DecisiveNets: Training Deep Associative Memories to Solve Complex
Machine Learning Problems
Ghouthi Boukli Hacene Vincent Gripon Carlos Lassance
作者信息
Abstract
Learning deep representations to solve complex machine learning tasks has
become the prominent trend in the past few years. Indeed, Deep Neural Networks
are now the golden standard in domains as various as computer vision, natural
language processing or even playing combinatorial games. However, problematic
limitations are hidden behind this surprising universal capability. Among other
things, explainability of the decisions is a major concern, especially since
deep neural networks are made up of a very large number of trainable
parameters. Moreover, computational complexity can quickly become a problem,
especially in contexts constrained by real time or limited resources.
Therefore, understanding how information is stored and the impact this storage
can have on the system remains a major and open issue. In this chapter, we
introduce a method to transform deep neural network models into deep
associative memories, with simpler, more explicable and less expensive
operations. We show through experiments that these transformations can be done
without penalty on predictive performance. The resulting deep associative
memories are excellent candidates for artificial intelligence that is easier to
theorize and manipulate.引用本文复制引用
Ghouthi Boukli Hacene,Vincent Gripon,Carlos Lassance.DecisiveNets: Training Deep Associative Memories to Solve Complex
Machine Learning Problems[EB/OL].(2020-12-02)[2026-04-04].https://arxiv.org/abs/2012.01509.学科分类
计算技术、计算机技术
|国家预印本平台
评论