38 citations · 102 across the 11 of their papers we have counts for
11 papers
MolExplain: An Interactive Tool for Explainable Molecular Property Prediction
Pirm Dhararag, Dylan Cashman
The application of machine learning to molecular property prediction has become increasingly prevalent in drug discovery, yet most models operate as black boxes, returning a predic…
VecCISC: Improving Confidence-Informed Self-Consistency with Reasoning Trace Clustering and Candidate Answer Selection
James Petullo, Sonny George, Dylan Cashman +1
A standard technique for scaling inference-time reasoning is Self-Consistency, whereby multiple candidate answers are sampled from an LLM and the most common answer is selected. Mo…
A Critical Analysis of the Usage of Dimensionality Reduction in Four Domains
Dylan Cashman, Mark Keller, Hyeon Jeon +2
Dimensionality reduction is used as an important tool for unraveling the complexities of high-dimensional datasets in many fields of science, such as cell biology, chemical informa…
Inferential Tasks as an Evaluation Technique for Visualization
Ashley Suh, Ab Mosca, Shannon Robinson +4
Designing suitable tasks for visualization evaluation remains challenging. Traditional evaluation techniques commonly rely on 'low-level' or 'open-ended' tasks to assess the effica…
Are Metrics Enough? Guidelines for Communicating and Visualizing Predictive Models to Subject Matter Experts
Ashley Suh, Gabriel Appleby, Erik W. Anderson +3
Presenting a predictive model's performance is a communication bottleneck that threatens collaborations between data scientists and subject matter experts. Accuracy and error metri…
UnProjection: Leveraging Inverse-Projections for Visual Analytics of High-Dimensional Data
Mateus Espadoto, Gabriel Appleby, Ashley Suh +6
Projection techniques are often used to visualize high-dimensional data, allowing users to better understand the overall structure of multi-dimensional spaces on a 2D screen. Altho…
CAVA: A Visual Analytics System for Exploratory Columnar Data Augmentation Using Knowledge Graphs
Dylan Cashman, Shenyu Xu, Subhajit Das +6
Most visual analytics systems assume that all foraging for data happens before the analytics process; once analysis begins, the set of data attributes considered is fixed. Such sep…
Ablate, Variate, and Contemplate: Visual Analytics for Discovering Neural Architectures
Dylan Cashman, Adam Perer, Remco Chang +1
Deep learning models require the configuration of many layers and parameters in order to get good results. However, there are currently few systematic guidelines for how to configu…
RNNbow: Visualizing Learning via Backpropagation Gradients in Recurrent Neural Networks
Dylan Cashman, Genevieve Patterson, Abigail Mosca +3
We present RNNbow, an interactive tool for visualizing the gradient flow during backpropagation training in recurrent neural networks. RNNbow is a web application that displays the…
A User-based Visual Analytics Workflow for Exploratory Model Analysis
Dylan Cashman, Shah Rukh Humayoun, Florian Heimerl +9
Many visual analytics systems allow users to interact with machine learning models towards the goals of data exploration and insight generation on a given dataset. However, in some…
NeuralCubes: Deep Representations for Visual Data Exploration
Zhe Wang, Dylan Cashman, Mingwei Li +5
Visual exploration of large multidimensional datasets has seen tremendous progress in recent years, allowing users to express rich data queries that produce informative visual summ…