Deep Learning has enabled remarkable progress over the last years on a variety of tasks, such as image recognition, speech recognition, and machine translation. One crucial aspect for this progress are novel neural architectures. Currently employed architectures have mostly been developed manually by human experts, which is a time-consuming and error-prone process. Because of this, there is growing interest in automated neural architecture search methods. We provide an overview of existing work in this field of research and categorize them according to three dimensions: search space, search strategy, and performance estimation strategy.

While deep learning is remarkably successful on perceptual tasks, it was also shown to be vulnerable to adversarial perturbations of the input. These perturbations denote noise added to the input that was generated specifically to fool the system while being quasi-imperceptible for humans. More severely, there even exist universal perturbations that are input-agnostic but fool the network on the majority of inputs. While recent work has focused on image classification, this work proposes attacks against semantic image segmentation: we present an approach for generating (universal) adversarial perturbations that make the network yield a desired target segmentation as output. We show empirically that there exist barely perceptible universal noise patterns which result in nearly the same predicted segmentation for arbitrary inputs. Furthermore, we also show the existence of universal noise which removes a target class (e.g., all pedestrians) from the segmentation while leaving the segmentation mostly unchanged otherwise.

ML is an expanding field. It is popular as it allows efficient processing of vast amounts of data for interpreting and real-time decision making. Already widely used in imaging and diagnosis, it is believed that ML will also play an important role in surgery and interventional treatments. In particular, ML could become a game changer into the conception of cognitive surgical robots. Such robots endowed with cognitive skills would assist the surgical team also on a cognitive level, such as possibly lowering the mental load of the team. For example, ML could help extracting surgical skill, learned through demonstration by human experts, and could transfer this to robotic skills. Such intelligent surgical assistance would significantly surpass the state of the art in surgical robotics. Current devices possess no intelligence whatsoever and are merely advanced and expensive instruments.

Neural Architecture Search aims at automatically finding neural network architectures that are competitive with architectures designed by human experts. While recent approaches have achieved state-of-the-art predictive performance for, e.g., image recognition, they are problematic under resource constraints for two reasons:(1) the neural architectures found are solely optimized for high predictive performance, without penalizing excessive resource consumption; (2) most architecture search methods require vast computational resources. We address the first shortcoming by proposing LEMONADE, an evolutionary algorithm for multi-objective architecture search that allows approximating the entire Pareto front of architectures under multiple objectives, such as predictive performance and number of parameters, in a single run of the method. We address the second shortcoming by proposing a Lamarckian inheritance mechanism for LEMONADE which generates child networks that are warm started with the predictive performance of their trained parents. This is accomplished by using (approximate) network morphism operators for generating children. The combination of these two contributions allows finding models that are on par or even outperform both hand-crafted as well as automatically-designed networks.

No abstract