Alex Beatson
YOU?
Author Swipe
View article: Machine Learning for Toxicity Prediction Using Chemical Structures: Pillars for Success in the Real World
Machine Learning for Toxicity Prediction Using Chemical Structures: Pillars for Success in the Real World Open
Machine learning (ML) is increasingly valuable for predicting molecular properties and toxicity in drug discovery. However, toxicity-related end points have always been challenging to evaluate experimentally with respect to in vivo transla…
View article: Meta-PDE: Learning to Solve PDEs Quickly Without a Mesh
Meta-PDE: Learning to Solve PDEs Quickly Without a Mesh Open
Partial differential equations (PDEs) are often computationally challenging to solve, and in many settings many related PDEs must be be solved either at every timestep or for a variety of candidate boundary conditions, parameters, or geome…
View article: Randomized Automatic Differentiation
Randomized Automatic Differentiation Open
The successes of deep learning, variational inference, and many other fields have been aided by specialized implementations of reverse-mode automatic differentiation (AD) to compute gradients of mega-dimensional objectives. The AD techniqu…
View article: Learning Composable Energy Surrogates for PDE Order Reduction
Learning Composable Energy Surrogates for PDE Order Reduction Open
Meta-materials are an important emerging class of engineered materials in which complex macroscopic behaviour--whether electromagnetic, thermal, or mechanical--arises from modular substructure. Simulation and optimization of these material…
View article: SUMO: Unbiased Estimation of Log Marginal Probability for Latent\n Variable Models
SUMO: Unbiased Estimation of Log Marginal Probability for Latent\n Variable Models Open
Standard variational lower bounds used to train latent variable models\nproduce biased estimates of most quantities of interest. We introduce an\nunbiased estimator of the log marginal likelihood and its gradients for latent\nvariable mode…
View article: SUMO: Unbiased Estimation of Log Marginal Probability for Latent Variable Models
SUMO: Unbiased Estimation of Log Marginal Probability for Latent Variable Models Open
Standard variational lower bounds used to train latent variable models produce biased estimates of most quantities of interest. We introduce an unbiased estimator of the log marginal likelihood and its gradients for latent variable models …
View article: A data-driven computational scheme for the nonlinear mechanical properties of cellular mechanical metamaterials under large deformation
A data-driven computational scheme for the nonlinear mechanical properties of cellular mechanical metamaterials under large deformation Open
A novel computational scheme using neural networks is proposed to efficiently capture the nonlinear mechanics of soft metamaterials under large deformation.
View article: Efficient Optimization of Loops and Limits with Randomized Telescoping Sums
Efficient Optimization of Loops and Limits with Randomized Telescoping Sums Open
We consider optimization problems in which the objective requires an inner loop with many steps or is the limit of a sequence of increasingly costly approximations. Meta-learning, training recurrent neural networks, and optimization of the…
View article: Efficient Optimization of Loops and Limits with Randomized Telescoping\n Sums
Efficient Optimization of Loops and Limits with Randomized Telescoping\n Sums Open
We consider optimization problems in which the objective requires an inner\nloop with many steps or is the limit of a sequence of increasingly costly\napproximations. Meta-learning, training recurrent neural networks, and\noptimization of …
View article: Continual Learning in Generative Adversarial Nets
Continual Learning in Generative Adversarial Nets Open
Developments in deep generative models have allowed for tractable learning of high-dimensional data distributions. While the employed learning procedures typically assume that training data is drawn i.i.d. from the distribution of interest…
View article: Assessing Respiratory Mechanics of Reverse-Triggered Breathing Cycles - Case Study of Two Mechanically Ventilated Patients
Assessing Respiratory Mechanics of Reverse-Triggered Breathing Cycles - Case Study of Two Mechanically Ventilated Patients Open
Mechanical ventilation patients may breathe spontaneously during ventilator supported breaths, altering airway pressure waveforms and hindering identification of true, underlying respiratory mechanics. This study aims to assess and identif…