2 citations · 2 across the 1 of their papers we have counts for
8 papers
Adversarial Training is Not Ready for Robot Learning
Mathias Lechner, Ramin Hasani, Radu Grosu +2
Adversarial training is an effective method to train deep learning models that are resilient to norm-bounded perturbations, with the cost of nominal performance drop. While adversa…
Liquid Time-constant Networks
Ramin Hasani, Mathias Lechner, Alexander Amini +2
We introduce a new class of time-continuous recurrent neural network models. Instead of declaring a learning system's dynamics by implicit nonlinearities, we construct networks of…
Learning Long-Term Dependencies in Irregularly-Sampled Time Series
Mathias Lechner, Ramin Hasani
Recurrent neural networks (RNNs) with continuous-time hidden states are a natural fit for modeling irregularly-sampled time series. These models, however, face difficulties when th…
Liquid Time-constant Recurrent Neural Networks as Universal Approximators
Ramin M. Hasani, Mathias Lechner, Alexander Amini +2
In this paper, we introduce the notion of liquid time-constant (LTC) recurrent neural networks (RNN)s, a subclass of continuous-time RNNs, with varying neuronal time-constant reali…
Response Characterization for Auditing Cell Dynamics in Long Short-term Memory Networks
Ramin M. Hasani, Alexander Amini, Mathias Lechner +3
In this paper, we introduce a novel method to interpret recurrent neural networks (RNNs), particularly long short-term memory networks (LSTMs) at the cellular level. We propose a s…
Can a Compact Neuronal Circuit Policy be Re-purposed to Learn Simple Robotic Control?
Ramin Hasani, Mathias Lechner, Alexander Amini +2
We propose a neural information processing system which is obtained by re-purposing the function of a biological neural circuit model, to govern simulated and real-world control ta…