Deepity
Ultra-fast, SIMD-accelerated Predictive Coding
Loading...
Searching...
No Matches
Linear.h File Reference

The identity activation and its (constant) derivative. More...

#include <algorithm>
#include <cstddef>
#include <deepity/utils/activations/ActivationMacros.h>

Go to the source code of this file.

Namespaces

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

Functions

static void Deep::linear (float *x, size_t n) noexcept
 Identity activation: f(x) = x. A no-op, kept as a real function so it can be used interchangeably with the other activations through ActivationFn.
static void Deep::dLinear (float *x, size_t n, bool activated=false) noexcept
 Derivative of linear(): a constant 1 everywhere.
static void Deep::dLinearInto (float *RESTRICT dst, const float *RESTRICT src, size_t n) noexcept
 Two-buffer variant of dLinear – src is unused (the derivative of a linear function is a constant), kept for signature consistency with To_dFn2's dispatch table.

Detailed Description

The identity activation and its (constant) derivative.