# Does it make sense to run lasso to select features for neural network training?

I want to train a neural network for regression. $$\Bbb R^{2800} \rightarrow \Bbb R^{1}$$ The dimension of feature vectors is $$2800$$. The figure is an illustration of one of the feature vectors.

Since the dimension of the feature vectors is relatively large, and there might be redundancies, I want to do an automatic feature selection to decrease the dimension.

Does it make sense to do lasso regression for selecting features? My concern is lasso regression is a linear regression method, however, a neural network can be trained to approximate non-linear relationships.

If lasso regression is not legitimate for selecting features for neural network training, how can I reduce the dimensionality of the feature vectors?