Timezone: »

 
Lunch break & Poster session
Breandan Considine · Michael Innes · Du Phan · Dougal Maclaurin · Robin Manhaeve · Alexey Radul · Shashi Gowda · Ekansh Sharma · Eli Sennesh · Maxim Kochurov · Gordon Plotkin · Thomas Wiecki · Navjot Kukreja · Chung-chieh Shan · Matthew Johnson · Dan Belov · Neeraj Pradhan · Wannes Meert · Angelika Kimmig · Luc De Raedt · Brian Patton · Matthew Hoffman · Rif A. Saurous · Daniel Roy · Eli Bingham · Martin Jankowiak · Colin Carroll · Junpeng Lao · Liam Paull · Martin Abadi · Angel Rojas Jimenez · JP Chen

Sat Dec 14 12:00 PM -- 02:00 PM (PST) @
in Program Transformations for ML »

Author Information

Breandan Considine (McGill University)
Michael Innes (Julia Computing)
Du Phan (Independent Researcher)
Dougal Maclaurin (Google)
Robin Manhaeve (KU Leuven)
Alexey Radul (Google)
Shashi Gowda (Massachusetts Institute of Technology)
Ekansh Sharma (University of Toronto)
Eli Sennesh (Northeastern University)

I work in the Probabilistic Modeling Lab at Northeastern University’s CCIS, as well as the Interdisciplinary Affective Science Laboratory. We use the tools of machine learning, statistics, and computation to study the deep questions at the heart of neuroscience, cognition, and agency. We’re making the world a better place through probabilistic programming!

Maxim Kochurov (Samsung)
Gordon Plotkin (Google)
Thomas Wiecki (Quantopian Inc.)
Navjot Kukreja (Imperial College London)
Chung-chieh Shan (Indiana University)
Matthew Johnson (Google Brain)

Matt Johnson is a research scientist at Google Brain interested in software systems powering machine learning research. He is the tech lead for JAX, a system for composable function transformations in Python. He was a postdoc at Harvard University with Ryan Adams, working on composing graphical models with neural networks and applications in neurobiology. His Ph.D. is from MIT, where he worked with Alan Willsky on Bayesian nonparametrics, time series models, and scalable inference.

Dan Belov (DeepMind)
Neeraj Pradhan (Uber AI Labs)
Wannes Meert (K.U.Leuven)
Angelika Kimmig (Cardiff University)
Luc De Raedt (KU Leuven)
Brian Patton (Google)
Matthew Hoffman (Google)
Rif A. Saurous (Google)
Daniel Roy (Univ of Toronto & Vector)
Eli Bingham (Uber AI Labs)
Martin Jankowiak (Uber AI Labs)
Colin Carroll (PyMC3)

Colin Carroll is a data scientist in Cambridge, MA interested in statistical computing, particularly as related to Bayesian methods. He is a core contributor to PyMC3, a Python library for Bayesian modelling and inference, as well as ArviZ, a Bayesian visualization and diagnostic library. He received his PhD in mathematics from Rice University, where he researched geometric measure theory.

Junpeng Lao (Google)
Liam Paull (Université de Montréal)
Martin Abadi (Google)
Angel Rojas Jimenez (Yachay Tech)

I obtained my B.Sc. in Mathematics at Yachay Tech in Imbabura, Ecuador. In the last semester of my undergraduate career prof. Griewank and I developed SALGO - Successive Abs-Linearized Global Optimization algorithm and its application to Neural Network (NN) training. Nowadays, we obtain three different optimization strategies for SALGO called TOAST, MILOP, and CGD. Also, we obtained a 92% accuracy for the MNIST digit recognition problem implementing SALGO-TOAST for a single-layer NN. Moreover, we have generalized the prediction model of a NN with hinge (or ReLU) activation functions with what we call GALL - Generalized Abs-Linear Learning.

JP Chen (Uber AI)

More from the Same Authors