29 citations · 50 across the 13 of their papers we have counts for
13 papers
Multi Resolution Analysis (MRA) for Approximate Self-Attention
Zhanpeng Zeng, Sourav Pal, Jeffery Kline +2
Transformers have emerged as a preferred model for many tasks in natural langugage processing and vision. Recent efforts on training and deploying Transformers more efficiently hav…
You Only Sample (Almost) Once: Linear Cost Self-Attention Via Bernoulli Sampling
Zhanpeng Zeng, Yunyang Xiong, Sathya N. Ravi +3
Transformer-based models are widely used in natural language processing (NLP). Central to the transformer model is the self-attention mechanism, which captures the interactions of…
Domain Agnostic Few-Shot Learning For Document Intelligence
Jaya Krishna Mandivarapu, Eric bunch, Glenn fung
Few-shot learning aims to generalize to novel classes with only a few samples with class labels. Research in few-shot learning has borrowed techniques from transfer learning, metri…
Efficient Document Image Classification Using Region-Based Graph Neural Network
Jaya Krishna Mandivarapu, Eric Bunch, Qian You +1
Document image classification remains a popular research area because it can be commercialized in many enterprise applications across different industries. Recent advancements in l…
Weighting vectors for machine learning: numerical harmonic analysis applied to boundary detection
Eric Bunch, Jeffery Kline, Daniel Dickinson +2
Metric space magnitude, an active field of research in algebraic topology, is a scalar quantity that summarizes the effective number of distinct points that live in a general metri…
Nyströmformer: A Nyström-Based Algorithm for Approximating Self-Attention
Yunyang Xiong, Zhanpeng Zeng, Rudrasis Chakraborty +4
Transformers have emerged as a powerful tool for a broad range of natural language processing tasks. A key component that drives the impressive performance of Transformers is the s…
A Simple yet Brisk and Efficient Active Learning Platform for Text Classification
Teja Kanchinadam, Qian You, Keith Westpfahl +4
In this work, we propose the use of a fully managed machine learning service, which utilizes active learning to directly build models from unstructured data. With this tool, busine…
Graph Neural Networks to Predict Customer Satisfaction Following Interactions with a Corporate Call Center
Teja Kanchinadam, Zihang Meng, Joseph Bockhorst +2
Customer satisfaction is an important factor in creating and maintaining long-term relationships with customers. Near real-time identification of potentially dissatisfied customers…
SGD Distributional Dynamics of Three Layer Neural Networks
Victor Luo, Yazhen Wang, Glenn Fung
With the rise of big data analytics, multi-layer neural networks have surfaced as one of the most powerful machine learning methods. However, their theoretical mathematical propert…
Simplicial 2-Complex Convolutional Neural Nets
Eric Bunch, Qian You, Glenn Fung +1
Recently, neural network architectures have been developed to accommodate when the data has the structure of a graph or, more generally, a hypergraph. While useful, graph structure…
Practical applications of metric space magnitude and weighting vectors
Eric Bunch, Daniel Dickinson, Jeffery Kline +1
Metric space magnitude, an active subject of research in algebraic topology, originally arose in the context of biology, where it was used to represent the effective number of dist…
Optimizing Nondecomposable Data Dependent Regularizers via Lagrangian Reparameterization offers Significant Performance and Efficiency Gains
Sathya N. Ravi, Abhay Venkatesh, Glenn Moo Fung +1
Data dependent regularization is known to benefit a wide variety of problems in machine learning. Often, these regularizers cannot be easily decomposed into a sum over a finite num…
Approximating the Convex Hull via Metric Space Magnitude
Glenn Fung, Eric Bunch, Dan Dickinson
Magnitude of a finite metric space and the related notion of magnitude functions on metric spaces is an active area of research in algebraic topology. Magnitude originally arose in…