Publications (24)
An LLM's Attempts to Adapt to Diverse Software Engineers' Problem-Solving Styles: More Inclusive & Equitable?
Andrew Anderson, David Piorkowski, Margaret Burnett +1
Software engineers use code-fluent large language models (LLMs) to help explain unfamiliar code, yet LLM explanations are not adapted to engineers' diverse problem-solving needs. W…
How to Measure Human-AI Prediction Accuracy in Explainable AI Systems
Sujay Koujalgi, Andrew Anderson, Iyadunni Adenuga +8
Assessing an AI system's behavior-particularly in Explainable AI Systems-is sometimes done empirically, by measuring people's abilities to predict the agent's next move-but how to…
Error Analysis and Improving the Accuracy of Winograd Convolution for Deep Neural Networks
Barbara Barabasz, Andrew Anderson, Kirk M. Soodhalter +1
Popular deep neural networks (DNNs) spend the majority of their execution time computing convolutions. The Winograd family of algorithms can greatly reduce the number of arithmetic…
Scalar Arithmetic Multiple Data: Customizable Precision for Deep Neural Networks
Andrew Anderson, David Gregg
Quantization of weights and activations in Deep Neural Networks (DNNs) is a powerful technique for network compression, and has enjoyed significant attention and success. However,…
Parallel Multi Channel Convolution using General Matrix Multiplication
Aravind Vasudevan, Andrew Anderson, David Gregg
Convolutional neural networks (CNNs) have emerged as one of the most successful machine learning technologies for image and video processing. The most computationally intensive par…
Measuring User Experience Inclusivity in Human-AI Interaction via Five User Problem-Solving Styles
Andrew Anderson, Jimena Noa Guevara, Fatima Moussaoui +3
Motivations: Recent research has emerged on generally how to improve AI product user experiences, but relatively little is known about an AI product's inclusivity. For example, wha…
TASO: Time and Space Optimization for Memory-Constrained DNN Inference
Yuan Wen, Andrew Anderson, Valentin Radu +2
Convolutional neural networks (CNNs) are used in many embedded applications, from industrial robotics and automation systems to biometric identification on mobile devices. State-of…
Performance-Oriented Neural Architecture Search
Andrew Anderson, Jing Su, Rozenn Dahyot +1
Hardware-Software Co-Design is a highly successful strategy for improving performance of domain-specific computing systems. We argue for the application of the same methodology to…
Vectorization of Multibyte Floating Point Data Formats
Andrew Anderson, David Gregg
We propose a scheme for reduced-precision representation of floating point data on a continuum between IEEE-754 floating point types. Our scheme enables the use of lower precision…
"Over-the-Hood" AI Inclusivity Bugs and How 3 AI Product Teams Found and Fixed Them
Andrew Anderson, Fatima A. Moussaoui, Jimena Noa Guevara +2
While much research has shown the presence of AI's "under-the-hood" biases (e.g., algorithmic, training data, etc.), what about "over-the-hood" inclusivity biases: barriers in user…
Low-memory GEMM-based convolution algorithms for deep neural networks
Andrew Anderson, Aravind Vasudevan, Cormac Keane +1
Deep neural networks (DNNs) require very large amounts of computation both for training and for inference when deployed in the field. A common approach to implementing DNNs is to r…
Optimal DNN Primitive Selection with Partitioned Boolean Quadratic Programming
Andrew Anderson, David Gregg
Deep Neural Networks (DNNs) require very large amounts of computation both for training and for inference when deployed in the field. Many different algorithms have been proposed t…
Domino Saliency Metrics: Improving Existing Channel Saliency Metrics with Structural Information
Kaveena Persand, Andrew Anderson, David Gregg
Channel pruning is used to reduce the number of weights in a Convolutional Neural Network (CNN). Channel pruning removes slices of the weight tensor so that the convolution layer r…
Winograd Convolution for Deep Neural Networks: Efficient Point Selection
Syed Asad Alam, Andrew Anderson, Barbara Barabasz +1
Convolutional neural networks (CNNs) have dramatically improved the accuracy of tasks such as object recognition, image segmentation and interactive speech systems. CNNs require la…
From Verification Burden to Trusted Collaboration: Design Goals for LLM-Assisted Literature Reviews
Brenda Nogueira, Werner Geyer, Andrew Anderson +4
Large Language Models (LLMs) are increasingly embedded in academic writing practices. Although numerous studies have explored how researchers employ these tools for scientific writ…
Composition of Saliency Metrics for Channel Pruning with a Myopic Oracle
Kaveena Persand, Andrew Anderson, David Gregg
The computation and memory needed for Convolutional Neural Network (CNN) inference can be reduced by pruning weights from the trained network. Pruning is guided by a pruning salien…
Bonseyes AI Pipeline -- bringing AI to you. End-to-end integration of data, algorithms and deployment tools
Miguel de Prado, Jing Su, Rabia Saeed +9
Next generation of embedded Information and Communication Technology (ICT) systems are collaborative systems able to perform autonomous tasks. The remarkable expansion of the embed…
Taxonomy of Saliency Metrics for Channel Pruning
Kaveena Persand, Andrew Anderson, David Gregg
Pruning unimportant parameters can allow deep neural networks (DNNs) to reduce their heavy computation and memory requirements. A saliency metric estimates which parameters can be…
Measuring SES-related traits relating to technology usage: Two validated surveys
Chimdi Chikezie, Pannapat Chenpaiseng, Puja Agarwal +9
Software producers are now recognizing the importance of improving their products' suitability for diverse populations, but little attention has been given to measurements to shed…
Explaining Reinforcement Learning to Mere Mortals: An Empirical Study
Andrew Anderson, Jonathan Dodge, Amrita Sadarangani +6
We present a user study to investigate the impact of explanations on non-experts' understanding of reinforcement learning (RL) agents. We investigate both a common RL visualization…
Toward Foraging for Understanding of StarCraft Agents: An Empirical Study
Sean Penney, Jonathan Dodge, Claudia Hilderbrand +3
Assessing and understanding intelligent agents is a difficult task for users that lack an AI background. A relatively new area, called "Explainable AI," is emerging to help address…
Can LLM Code Explanations Adapt to Diverse Problem-Solvers' Needs?
Andrew Anderson, David Piorkowski, Justin Weisz +2
Large language model (LLM) code explanations can support people in solving code-related problems, yet prior work has shown that people have diverse problem-solving styles. If expla…
How the Experts Do It: Assessing and Explaining Agent Behaviors in Real-Time Strategy Games
Jonathan Dodge, Sean Penney, Claudia Hilderbrand +2
How should an AI-based explanation system explain an agent's complex behavior to ordinary end users who have no background in AI? Answering this question is an active research area…
Inclusive Design of AI's Explanations: Just for Those Previously Left Out, or for Everyone?
Md Montaser Hamid, Fatima Moussaoui, Jimena Noa Guevara +4
Motivations: Explainable Artificial Intelligence (XAI) systems aim to improve users' understanding of AI, but XAI research shows many cases of different explanations serving some u…