activity
20052024
most citedAutomatic Differentiation of Algorithms for Machine Learning

24 citations · 64 across the 15 of their papers we have counts for

collaborators
Showing cs.LGShow all

10 papers · 1 filter

cs.LG2024

Low-Rank Learning by Design: the Role of Network Architecture and Activation Linearity in Gradient Rank Collapse

Bradley T. Baker, Barak A. Pearlmutter, Robyn Miller +2

Our understanding of learning dynamics of deep neural networks (DNNs) remains incomplete. Recent research has begun to uncover the mathematical principles underlying these networks…

cs.LG202220 cited

Gradients without Backpropagation

Atılım Güneş Baydin, Barak A. Pearlmutter, Don Syme +2

Using backpropagation to compute gradients of objective functions for optimization has remained a mainstay of machine learning. Backpropagation, or reverse-mode differentiation, is…

cs.LG2021

Continuous Convolutional Neural Networks: Coupled Neural PDE and ODE

Mansura Habiba, Barak A. Pearlmutter

Recent work in deep learning focuses on solving physical systems in the Ordinary Differential Equation or Partial Differential Equation. This current work proposed a variant of Con…

cs.LG2021

Neural Network based on Automatic Differentiation Transformation of Numeric Iterate-to-Fixedpoint

Mansura Habiba, Barak A. Pearlmutter

This work proposes a Neural Network model that can control its depth using an iterate-to-fixed-point operator. The architecture starts with a standard layered Network but with adde…

cs.LG2021

HeunNet: Extending ResNet using Heun's Methods

Mehrdad Maleki, Mansura Habiba, Barak A. Pearlmutter

There is an analogy between the ResNet (Residual Network) architecture for deep neural networks and an Euler solver for an ODE. The transformation performed by each layer resembles…

cs.LG20203 cited

Neural ODEs for Informative Missingness in Multivariate Time Series

Mansura Habiba, Barak A. Pearlmutter

Informative missingness is unavoidable in the digital processing of continuous time series, where the value for one or more observations at different time points are missing. Such…