FullPCNetwork.h File Reference

Orchestrates FullPCLayer's phases, matching DirectKPPCNetwork's exact four-phase DKP-PC structure (see that class's own docs for the full phase breakdown and citation), plus network-level toggles for muPC scaling and residual connections – both OFF by default, so a plain FullPCNetwork with every toggle left alone reproduces DirectKPPCNetwork exactly (confirmed at the layer level: FullPCLayer with a=1.0, useResidual=false is a bit-identical match to DirectKPPCLayer). More...

#include <deepity/backend/Backend.h>
#include <deepity/layers/FullPCLayer.h>
#include <deepity/utils/DeviceMemoryArena.h>
#include <deepity/utils/MemoryArena.h>
#include <memory>
#include <random>
#include <vector>

Go to the source code of this file.

Classes
class	Deep::FullPCNetwork
	Predictive Coding network combining muPC scaling, optional residual connections, and DKP direct feedback – see the file-level note above for how its defaults reproduce DirectKPPCNetwork exactly. More...

Namespaces
namespace	Deep
	This file exists to provide both Tensor.h and IComputeBackend.h with device types without introducing circular dependencies.

Detailed Description

Orchestrates FullPCLayer's phases, matching DirectKPPCNetwork's exact four-phase DKP-PC structure (see that class's own docs for the full phase breakdown and citation), plus network-level toggles for muPC scaling and residual connections – both OFF by default, so a plain FullPCNetwork with every toggle left alone reproduces DirectKPPCNetwork exactly (confirmed at the layer level: FullPCLayer with a=1.0, useResidual=false is a bit-identical match to DirectKPPCLayer).

THIS PASS: muPC scaling and residual connections only. iPC, muP-style per-layer LR scaling, momentum settling, and cross-entropy terminal loss are not yet added – each is meant to become its own, separate toggle later, following the same pattern.