We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. The repositories linked to it are listed below.
Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.
We describe the class of convexified convolutional neural networks (CCNNs), which capture the parameter sharing of convolutional neural networks in a convex manner. By representing the nonlinear convolutional filters as vectors in a reproducing kernel Hilbert space, the CNN parameters can be represented as a low-rank matrix, which can be relaxed to obtain a convex optimization problem. For learning two-layer convolutional neural networks, we prove that the generalization error obtained by a convexified CNN converges to that of the best possible CNN. For learning deeper networks, we train CCNNs in a layer-wise manner. Empirically, CCNNs achieve performance competitive with CNNs trained by backpropagation, SVMs, fully-connected neural networks, stacked denoising auto-encoders, and other baseline methods.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("1609.01000")
get_code_for_paper("1609.01000")
have("1609.01000")
The run record, dated, one paper per request, free:
curl https://syntology.ai/api/ran/1609.01000.json
A badge for a README (the split and the date, never a ratio):
[](https://syntology.ai/paper/1609.01000)
Connect an agent — have() is free.