Picture for Decebal Mocanu

Decebal Mocanu

More ConvNets in the 2020s: Scaling up Kernels Beyond 51x51 using Sparsity

Add code
Jul 07, 2022
Figure 1 for More ConvNets in the 2020s: Scaling up Kernels Beyond 51x51 using Sparsity
Figure 2 for More ConvNets in the 2020s: Scaling up Kernels Beyond 51x51 using Sparsity
Figure 3 for More ConvNets in the 2020s: Scaling up Kernels Beyond 51x51 using Sparsity
Figure 4 for More ConvNets in the 2020s: Scaling up Kernels Beyond 51x51 using Sparsity
Viaarxiv icon

Softmax-based Classification is k-means Clustering: Formal Proof, Consequences for Adversarial Attacks, and Improvement through Centroid Based Tailoring

Add code
Jan 07, 2020
Figure 1 for Softmax-based Classification is k-means Clustering: Formal Proof, Consequences for Adversarial Attacks, and Improvement through Centroid Based Tailoring
Figure 2 for Softmax-based Classification is k-means Clustering: Formal Proof, Consequences for Adversarial Attacks, and Improvement through Centroid Based Tailoring
Figure 3 for Softmax-based Classification is k-means Clustering: Formal Proof, Consequences for Adversarial Attacks, and Improvement through Centroid Based Tailoring
Figure 4 for Softmax-based Classification is k-means Clustering: Formal Proof, Consequences for Adversarial Attacks, and Improvement through Centroid Based Tailoring
Viaarxiv icon