- 博客(2)
- 资源 (23)
- 收藏
- 关注
RSS订阅转载 Linux 设备驱动 Edition 3(书摘)
主要是一重要的设备接口与内部API函数，以供查阅.中断：/proc/interrupts 的显示展示了有多少中断硬件递交给系统中的每个 CPU/proc/stat 记录了几个关于系统活动的低级统计量, 包括(但是不限于)自系统启动以来收到的中断数. intr 5167833 51
2011-07-08 17:33:07
1683
翻译 如何加入Linux社区开发(译)二
5：发布补丁或早或晚，总有一天，你的工作是准备提交给社区审查，并最终纳入到内核主线。 并不奇怪，内核开发社区已经形成了一套公约和程序，用来发布补丁，遵循他们会让大家更容易参与。 这份文件将试图在合理的细节上覆盖这些程序，更多信息也可以在内核文档目录中SubmittingPatch
2011-07-07 16:14:51
1999
1
inception-resnet-v1-part0
tensorflow, models, slim pre-trained model: inception-resnet-v1-201608-30.tar.gz
2017-07-11
inception-resnet-v1-part24
tensorflow, models, slim pre-trained model: inception-resnet-v1-201608-30.tar.gz
2017-07-11
inception-resnet-v1-part3
tensorflow, models, slim pre-trained model: inception-resnet-v1-201608-30.tar.gz
2017-07-11
inception-resnet-v1-part2
tensorflow, models, slim pre-trained model: inception-resnet-v1-201608-30.tar.gz
2017-07-11
inception-resnet-v1-part1
tensorflow, models, slim pre-trained model: inception-resnet-v1-201608-30.tar.gz
2017-07-11
Letter Recognition Using Holland-Style Adaptive Classifiers
Machine rule induction was examined on a difficult categorization problem by applying a Hollandstyle
classifier system to a complex letter recognition task. A set of 20,000 unique letter images was generated
by randomly distorting pixel images of the 26 uppercase letters from 20 different commercial fonts. The parent
fonts represented a full range of character types including script, italic, serif, and Gothic. The features of each
of the 20,000 characters were summarized in terms of 16 primitive numerical attributes. Our research focused
on machine induction techniques for generating IF-THEN classifiers in which the IF part was a list of values
for each of the 16 attributes and the THEN part was the correct category, i.e., one of the 26 letters of the alphabet.
We examined the effects of different procedures for encoding attributes, deriving new rules, and apportioning
credit among the rules. Binary and Gray-code attribute encodings that required exact matches for rule activation
were compared with integer representations that employed fuzzy matching for rule activation. Random and genetic
methods for rule creation were compared with instance-based generalization. The strength/specificity method
for credit apportionment was compared with a procedure we call "accuracy/utility."
2012-02-05
空空如也
TA创建的收藏夹 TA关注的收藏夹
TA关注的人