136 citations · 231 across the 11 of their papers we have counts for
15 papers
Fuzzy Simplicial Networks: A Topology-Inspired Model to Improve Task Generalization in Few-shot Learning
Henry Kvinge, Zachary New, Nico Courts +6
Deep learning has shown great success in settings with massive amounts of data but has struggled when data is limited. Few-shot learning algorithms, which seek to address this limi…
Deep learning to generate in silico chemical property libraries and candidate molecules for small molecule identification in complex samples
Sean M. Colby, Jamie R. Nuñez, Nathan O. Hodas +2
Comprehensive and unambiguous identification of small molecules in complex samples will revolutionize our understanding of the role of metabolites in biological systems. Existing a…
The Outer Product Structure of Neural Network Derivatives
Craig Bakker, Michael J. Henry, Nathan O. Hodas
In this paper, we show that feedforward and recurrent neural networks exhibit an outer product derivative structure but that convolutional neural networks do not. This structure ma…
Model of Cognitive Dynamics Predicts Performance on Standardized Tests
Nathan O. Hodas, Jacob Hunter, Stephen J. Young +1
In the modern knowledge economy, success demands sustained focus and high cognitive performance. Research suggests that human cognition is linked to a finite resource, and upon its…
Doing the impossible: Why neural networks can be trained at all
Nathan O. Hodas, Panos Stinis
As deep neural networks grow in size, from thousands to millions to billions of weights, the performance of those networks becomes limited by our ability to accurately train them.…
Sharkzor: Interactive Deep Learning for Image Triage, Sort and Summary
Meg Pirrung, Nathan Hilliard, Artëm Yankov +4
Sharkzor is a web application for machine-learning assisted image sort and summary. Deep learning algorithms are leveraged to infer, augment, and automate the user's mental model.…
Few-Shot Learning with Metric-Agnostic Conditional Embeddings
Nathan Hilliard, Lawrence Phillips, Scott Howland +3
Learning high quality class representations from few examples is a key problem in metric-learning approaches to few-shot learning. To accomplish this, we introduce a novel architec…
SMILES2Vec: An Interpretable General-Purpose Deep Neural Network for Predicting Chemical Properties
Garrett B. Goh, Nathan O. Hodas, Charles Siegel +1
Chemical databases store information in text representations, and the SMILES format is a universal standard used in many cheminformatics software. Encoded in each SMILES string is…
How Much Chemistry Does a Deep Neural Network Need to Know to Make Accurate Predictions?
Garrett B. Goh, Charles Siegel, Abhinav Vishnu +2
The meteoric rise of deep learning models in computer vision research, having achieved human-level accuracy in image recognition tasks is firm evidence of the impact of representat…
Bounded Rationality in Scholarly Knowledge Discovery
Kristina Lerman, Nathan Hodas, Hao Wu
In an information-rich world, people's time and attention must be divided among rapidly changing information sources and the diverse tasks demanded of them. How people decide which…
A Koopman Operator Approach for Computing and Balancing Gramians for Discrete Time Nonlinear Systems
Enoch Yeung, Zhiyuan Liu, Nathan O. Hodas
In this paper, we consider the problem of quantifying controllability and observability of a nonlinear discrete time dynamical system. We introduce the Koopman operator as a canoni…
Dynamic Input Structure and Network Assembly for Few-Shot Learning
Nathan Hilliard, Nathan O. Hodas, Courtney D. Corley
The ability to learn from a small number of examples has been a difficult problem in machine learning since its inception. While methods have succeeded with large amounts of traini…
Learning Deep Neural Network Representations for Koopman Operators of Nonlinear Dynamical Systems
Enoch Yeung, Soumya Kundu, Nathan Hodas
The Koopman operator has recently garnered much attention for its value in dynamical systems analysis and data-driven model discovery. However, its application has been hindered by…
How a user's personality influences content engagement in social media
Nathan O. Hodas, Ryan Butner, Court Corley
Social media presents an opportunity for people to share content that they find to be significant, funny, or notable. No single piece of content will appeal to all users, but are t…
The Quality of Oscillations in Overdamped Networks
Nathan O. Hodas
The second law of thermodynamics implies that no macroscopic system may oscillate indefinitely without consuming energy. The question of the number of possible oscillations and the…