- R Deep Learning Essentials
- Mark Hodnett Joshua F. Wiley
- 256字
- 2021-08-13 15:34:32
Back to deep learning
Many of the concepts in the previous section apply to deep learning because deep learning is simply neural networks with two or more hidden layers. To demonstrate this, let's look at the following code in R that loads the mxnet deep learning library and calls the help command on the function in that library that trains a deep learning model. Even though we have not trained any models using this library yet, we have already seen many of the parameters in this function:
library(mxnet)
?mx.model.FeedForward.create
This brings up the help page for the FeedForward function in the mxnet library, which is the forward-propagation/model train function. mxnet and most deep learning libraries do not have a specific backward-propagation function, they handle this implicitly:
mx.model.FeedForward.create(symbol, X, y = NULL, ctx = NULL,
begin.round = 1, num.round = 10, optimizer = "sgd",
initializer = mx.init.uniform(0.01), eval.data = NULL,
eval.metric = NULL, epoch.end.callback = NULL,
batch.end.callback = NULL, array.batch.size = 128
...)
We will see more of this function in subsequent chapters; for now we will just look at the parameters.
- 龍芯應(yīng)用開發(fā)標(biāo)準(zhǔn)教程
- 基于Proteus和Keil的C51程序設(shè)計項(xiàng)目教程(第2版):理論、仿真、實(shí)踐相融合
- Linux運(yùn)維之道(第2版)
- 基于ARM的嵌入式系統(tǒng)和物聯(lián)網(wǎng)開發(fā)
- Hands-On Machine Learning with C#
- Hands-On Artificial Intelligence for Banking
- BeagleBone Robotic Projects
- 超大流量分布式系統(tǒng)架構(gòu)解決方案:人人都是架構(gòu)師2.0
- RISC-V處理器與片上系統(tǒng)設(shè)計:基于FPGA與云平臺的實(shí)驗(yàn)教程
- Spring Cloud微服務(wù)和分布式系統(tǒng)實(shí)踐
- 新編電腦組裝與硬件維修從入門到精通
- Intel FPGA權(quán)威設(shè)計指南:基于Quartus Prime Pro 19集成開發(fā)環(huán)境
- 單片機(jī)項(xiàng)目設(shè)計教程
- 觸摸屏應(yīng)用技術(shù)從入門到精通
- FPGA實(shí)驗(yàn)實(shí)訓(xùn)教程