How is the spectralConvolution1dLayer forward computation process performed

Question

0 个投票

spectralConvolution1dLayer performs convolution on 1-D input using frequency domain transformations. The layer convolves the input by using the frequency domain representation, where convolution becomes multiplication via the Fourier theorem. I want to know how the spectral convolution is performed when the 1-D input is "CBT" dlarray and the weights is NumModes-by-InputSize-by-HiddenSize dlarray.

0 个评论
显示 -2更早的评论隐藏 -2更早的评论

请先登录，再进行评论。

请先登录，再回答此问题。

Follow Question

Answer 1

Matt J 2026-6-25，11:16

编辑：Matt J 2026-6-25，11:18

0 个投票

According to the doc you referenced, the convolution is performed with respect to the time dimension in that case,

For time series and vector sequence input (data with three dimensions corresponding to the channels, observations, and time steps), the layer convolves over the time dimension.

3 个评论
显示 1更早的评论隐藏 1更早的评论

Chuguang Pan 2026-6-26，3:28

编辑：Torsten 2026-6-26，15:18

在 MATLAB Online 中打开

@Matt J. Thanks for your answer. I want to know the internal computation details of the spectralConvolution1dLayer. How the predict/forward function of this layer is calculated. I have reviewed the spectralConvolution1dLayer.m file, however there is no concrete calculation details.

type spectralConvolution1dLayer.m
function layer = spectralConvolution1dLayer(numModes, hiddenSize, args)
%   Run "doc spectralConvolution1dLayer" for more information.

%   Copyright 2025 The MathWorks, Inc.

arguments
    numModes (1,1) {iValidateNumModes}
    hiddenSize (1,1) {iValidateHiddenSize}
    args.Name {nnet.internal.cnn.layer.paramvalidation.validateLayerName} = ''
    args.Weights = []
    args.WeightsInitializer = 'complex-glorot-normal'
    args.WeightL2Factor {iAssertValidFactor} = 1
    args.WeightLearnRateFactor {iAssertValidFactor} = 1
end
args.NumModes = numModes;
args.HiddenSize = hiddenSize;
args = nnet.internal.cnn.layer.util.gatherParametersToCPU(args);
args = iConvertToCanonicalForm(args);

player = nnet.internal.cnn.layer.SpectralConvolution1D(args.Name, args.NumModes, args.HiddenSize);
player.LearnableParameters.L2Factor = args.WeightL2Factor;
player.LearnableParameters.LearnRateFactor = args.WeightLearnRateFactor;

layer = nnet.cnn.layer.SpectralConvolution1DLayer(player);
layer.WeightsInitializer = args.WeightsInitializer;
layer.Weights = args.Weights;
end

function args = iConvertToCanonicalForm(args)
import nnet.internal.cnn.layer.util.convertToDouble
args.HiddenSize = convertToDouble(args.HiddenSize);
args.NumModes = convertToDouble(args.NumModes);
args.Name = char(args.Name);
end

function iValidateNumModes(sz)
nnet.internal.cnn.layer.paramvalidation.validateSizeParameter(sz, 'NumModes', 1);
end

function iValidateHiddenSize(sz)
nnet.internal.cnn.layer.paramvalidation.validateSizeParameter(sz, 'HiddenSize', 1)
end

function iAssertValidFactor(value)
nnet.internal.cnn.layer.paramvalidation.validateLearnFactor(value);
end

Matt J 2026-6-26，15:14

I want to know the internal computation details

Like what? The documentation tells you it's an FFT-based convolution. What else is there to know?

Chuguang Pan 2026-6-27，2:12

@Matt J. I have find that the Solve PDE Using Fourier Neural Operator example gives the customized implementation of spectralConvolution1dLayer. The predict method presents the specific calculation process using fft and ifft. Thanks for your answer.

请先登录，再进行评论。

How is the spectralConvolution1dLayer forward computation process performed

0 个评论
显示 -2更早的评论隐藏 -2更早的评论

回答（1 个）

3 个评论
显示 1更早的评论隐藏 1更早的评论

类别

产品

版本

标签

Community Treasure Hunt

How is the spectralCo​nvolution1​dLayer forward computation process performed

0 个评论 显示 -2更早的评论 隐藏 -2更早的评论

回答（1 个）

3 个评论 显示 1更早的评论 隐藏 1更早的评论

类别

产品

版本

标签

另请参阅

Community Treasure Hunt

How is the spectralConvolution1dLayer forward computation process performed

0 个评论
显示 -2更早的评论隐藏 -2更早的评论

3 个评论
显示 1更早的评论隐藏 1更早的评论