36 citations · 156 across the 39 of their papers we have counts for
9 papers · 1 filter
BarrierNet: A Safety-Guaranteed Layer for Neural Networks
Wei Xiao, Ramin Hasani, Xiao Li +1
This paper introduces differentiable higher-order control barrier functions (CBF) that are end-to-end trainable together with learning systems. CBFs are usually overly conservative…
Interactive Analysis of CNN Robustness
Stefan Sietzen, Mathias Lechner, Judy Borowski +2
While convolutional neural networks (CNNs) have found wide adoption as state-of-the-art models for image-related tasks, their predictions are often highly sensitive to small input…
GoTube: Scalable Stochastic Verification of Continuous-Depth Models
Sophie Gruenbacher, Mathias Lechner, Ramin Hasani +4
We introduce a new stochastic verification algorithm that formally quantifies the behavioral robustness of any time-continuous process formulated as a continuous-depth model. Our a…
On-Off Center-Surround Receptive Fields for Accurate and Robust Image Classification
Zahra Babaiee, Ramin Hasani, Mathias Lechner +2
Robustness to variations in lighting conditions is a key objective for any deep vision system. To this end, our paper extends the receptive field of convolutional neural networks w…
Closed-form Continuous-time Neural Models
Ramin Hasani, Mathias Lechner, Alexander Amini +5
Continuous-time neural processes are performant sequential decision-makers that are built by differential equations (DE). However, their expressive power when they are deployed on…
Sparse Flows: Pruning Continuous-depth Models
Lucas Liebenwein, Ramin Hasani, Alexander Amini +1
Continuous deep learning architectures enable learning of flexible probabilistic models for predictive modeling as neural ordinary differential equations (ODEs), and for generative…