Position Paper: Towards Transparent Machine Learning
arXiv:1911.06612
Abstract
Transparent machine learning is introduced as an alternative form of machine learning, where both the model and the learning system are represented in source code form. The goal of this project is to enable direct human understanding of machine learning models, giving us the ability to learn, verify, and refine them as programs. If solved, this technology could represent a best-case scenario for the safety and security of AI systems going forward.
References in corpus (8)
- Methods for Interpreting and Understanding Deep Neural Networks
- Explainable Artificial Intelligence: Understanding, Visualizing and Interpreting Deep Learning Models
- PyCUDA and PyOpenCL: A Scripting-Based Approach to GPU Run-Time Code Generation
- Billion-scale semi-supervised learning for image classification
- Towards Fast Computation of Certified Robustness for ReLU Networks
- Towards Verified Artificial Intelligence
- Unexplainability and Incomprehensibility of Artificial Intelligence
- Unpredictability of AI