Statistical model-based evaluation of neural networks

2020/11/18 by Sandipan Das, Prakash B. Gohain, Das, Sandipan +7
Computer Science · #Adversarial Robustness in Machine Learning #FOS: Computer and information sciences #Machine Learning (cs.LG) #Machine Learning and Data Classification #Neural Networks and Applications

paper · pdf · doi:10.48550/arxiv.2011.09015

openalex publication_date 2020/11/18 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

Using a statistical model-based data generation, we develop an experimental setup for the evaluation of neural networks (NNs). The setup helps to benchmark a set of NNs vis-a-vis minimum-mean-square-error (MMSE) performance bounds. This allows us to test the effects of training data size, data dimension, data geometry, noise, and mismatch between training and testing conditions. In the proposed setup, we use a Gaussian mixture distribution to generate data for training and testing a set of competing NNs. Our experiments show the importance of understanding the type and statistical conditions of data for appropriate application and design of NNs

Citations

• Understanding Neural Networks Through Deep Visualization
• Fundamentals of Statistical Signal Processing: Estimation Theory
• SSFN -- Self Size-estimating Feed-forward Network with Low Complexity, Limited Need for Human Intervention, and Consistent Behaviour across Trials

Related

• MLDS: A Dataset for Weight-Space Analysis of Neural Networks
• Reliable Evaluation of Neural Network for Multiclass Classification of\n Real-world Data
• Testing for Normality with Neural Networks
• Neural Network based Explicit Mixture Models and Expectation-maximization based Learning
• ALT-MAS: A Data-Efficient Framework for Active Testing of Machine Learning Algorithms