We will further try to simplify the paper in general.

In this subsection, we derive the necessary and sufficient condition in proposition??. Denote B,K be some natural numbers. We introduce the proposition from [8] that proves geometrical convergence of positive concave mapping. Bycorollary 2, g(v(n);Q) is a concave mapping. Wedonotapplyweightdecayanduse cosine scheduled the learning rate.

We present an approach for lifelong/continual learning of convolutional neural networks (CNN) that does not suffer from the problem of catastrophic forgetting when moving from onetask totheother. Weshowthat theactivation maps generated by the CNN trained on the old task can be calibrated using very few calibration parameters, to become relevant to the new task.

We evaluate the identified RSTs' robustness against more attacks on top of two networks on CIFAR-10 as a complement for Sec. As observed from Tab. 1, we can see that the RSTs searched by PGD-7 training are also robust against other attacks. As observed in Figure 1, RSTs drawn from randomly initialized networks achieve a comparable natural accuracy with the RTTs drawn from naturally/adversarially trained networks and adversarial RTTs generally achieve the best natural accuracy. Trained), (2) adversarially trained dense models (Dense Adv. Trained 70.70 74.35 77.20 77.71 75.55 79.22 78.85 77.33 0 81.28 Dense Adv.