
Equivariant Maps for Hierarchical Structures
In many realworld settings, we are interested in learning invariant and...
read it

Universal Equivariant Multilayer Perceptrons
Group invariant and equivariant Multilayer Perceptrons (MLP), also known...
read it

Incidence Networks for Geometric Deep Learning
One may represent a graph using both its nodeedge and its nodenode inc...
read it

Deep Models for Relational Databases
Due to its extensive use in databases, the relational model is ubiquitou...
read it

Improved Knowledge Graph Embedding using Background Taxonomic Information
Knowledge graphs are used to represent relational information in terms o...
read it

Learning to Predict the Cosmological Structure Formation
Matter evolved under influence of gravity from minuscule density fluctua...
read it

Subject2Vec: GenerativeDiscriminative Approach from a Set of Image Patches to a Vector
We propose an attentionbased method that aggregates local image feature...
read it

Deep Models of Interactions Across Sets
We use deep learning to model interactions across two or more sets of ob...
read it

Estimating Cosmological Parameters from the Dark Matter Distribution
A grand challenge of the 21st century cosmology is to accurately estimat...
read it

Deep Sets
In this paper, we study the problem of designing objective functions for...
read it

Equivariance Through ParameterSharing
We propose to study equivariance in deep neural networks through paramet...
read it

Deep Learning with Sets and Point Clouds
We introduce a simple permutation equivariant layer for deep learning wi...
read it

Annealing Gaussian into ReLU: a New Sampling Strategy for LeakyReLU RBM
Restricted Boltzmann Machine (RBM) is a bipartite graphical model that i...
read it

Enabling Dark Energy Science with Deep Generative Models of Galaxy Images
Understanding the nature of dark energy, the mysterious force driving th...
read it

Stochastic Neural Networks with Monotonic Activation Functions
We propose a Laplace approximation that creates a stochastic unit from a...
read it

Boolean Matrix Factorization and Noisy Completion via Message Passing
Boolean matrix factorization and Boolean matrix completion from noisy ob...
read it

Message Passing and Combinatorial Optimization
Graphical models use the intuitive and wellstudied methods of graph the...
read it

Revisiting Algebra and Complexity of Inference in Graphical Models
This paper studies the form and complexity of inference in graphical mod...
read it

Accurate, fullyautomated NMR spectral profiling for metabolomics
Many diseases cause significant changes to the concentrations of small m...
read it

Augmentative Message Passing for Traveling Salesman Problem and Graph Partitioning
The cutting plane method is an augmentative constrained optimization pro...
read it

Training Restricted Boltzmann Machine by Perturbation
A new approach to maximum likelihood learning of discrete graphical mode...
read it

Perturbed Message Passing for Constraint Satisfaction Problems
We introduce an efficient message passing scheme for solving Constraint ...
read it

A Generalized Loop Correction Method for Approximate Inference in Graphical Models
Belief Propagation (BP) is one of the most popular methods for inference...
read it
Siamak Ravanbakhsh
is this you? claim profile
Siamak Ravanbakhsh is an assistant professor at the University of British Columbia in Vancouver. His research is in the area of machine learning.
Ravanbakhsh received his M.Sc. and his Ph.D. from the University of Alberta. While there, he was affiliated with the Alberta Ingenuity Center for Machine Learning and the Metabolomics Innovation Centre.
Prior to taking the position at UBC, Ravanbakhsh was a postdoctoral fellow at the Machine Learning Department and Robotics Institute at Carnegie Mellon University in Pittsburgh. He was affiliated with the Auton Lab and the McWilliams Center for Cosmology.
He became an assistant professor at the University of British Columbia in 2017.