• Publications
  • Influence
Supervised Learning with Tensor Networks
TLDR
It is demonstrated how algorithms for optimizing tensor networks can be adapted to supervised learning tasks by using matrix product states (tensor trains) to parameterize non-linear kernel learning models.
An exact mapping between the Variational Renormalization Group and Deep Learning
TLDR
This work constructs an exact mapping from the variational renormalization group, first introduced by Kadanoff, and deep learning architectures based on Restricted Boltzmann Machines (RBMs), and suggests that deep learning algorithms may be employing a generalized RG-like scheme to learn relevant features from data.
Modeling circulation and thermal structure in Lake Michigan: Annual cycle and interannual variability
A three-dimensional primitive equation numerical model was applied to Lake Michigan for the periods 1982–1983 and 1994–1995 to study seasonal and interannual variability of lake-wide circulation and
Transport and Mixing Between the Coastal and Offshore Waters in the Great Lakes: a Review
ABSTRACT The Laurentian Great Lakes of North America have horizontal scales of hundreds of kilometers and depth scales of hundreds of meters. In terms of coastal dynamics, they behave much like
The Deterministic Information Bottleneck
TLDR
This work introduces an alternative formulation of the information bottleneck method that replaces mutual information with entropy, which it is argued better captures this notion of compression and empirically finds that the DIB offers a considerable gain in computational efficiency over the IB, over a range of convergence parameters.
Modeling the transport and inactivation of E. coli and enterococci in the near-shore region of Lake Michigan.
TLDR
Sunlight is a major contributor to inactivation in the surf-zone and the formulation based on sunlight, temperature and sedimentation is preferred over the first-order inactivation formulation, while Enterococci appear to survive longer than E. coli.
Supervised Learning with Quantum-Inspired Tensor Networks
TLDR
It is demonstrated how algorithms for optimizing such networks can be adapted to supervised learning tasks by using matrix product states (tensor trains) to parameterize models for classifying images.
...
1
2
3
4
5
...