- Deep Learning with Keras
- Antonio Gulli Sujit Pal
- 84字
- 2021-07-02 23:58:05
Increasing the number of epochs
Let's make another attempt and increase the number of epochs used for training from 20 to 200. Unfortunately, this choice increases our computation time by 10, but it gives us no gain. The experiment is unsuccessful, but we have learned that if we spend more time learning, we will not necessarily improve. Learning is more about adopting smart techniques and not necessarily about the time spent in computations. Let's keep track of our sixth variant in the following graph:

推薦閱讀
- Raspberry Pi 3 Cookbook for Python Programmers
- 新型電腦主板關鍵電路維修圖冊
- Applied Unsupervised Learning with R
- Python GUI Programming:A Complete Reference Guide
- Manage Partitions with GParted How-to
- Arduino BLINK Blueprints
- 電腦高級維修及故障排除實戰
- 基于Proteus仿真的51單片機應用
- LPC1100系列處理器原理及應用
- Spring Cloud微服務和分布式系統實踐
- IP網絡視頻傳輸:技術、標準和應用
- 微服務實戰
- Advanced Machine Learning with R
- 微服務架構實戰:基于Spring Boot、Spring Cloud、Docker
- Learning Microsoft Cognitive Services