
TASO: Time and Space Optimization for MemoryConstrained DNN Inference
Convolutional neural networks (CNNs) are used in many embedded applicati...
read it

Composition of Saliency Metrics for Channel Pruning with a Myopic Oracle
The computation and memory needed for Convolutional Neural Network (CNN)...
read it

PerformanceOriented Neural Architecture Search
HardwareSoftware CoDesign is a highly successful strategy for improvin...
read it

A Taxonomy of Channel Pruning Signals in CNNs
Convolutional neural networks (CNNs) are widely used for classification ...
read it

Explaining Reinforcement Learning to Mere Mortals: An Empirical Study
We present a user study to investigate the impact of explanations on non...
read it

Scalar Arithmetic Multiple Data: Customizable Precision for Deep Neural Networks
Quantization of weights and activations in Deep Neural Networks (DNNs) i...
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...
read it

Improving accuracy of Winograd convolution for DNNs
Modern deep neural networks (DNNs) spend a large amount of their executi...
read it

Toward Foraging for Understanding of StarCraft Agents: An Empirical Study
Assessing and understanding intelligent agents is a difficult task for u...
read it

How the Experts Do It: Assessing and Explaining Agent Behaviors in RealTime Strategy Games
How should an AIbased explanation system explain an agent's complex beh...
read it

Optimal DNN Primitive Selection with Partitioned Boolean Quadratic Programming
Deep Neural Networks (DNNs) require very large amounts of computation bo...
read it

Lowmemory GEMMbased convolution algorithms for deep neural networks
Deep neural networks (DNNs) require very large amounts of computation bo...
read it

Parallel Multi Channel Convolution using General Matrix Multiplication
Convolutional neural networks (CNNs) have emerged as one of the most suc...
read it

Vectorization of Multibyte Floating Point Data Formats
We propose a scheme for reducedprecision representation of floating poi...
read it
Andrew Anderson
is this you? claim profile