datapath, FCVT int/float conversions, single gate-routed CPU runtime, leveled fast evaluation; single-file docs and consolidated machine runtime; strict-ternary build 10 days ago
README.md

56.7 kB
neural_reversible: analog read-noise and conductance-mismatch sweeps on the reversible matrix stack. The permutation stays bit-exact through read noise sigma ~ 0.10 (errors at 0.15, where the 0.5-margin error model predicts) and conductance mismatch sigma_G ~ 0.10, the same tolerances neural_matrix8 measures; README states the confirmed tolerance rather than implying it. 8 days ago
neural_computer.safetensors

46 MB
xet

8-bit computer decode and PC sequencing as threshold gates: a 4-to-16 opcode one-hot decoder and a next-PC network (PC+2/PC+4 increment chains plus a priority mux over PC+2, PC+4, the conditional-jump mux, and the direct target). The runtime dispatches on the gate one-hots and takes the next PC from the mux instead of Python slicing and PC+2. Full 10/10 CPU suite passes; all variants rebuilt. Completes decode/PC-as-gates across every runtime (rv32, subleq, 8-bit computer). 8 days ago
todo.md

105 Bytes
8-bit computer decode and PC sequencing as threshold gates: a 4-to-16 opcode one-hot decoder and a next-PC network (PC+2/PC+4 increment chains plus a priority mux over PC+2, PC+4, the conditional-jump mux, and the direct target). The runtime dispatches on the gate one-hots and takes the next PC from the mux instead of Python slicing and PC+2. Full 10/10 CPU suite passes; all variants rebuilt. Completes decode/PC-as-gates across every runtime (rv32, subleq, 8-bit computer). 8 days ago