activity
20172021
most citedWorm-level Control through Search-based Reinforcement Learning

2 citations · 2 across the 1 of their papers we have counts for

collaborators

8 papers

cs.LG2021

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…

cs.LG2020

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…

cs.LG2020

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…

cs.LG2018

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…

cs.LG2018

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…

cs.LG2018

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…