feat: modernize PSO and add convergence research
Migrate the package and examples to the tensor-native PyTorch implementation, add benchmark evidence, and add the guarded post-training convergence protocol with TensorBoard progress monitoring and hash-verified recovery. Constraint: Preserve one-shot official-test sealing and auditable research artifacts Rejected: Commit local .omc runs and downloaded datasets | multi-gigabyte runtime state is machine-local Confidence: high Scope-risk: broad Not-tested: Production CUDA run on pieroot-server
|
After Width: | Height: | Size: 186 KiB |
|
After Width: | Height: | Size: 206 KiB |
|
After Width: | Height: | Size: 464 KiB |
|
After Width: | Height: | Size: 268 KiB |
|
After Width: | Height: | Size: 406 KiB |
|
After Width: | Height: | Size: 217 KiB |
|
After Width: | Height: | Size: 281 KiB |
|
After Width: | Height: | Size: 298 KiB |
|
After Width: | Height: | Size: 92 KiB |
|
After Width: | Height: | Size: 162 KiB |
|
After Width: | Height: | Size: 294 KiB |
|
After Width: | Height: | Size: 132 KiB |
|
After Width: | Height: | Size: 126 KiB |
|
After Width: | Height: | Size: 250 KiB |
|
After Width: | Height: | Size: 337 KiB |
|
After Width: | Height: | Size: 232 KiB |