Search Results for author:
Found 10 papers, 7 papers with code
Nature's Cost Function: Simulating Physics by Minimizing the Action
In physics, there is a scalar function called the action which behaves like a cost function.
Dissipative Hamiltonian Neural Networks: Learning Dissipative and Conservative Dynamics Separately
Recent work has shown that neural networks can learn such symmetries directly from data using Hamiltonian Neural Networks (HNNs).
Piecewise-constant Neural ODEs
Neural networks are a popular tool for modeling sequential data but they generally do not treat time as a continuous variable.
Scaling down Deep Learning
Though deep learning models have taken on commercial and political relevance, many aspects of their training and operation remain poorly understood.
Lagrangian Neural Networks
Accurate models of the world are built upon notions of its underlying symmetries.
Neural reparameterization improves structural optimization
Structural optimization is a popular method for designing objects such as bridge trusses, airplane wings, and optical devices.
Hamiltonian Neural Networks
Even though neural networks enjoy widespread use, they still struggle to learn the basic laws of physics.
Learning Finite State Representations of Recurrent Policy Networks
Recurrent neural networks (RNNs) are an effective representation of control policies for a wide range of reinforcement and imitation learning problems.
Visualizing and Understanding Atari Agents
While deep reinforcement learning (deep RL) agents are effective at maximizing rewards, it is often unclear what strategies they use to do so.
Learning the Enigma with Recurrent Neural Networks
We demonstrate that RNNs can learn decryption algorithms -- the mappings from plaintext to ciphertext -- for three polyalphabetic ciphers (Vigen\`ere, Autokey, and Enigma).
