First provide a summary of the paper, and then address the following criteria: Quality, clarity, originality and significance. Dropout in deep neural networks is perturbing the output layer after non-linear mapping. Later it has been shown that this is closely related to perturbing the weight matrix before non-linear mapping due to the choice of mapping functions in neural networks (known as DropConnect). In a way, both Dropout and DropConnect perturb the decision boundary (ie parameter) after training, which is different from (though might be related to) perturbing the input feature vectors before training. This paper provides generalization bounds for training with perturbed features, which is more closely related to learning by feature deletion [13] or learning with corrupted features [9].

Neural Information Processing Systems http://nips.cc/

We would like to thank all the reviewers for their insightful and constructive feedback. This model can get comparable win rate to the RNN-Discriminative in Table3. Finally, we appreciate the reviewers for suggesting additional citations and interesting future directions. Natural language has several advantages over latent programs. Secondly, gathering supervision for natural language actions is possible with the framework we introduce.

We study the effect of adversarial perturbations on the task of monocular depth prediction. Specifically, we explore the ability of small, imperceptible additive perturbations to selectively alter the perceived geometry of the scene.

In this paper, we demonstrate that theoretically there is no limitation to using low-dimensional embedding-based methods, and provide experimental evidence that overfitting is the root cause of the poor performance of embedding-based methods.

Graph convolution networks (GCNs) have become effective models for graph classification. Similar to many deep networks, GCNs are vulnerable to adversarial attacks on graph topology and node attributes. Recently, a number of effective attack and defense algorithms have been designed, but no certificate of robustness has been developed for GCN-based graph classification under topological perturbations with both local and global budgets. In this paper, we propose the first certificate for this problem. Our method is based on Lagrange dualization and convex envelope, which result in tight approximation bounds that are efficiently computable by dynamic programming. When used in conjunction with robust training, it allows an increased number of graphs to be certified as robust.

CORnet-S, a shallow ANN with four anatomically mapped areas and recurrent connectivity, guided by Brain-Score, a new large-scale composite of neural and behavioral benchmarks for quantifying the functional fidelity of models of the primate ventral visual stream. Despite being significantly shallower than most models, CORnet-S is the top model on Brain-Score and outperforms similarly compact models on ImageNet.

Neural Information Processing Systems http://nips.cc/

Neural Information Processing Systems http://nips.cc/