Oren Wright
YOU?
Author Swipe
View article: Kalman Bayesian Transformer
Kalman Bayesian Transformer Open
Sequential fine-tuning of transformers is useful when new data arrive sequentially, especially with shifting distributions. Unlike batch learning, sequential learning demands that training be stabilized despite a small amount of data by ba…
View article: A Guide to Failure in Machine Learning: Reliability and Robustness from Foundations to Practice
A Guide to Failure in Machine Learning: Reliability and Robustness from Foundations to Practice Open
One of the main barriers to adoption of Machine Learning (ML) is that ML models can fail unexpectedly. In this work, we aim to provide practitioners a guide to better understand why ML models fail and equip them with techniques they can us…
View article: An Analytic Solution to Covariance Propagation in Neural Networks
An Analytic Solution to Covariance Propagation in Neural Networks Open
Uncertainty quantification of neural networks is critical to measuring the reliability and robustness of deep learning systems. However, this often involves costly or inaccurate sampling methods and approximations. This paper presents a sa…
View article: Edge Entropy as an Indicator of the Effectiveness of GNNs over CNNs for Node Classification
Edge Entropy as an Indicator of the Effectiveness of GNNs over CNNs for Node Classification Open
Graph neural networks (GNNs) extend convolutional neural networks (CNNs) to graph-based data. A question that arises is how much performance improvement does the underlying graph structure in the GNN provide over the CNN (that ignores this…
View article: Graph Signal Processing and Deep Learning: Convolution, Pooling, and Topology
Graph Signal Processing and Deep Learning: Convolution, Pooling, and Topology Open
Deep learning, particularly convolutional neural networks (CNNs), have\nyielded rapid, significant improvements in computer vision and related domains.\nBut conventional deep learning architectures perform poorly when data have an\nunderly…
View article: Pooling in Graph Convolutional Neural Networks
Pooling in Graph Convolutional Neural Networks Open
Graph convolutional neural networks (GCNNs) are a powerful extension of deep learning techniques to graph-structured data problems. We empirically evaluate several pooling methods for GCNNs, and combinations of those graph pooling methods …
View article: Detecting gender differences in perception of emotion in crowdsourced data
Detecting gender differences in perception of emotion in crowdsourced data Open
Do men and women perceive emotions differently? Popular convictions place women as more emotionally perceptive than men. Empirical findings, however, remain inconclusive. Most prior studies focus on visual modalities. In addition, almost a…