Lennart Schulze

Patrick Odagiu, Vasilis Belis, Lennart Schulze et al.

Data sets that are specified by a large number of features are currently outside the area of applicability for quantum machine learning algorithms. An immediate solution to this impasse is the application of dimensionality reduction methods before passing the data to the quantum algorithm. We investigate six conventional feature extraction algorithms and five autoencoder-based dimensionality reduction models to a particle physics data set with 67 features. The reduced representations generated by these models are then used to train a quantum support vector machine for solving a binary classification problem: whether a Higgs boson is produced in proton collisions at the LHC. We show that the autoencoder methods learn a better lower-dimensional representation of the data, with the method we design, the Sinkclass autoencoder, performing 40% better than the baseline. The methods developed here open up the applicability of quantum machine learning to a larger array of data sets. Moreover, we provide a recipe for effective dimensionality reduction in this context.

Lennart Schulze, Hod Lipson

A robot self-model is a task-agnostic representation of the robot's physical morphology that can be used for motion planning tasks in the absence of a classical geometric kinematic model. In particular, when the latter is hard to engineer or the robot's kinematics change unexpectedly, human-free self-modeling is a necessary feature of truly autonomous agents. In this work, we leverage neural fields to allow a robot to self-model its kinematics as a neural-implicit query model learned only from 2D images annotated with camera poses and configurations. This enables significantly greater applicability than existing approaches which have been dependent on depth images or geometry knowledge. To this end, alongside a curricular data sampling strategy, we propose a new encoder-based neural density field architecture for dynamic object-centric scenes conditioned on high numbers of degrees of freedom (DOFs). In a 7-DOF robot test setup, the learned self-model achieves a Chamfer-L2 distance of 2% of the robot's workspace dimension. We demonstrate the capabilities of this model on motion planning tasks as an exemplary downstream application.

Stephen Casper, Lennart Schulze, Oam Patel et al.

Despite extensive diagnostics and debugging by developers, AI systems sometimes exhibit harmful unintended behaviors. Finding and fixing these is challenging because the attack surface is so large -- it is not tractable to exhaustively search for inputs that may elicit harmful behaviors. Red-teaming and adversarial training (AT) are commonly used to improve robustness, however, they empirically struggle to fix failure modes that differ from the attacks used during training. In this work, we utilize latent adversarial training (LAT) to defend against vulnerabilities without leveraging knowledge of what they are or using inputs that elicit them. LAT makes use of the compressed, abstract, and structured latent representations of concepts that the network actually uses for prediction. Here, we use it to defend against failure modes without examples that elicit them. Specifically, we use LAT to remove backdoors and defend against held-out classes of adversarial attacks. We show in image classification, text classification, and text generation tasks that LAT usually improves both robustness to novel attacks and performance on clean data relative to AT. This suggests that LAT can be a promising tool for defending against failure modes that are not explicitly identified by developers.