Here are the classes, structs, unions and interfaces with brief descriptions:

[detail level 12]

NDeep	This file exists to provide both Tensor.h and IComputeBackend.h with device types without introducing circular dependencies
CCPUBackend	CPU implementation of IComputeBackend: SIMD (via Activations.h) for elementwise ops, BLAS for GEMM. Graph capture/replay are no-ops (there's no async device queue to record)
CCUDABackend	CUDA implementation of IComputeBackend: device kernels for elementwise ops, cuBLAS for GEMM, CUTLASS for the fused forward path, CUDA graphs for capture/replay. See src/backend/cuda/ for the implementation, split by concern to mirror this interface's own section grouping
CIComputeBackend	Device-agnostic compute backend interface: every numerical primitive a layer/network needs, implemented once each by CPUBackend (SIMD/BLAS) and CUDABackend (kernels/cuBLAS/CUTLASS), so layer code never branches on device directly
CTensor	A device-aware, RAII-managed, move-only buffer – see the file-level note above for the full ownership/device contract
CConvPCLayer	Convolutional Predictive Coding layer (im2col-based). See the file-level warning above before enabling an unclamped middle layer
CDirectKPPCLayer	Predictive Coding layer using Direct Kolen-Pollack feedback alignment (DFA): a per-layer feedback matrix Psi, trained to gradually correlate with W's transpose chain, replaces symmetric weight transport for the feedback term. See DirectKPPCNetwork.h's class docs and the paper's Appendix A.1
CDiscriminativePCLayer
CFullPCLayer	PC layer combining muPC scaling, optional residual connections, and DKP direct feedback – every extra OFF by default, so plain defaults reproduce DirectKPPCLayer exactly. See the file-level note above for the full design rationale
CGaussSeidelPCLayer	PC layer with Gauss-Seidel (sequential-sweep) settling dynamics, in place of the usual simultaneous update. Not yet gradient-checked – see the file-level warning above
CTensorDescriptor	A named, shaped view into a layer's weight/bias data, for ModelIO's save/load (see Layer::GetStateDict())
CLayer	A deepity layer virtual class
CRBLayer	Restricted Boltzmann-style Predictive Coding (PC) Layer
CSimpleConvPCLayer	Convolutional PC layer, precision-free, AdamW-capable, routed through IComputeBackend for GPU portability – see the file-level warning above for the GPU path's verification status
CSimplePCLayer	Predictive Coding layer without precision weighting – the simpler, unweighted-energy counterpart to DiscriminativePCLayer
CConvPCNetwork	Convolutional Predictive Coding Network built from ConvPCLayer
CDirectKPPCNetwork	Predictive Coding network built from DirectKPPCLayer, using Direct Kolen-Pollack feedback alignment (DFA) instead of symmetric weight transport. See the file-level warning above on its current verification status
CDiscriminativePCNetwork	An abstracted class for an array of DiscriminativePCLayer
CFullPCNetwork	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
CGaussSeidelPCNetwork	Predictive Coding network built from GaussSeidelPCLayer, sweeping layers sequentially rather than updating them simultaneously. See the file-level warning above on its current verification status
CSimpleConvPCNetwork	Convolutional Predictive Coding Network built from SimpleConvPCLayer – precision-free, AdamW-capable, device-aware
CSimplePCNetwork	An abstracted class for an array of SimplePCLayer
CDeviceMemoryArena	A 64-byte-aligned bump-pointer allocator over a single contiguous block of device memory, obtained via a supplied IComputeBackend (expected to be a CUDABackend in practice, though this class itself doesn't hard-require that specific type)
CMemoryArena	A 64-byte-aligned bump-pointer allocator over a single contiguous block of host memory. Every chunk handed out via AllocateFloats() is itself 64-byte aligned, satisfying this codebase's strict alignment requirement for AVX2/AVX-512 loads
CModelIO	Static save/load helpers for any network type exposing GetLayers() – templated so it works across every PC network variant without each one reimplementing serialization
CProfileAccumulator	One layer's accumulated time-per-phase, in seconds – see the file-level note for the reconciliation invariants (PhaseSum() vs. the top-level totals vs. external wall-clock)
CProfileEntry	One registered layer's profiling data: its print label paired with its accumulator
CScopedTimer	No-op stand-in for the PCN_PROFILE build of ScopedTimer above, so PCN_TIME() call sites compile identically either way
CStreamAlignedBatcher	Builds batches with a fixed, grouped number of examples per class – see the file-level note for why this exists and what it deliberately doesn't own
CTimer	Implementation by Alex: https://www.learncpp.com/cpp-tutorial/timing-your-code/