Search Results for author: Barak A. Pearlmutter

Found 14 papers, 4 papers with code

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

no code implementations30 Oct 2021 Mansura Habiba, Barak A. Pearlmutter

In a typical case, where the ``wormhole'' connections are inactive, this is inexpensive; but when they are active, the network takes a longer time to settle down, and the gradient calculation is also more laborious, with an effect similar to making the network deeper.

ECG synthesis with Neural ODE and GAN models

no code implementations30 Oct 2021 Mansura Habiba, Eoin Borphy, Barak A. Pearlmutter, Tomas Ward

Continuous medical time series data such as ECG is one of the most complex time series due to its dynamic and high dimensional characteristics.

Time Series

Continuous Convolutional Neural Networks: Coupled Neural PDE and ODE

no code implementations30 Oct 2021 Mansura Habiba, Barak A. Pearlmutter

Recent work in deep learning focuses on solving physical systems in the Ordinary Differential Equation or Partial Differential Equation.

Time Series

HeunNet: Extending ResNet using Heun's Methods

1 code implementation13 May 2021 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.

Neural ODEs for Informative Missingness in Multivariate Time Series

no code implementations20 May 2020 Mansura Habiba, Barak A. Pearlmutter

Practical applications, e. g., sensor data, healthcare, weather, generates data that is in truth continuous in time, and informative missingness is a common phenomenon in these datasets.

Imputation Time Series +2

Neural Ordinary Differential Equation based Recurrent Neural Network Model

no code implementations20 May 2020 Mansura Habiba, Barak A. Pearlmutter

(ii)~can Neural ODEs solve the irregular sampling rate challenge of existing neural network models for a continuous time series, i. e., length and dynamic nature, (iii)~how to reduce the training and evaluation time of existing Neural ODE systems?

Time Series

Concurrent Robin Hood Hashing

2 code implementations12 Sep 2018 Robert Kelly, Barak A. Pearlmutter, Phil Maguire

In this paper we examine the issues involved in adding concurrency to the Robin Hood hash table algorithm.

Distributed, Parallel, and Cluster Computing

DiffSharp: An AD Library for .NET Languages

no code implementations10 Nov 2016 Atılım Güneş Baydin, Barak A. Pearlmutter, Jeffrey Mark Siskind

DiffSharp is an algorithmic differentiation or automatic differentiation (AD) library for the . NET ecosystem, which is targeted by the C# and F# languages, among others.

Tricks from Deep Learning

no code implementations10 Nov 2016 Atılım Güneş Baydin, Barak A. Pearlmutter, Jeffrey Mark Siskind

The deep learning community has devised a diverse set of methods to make gradient optimization, using large datasets, of large and highly complex models with deeply cascaded nonlinearities, practical.

Machine Translation Speech Recognition

Binomial Checkpointing for Arbitrary Programs with No User Annotation

no code implementations10 Nov 2016 Jeffrey Mark Siskind, Barak A. Pearlmutter

Heretofore, automatic checkpointing at procedure-call boundaries, to reduce the space complexity of reverse mode, has been provided by systems like Tapenade.

Automatic differentiation in machine learning: a survey

3 code implementations20 Feb 2015 Atilim Gunes Baydin, Barak A. Pearlmutter, Alexey Andreyevich Radul, Jeffrey Mark Siskind

Derivatives, mostly in the form of gradients and Hessians, are ubiquitous in machine learning.

Automatic Differentiation of Algorithms for Machine Learning

no code implementations28 Apr 2014 Atilim Gunes Baydin, Barak A. Pearlmutter

Automatic differentiation---the mechanical transformation of numeric computer programs to calculate derivatives efficiently and accurately---dates to the origin of the computer age.

Block Coordinate Descent for Sparse NMF

1 code implementation15 Jan 2013 Vamsi K. Potluru, Sergey M. Plis, Jonathan Le Roux, Barak A. Pearlmutter, Vince D. Calhoun, Thomas P. Hayes

However, present algorithms designed for optimizing the mixed norm L$_1$/L$_2$ are slow and other formulations for sparse NMF have been proposed such as those based on L$_1$ and L$_0$ norms.

Confusion of Tagged Perturbations in Forward Automatic Differentiation of Higher-Order Functions

no code implementations20 Nov 2012 Oleksandr Manzyuk, Barak A. Pearlmutter, Alexey Andreyevich Radul, David R. Rush, Jeffrey Mark Siskind

The essence of Forward AD is to attach perturbations to each number, and propagate these through the computation.

Symbolic Computation Mathematical Software Differential Geometry

Cannot find the paper you are looking for? You can Submit a new open access paper.