175 citations · 362 across the 9 of their papers we have counts for
9 papers
Weakly-supervised multi-class object localization using only object counts as labels
Kyle Mills, Isaac Tamblyn
We demonstrate the use of an extensive deep neural network to localize instances of objects in images. The EDNN is naturally able to accurately perform multi-class counting using o…
Controlled Online Optimization Learning (COOL): Finding the ground state of spin Hamiltonians with reinforcement learning
Kyle Mills, Pooya Ronagh, Isaac Tamblyn
Reinforcement learning (RL) has become a proven method for optimizing a procedure for which success has been defined, but the specific actions needed to achieve it have not. We app…
Optical lattice experiments at unobserved conditions and scales through generative adversarial deep learning
Corneel Casert, Kyle Mills, Tom Vieijra +2
Machine learning provides a novel avenue for the study of experimental realizations of many-body systems, and has recently been proven successful in analyzing properties of experim…
Optimizing thermodynamic trajectories using evolutionary and gradient-based reinforcement learning
Chris Beeler, Uladzimir Yahorau, Rory Coles +3
Using a model heat engine, we show that neural network-based reinforcement learning can identify thermodynamic trajectories of maximal efficiency. We consider both gradient and gra…
Phase space sampling and operator confidence with generative adversarial networks
Kyle Mills, Isaac Tamblyn
We demonstrate that a generative adversarial network can be trained to produce Ising model configurations in distinct regions of phase space. In training a generative adversarial n…
Extensive deep neural networks for transferring small scale learning to large scale systems
Kyle Mills, Kevin Ryczko, Iryna Luchak +3
We present a physically-motivated topology of a deep neural network that can efficiently infer extensive parameters (such as energy, entropy, or number of particles) of arbitrarily…