Affiliation:
1. Knowledge-Trail, Los Banos, CA 93635, USA
Abstract
It is well known that deep learning (DNN) has strong limitations due to a lack of explainability and weak defense against possible adversarial attacks. These attacks would be a concern for autonomous teams producing a state of high entropy for the team’s structure. In our first article for this Special Issue, we propose a meta-learning/DNN → kNN architecture that overcomes these limitations by integrating deep learning with explainable nearest neighbor learning (kNN). This architecture is named “shaped charge”. The focus of the current article is the empirical validation of “shaped charge”. We evaluate the proposed architecture for summarization, question answering, and content creation tasks and observe a significant improvement in performance along with enhanced usability by team members. We observe a substantial improvement in question answering accuracy and also the truthfulness of the generated content due to the application of the shaped-charge learning approach.
Subject
General Physics and Astronomy
Reference42 articles.
1. Galitsky, B., Ilvovsky, D., and Goldberg, S. (2023). Shaped-Charge Learning Architecture for the Human-Machine Teams. Entropy, 25.
2. Rombach, R., Blattmann, A., Lorenz, D., Esser, P., and Ommer, B. (2022, January 19–20). HighResolution Image Synthesis with Latent Diffusion Models. Proceedings of the CVPR, New Orleans, LA, USA.
3. Ramesh, A., Dhariwal, P., Nichol, A., Chu, C., and Chen, M. (2022). Hierarchical Text-Conditional Image Generation with CLIP Latents. arXiv.
4. Favretti, M. (2018). Remarks on the Maximum Entropy Principle with Application to the Maximum Entropy Theory of Ecology. Entropy, 20.
5. On information and sufficiency;Kullback;Ann. Math. Stat.,1951