Problem
Research questions and friction points this paper is trying to address.
deep learning
entropy space theory
theoretical research
Understanding Deep Learning via Entropy Space Theory
🤖 AI Summary
本文通过引入熵空间理论来解决深度学习理论研究滞后的问题，提出了一种统一的坐标系统以更好地理解和评估模型状态。
📝 Abstract
Deep learning is often criticized for its theoretical research lagging behind practice. To make deep learning easier to understand, the entropy space theory is first introduced here. The entropy space can cover all the possibilities of any deep learning model by topological structure. It is independent of network parameters. Through the designed fundamental operations and norm, entropy space is proven to be a normed space within the formal axiomatic framework. Based on the theory, a unified coordinate system is proposed. It can coordinatize every state of a model and rank them by compression of the maximal value of information entropy. The theory offers a novel priori framework for mathematical fundamentals of deep learning.
Innovation
Methods, ideas, or system contributions that make the work stand out.
Entropy Space Theory
Topological Structure
Unified Coordinate System
Information Entropy
🔎 Similar Papers
No similar papers found.
