5 papers
Efficiera Residual Networks: Hardware-Friendly Fully Binary Weight with 2-bit Activation Model Achieves Practical ImageNet Accuracy
Shuntaro Takahashi, Takuya Wakisaka, Hiroyuki Tokunaga
The edge-device environment imposes severe resource limitations, encompassing computation costs, hardware resource usage, and energy consumption for deploying deep neural network m…
A Comparison of Two Fluctuation Analyses for Natural Language Clustering Phenomena: Taylor and Ebeling & Neiman Methods
Kumiko Tanaka-Ishii, Shuntaro Takahashi
This article considers the fluctuation analysis methods of Taylor and Ebeling & Neiman. While both have been applied to various phenomena in the statistical mechanics domain, their…
Evaluating Computational Language Models with Scaling Properties of Natural Language
Shuntaro Takahashi, Kumiko Tanaka-Ishii
In this article, we evaluate computational models of natural language with respect to the universal statistical behaviors of natural language. Statistical mechanical analyses have…
Assessing Language Models with Scaling Properties
Shuntaro Takahashi, Kumiko Tanaka-Ishii
Language models have primarily been evaluated with perplexity. While perplexity quantifies the most comprehensible prediction performance, it does not provide qualitative informati…
Do Neural Nets Learn Statistical Laws behind Natural Language?
Shuntaro Takahashi, Kumiko Tanaka-Ishii
The performance of deep learning in natural language processing has been spectacular, but the reasons for this success remain unclear because of the inherent complexity of deep lea…