83 citations · 308 across the 26 of their papers we have counts for
8 papers · 1 filter
Unwrapping The Black Box of Deep ReLU Networks: Interpretability, Diagnostics, and Simplification
Agus Sudjianto, William Knauth, Rahul Singh +2
The deep neural networks (DNNs) have achieved great success in learning complex patterns with strong predictive power, but they are often thought of as "black box" models without a…
Model Robustness with Text Classification: Semantic-preserving adversarial attacks
Rahul Singh, Tarun Joshi, Vijayan N. Nair +1
We propose algorithms to create adversarial attacks to assess model robustness in text classification problems. They can be used to create white box attacks and black box attacks w…
SHAP values for Explaining CNN-based Text Classification Models
Wei Zhao, Tarun Joshi, Vijayan N. Nair +1
Deep neural networks are increasingly used in natural language processing (NLP) models. However, the need to interpret and explain the results from complex algorithms are limiting…
Supervised Machine Learning Techniques: An Overview with Applications to Banking
Linwei Hu, Jie Chen, Joel Vaughan +4
This article provides an overview of Supervised Machine Learning (SML) with a focus on applications to banking. The SML techniques covered include Bagging (Random Forest or RF), Bo…
Surrogate Locally-Interpretable Models with Supervised Machine Learning Algorithms
Linwei Hu, Jie Chen, Vijayan N. Nair +1
Supervised Machine Learning (SML) algorithms, such as Gradient Boosting, Random Forest, and Neural Networks, have become popular in recent years due to their superior predictive pe…
An Effective and Efficient Initialization Scheme for Training Multi-layer Feedforward Neural Networks
Zebin Yang, Hengtao Zhang, Agus Sudjianto +1
Network initialization is the first and critical step for training neural networks. In this paper, we propose a novel network initialization scheme based on the celebrated Stein's…