TY - GEN
T1 - Deep Convolutional Networks as shallow Gaussian Processes
AU - Garriga-Alonso, Adria
AU - Rasmussen, Carl E.
AU - Aitchison, Laurence
PY - 2019/5/6
Y1 - 2019/5/6
N2 - We show that the output of a (residual) CNN with an appropriate prior over the weights and biases is a GP in the limit of infinitely many convolutional filters, extending similar results for dense networks. For a CNN, the equivalent kernel can be computed exactly and, unlike "deep kernels", has very few parameters: only the hyperparameters of the original CNN. Further, we show that this kernel has two properties that allow it to be computed efficiently; the cost of evaluating the kernel for a pair of images is similar to a single forward pass through the original CNN with only one filter per layer. The kernel equivalent to a 32-layer ResNet obtains 0.84% classification error on MNIST, a new record for GP with a comparable number of parameters.
AB - We show that the output of a (residual) CNN with an appropriate prior over the weights and biases is a GP in the limit of infinitely many convolutional filters, extending similar results for dense networks. For a CNN, the equivalent kernel can be computed exactly and, unlike "deep kernels", has very few parameters: only the hyperparameters of the original CNN. Further, we show that this kernel has two properties that allow it to be computed efficiently; the cost of evaluating the kernel for a pair of images is similar to a single forward pass through the original CNN with only one filter per layer. The kernel equivalent to a 32-layer ResNet obtains 0.84% classification error on MNIST, a new record for GP with a comparable number of parameters.
M3 - Conference Contribution (Conference Proceeding)
T3 - ICLR
SP - 1
EP - 16
BT - International Conference on Learning Representations
ER -
