Andrew Anderson

is this you? claim profile

0 followers
Trinity College Dublin ∙ Oregon State University

TASO: Time and Space Optimization for Memory-Constrained DNN Inference

Convolutional neural networks (CNNs) are used in many embedded applicati...
05/21/2020 ∙ by Yuan Wen, et al. ∙ 10 ∙ share

read it
Composition of Saliency Metrics for Channel Pruning with a Myopic Oracle

The computation and memory needed for Convolutional Neural Network (CNN)...
04/03/2020 ∙ by Kaveena Persand, et al. ∙ 0 ∙ share

read it
Performance-Oriented Neural Architecture Search

Hardware-Software Co-Design is a highly successful strategy for improvin...
01/09/2020 ∙ by Andrew Anderson, et al. ∙ 0 ∙ share

read it
A Taxonomy of Channel Pruning Signals in CNNs

Convolutional neural networks (CNNs) are widely used for classification ...
06/11/2019 ∙ by Kaveena Persand, et al. ∙ 0 ∙ share

read it
Explaining Reinforcement Learning to Mere Mortals: An Empirical Study

We present a user study to investigate the impact of explanations on non...
03/22/2019 ∙ by Andrew Anderson, et al. ∙ 0 ∙ share

read it
Scalar Arithmetic Multiple Data: Customizable Precision for Deep Neural Networks

Quantization of weights and activations in Deep Neural Networks (DNNs) i...
09/27/2018 ∙ by Andrew Anderson, et al. ∙ 0 ∙ share

read it
Error Analysis and Improving the Accuracy of Winograd Convolution for Deep Neural Networks

Modern deep neural networks (DNNs) spend a large amount of their executi...
03/29/2018 ∙ by Barbara Barabasz, et al. ∙ 0 ∙ share

read it
Improving accuracy of Winograd convolution for DNNs

Modern deep neural networks (DNNs) spend a large amount of their executi...
03/29/2018 ∙ by Barbara Barabasz, et al. ∙ 0 ∙ share

read it
Toward Foraging for Understanding of StarCraft Agents: An Empirical Study

Assessing and understanding intelligent agents is a difficult task for u...
11/21/2017 ∙ by Sean Penney, et al. ∙ 0 ∙ share

read it
How the Experts Do It: Assessing and Explaining Agent Behaviors in Real-Time Strategy Games

How should an AI-based explanation system explain an agent's complex beh...
11/19/2017 ∙ by Jonathan Dodge, et al. ∙ 0 ∙ share

read it
Optimal DNN Primitive Selection with Partitioned Boolean Quadratic Programming

Deep Neural Networks (DNNs) require very large amounts of computation bo...
10/03/2017 ∙ by Andrew Anderson, et al. ∙ 0 ∙ share

read it
Low-memory GEMM-based convolution algorithms for deep neural networks

Deep neural networks (DNNs) require very large amounts of computation bo...
09/08/2017 ∙ by Andrew Anderson, et al. ∙ 0 ∙ share

read it
Parallel Multi Channel Convolution using General Matrix Multiplication

Convolutional neural networks (CNNs) have emerged as one of the most suc...
04/06/2017 ∙ by Aravind Vasudevan, et al. ∙ 0 ∙ share

read it
Vectorization of Multibyte Floating Point Data Formats

We propose a scheme for reduced-precision representation of floating poi...
01/26/2016 ∙ by Andrew Anderson, et al. ∙ 0 ∙ share

read it

Andrew Anderson

Featured Co-authors

Alan Fern

David Gregg

Rozenn Dahyot

Jing Su

Michael F. P. O'Boyle

Valentin Radu

Margaret Burnett

Claudia Hilderbrand

Jonathan Dodge

Barbara Barabasz

Yuan Wen

TASO: Time and Space Optimization for Memory-Constrained DNN Inference

Composition of Saliency Metrics for Channel Pruning with a Myopic Oracle

Performance-Oriented Neural Architecture Search

A Taxonomy of Channel Pruning Signals in CNNs

Explaining Reinforcement Learning to Mere Mortals: An Empirical Study

Scalar Arithmetic Multiple Data: Customizable Precision for Deep Neural Networks

Error Analysis and Improving the Accuracy of Winograd Convolution for Deep Neural Networks

Improving accuracy of Winograd convolution for DNNs

Toward Foraging for Understanding of StarCraft Agents: An Empirical Study

How the Experts Do It: Assessing and Explaining Agent Behaviors in Real-Time Strategy Games

Optimal DNN Primitive Selection with Partitioned Boolean Quadratic Programming

Low-memory GEMM-based convolution algorithms for deep neural networks

Parallel Multi Channel Convolution using General Matrix Multiplication

Vectorization of Multibyte Floating Point Data Formats