Differences

This shows you the differences between two versions of the page.

--- knowledge_base:programming:machine_learning [2022/12/02 14:45] – removed - external edit (Unknown date) 127.0.0.1
+++ knowledge_base:programming:machine_learning [2023/02/18 12:12] (current) – [Useful Resources] Normal User
@@ Line 1: / Line 1: @@
+====== Machine Learning ======
+===== Useful Resources =====
+http://www-bcf.usc.edu/~gareth/ISL/\\
+https://www.r-project.org/about.html\\
+https://www.rstudio.com/products/rstudio/\\
+https://www.kaggle.com/c/digit-recognizer\\
+[[https://www.guru99.com/tensorflow-tutorial.html|TensorFlow and general SW learning website]]
+References
+[1] C.J. Wu et al., Machine Learning at Facebook: Understanding Inference at the Edge [From Facebook]\\
+[2] N.P. Jouppi et. al., In Datacenter Performance Analysis of a Tensor Processing Unit [From Google]\\
+[3] Vivien Sze et. al., Efficient Processing of Deep Neural Networks: A tutorial and survey [From MIT]\\
+[4] Amr Suleiman et. al., Navion: A 2mW Fully Integrated Real-Time Visual-Inertial Odometry Accelerator for Autonomous Navigation of Nano Drones [From MIT]
+====== Handwriting Learning Code Example ======
+===== Example 1 =====
+<code>
+library(h2o)
+h2o.init(nthreads = 6)
+h2o.removeAll()
+traindat=read.csv("train.csv")
+traindat[,1] = as.factor(traindat[,1])
+traindat[,2:785] = ifelse(traindat[,2:785]>20, 1, 0)
+par(mfrow = c(10,10), mar = c(0,0,0,0))
+for (i in 1:100) {
+  y = as.matrix(traindat[i,2:785])
+  dim(y) = c(28,28)
+  image(y[,28:1], col = gray(1:0), axes = FALSE)
+  text(0.2, 0, traindat[i,1], cex = 3, col = 2, pos = c(3,4))
+}
+train.h2o = as.h2o(traindat)
+nnmodel.h2o = h2o.deeplearning(
+  x = 2:785,
+  y = 1,
+  training_frame = train.h2o,
+  activation = "RectifierWithDropout",
+  input_dropout_ratio = 0.2,
+  balance_classes = TRUE,
+  hidden = c(1024,1024,1024),
+  l1 = 1e-5,
+  classification_stop = 0.001,
+  epochs = 100
+)
+testdat = read.csv("test.csv")
+testdat = ifelse(testdat>20, 1, 0)
+test.h2o = as.h2o(testdat)
+pred.h2o = h2o.predict(nnmodel.h2o, newdata = test.h2o)
+pred = as.data.frame(pred.h2o)
+par(mfrow = c(10,10), mar = c(0,0,0,0))
+for (i in 1:100) {
+  y = as.matrix(testdat[i,])
+  dim(y) = c(28,28)
+  image(y[,28:1],col = gray(255:0/255), axes = FALSE)
+  text(0.2, 0, pred[i,1], cex = 3, col = 2, pos = c(3,4))
+}
+</code>
+===== Example 2 =====
+<code>
+library(h2o)
+h2o.init(nthreads = 6)
+h2o.removeAll()
+train.h2o = h2o.importFile("train.csv")
+train.h2o[,1] = as.factor(train.h2o[,1])
+nnmodel.h2o = h2o.deeplearning(
+  x = 2:785,
+  y = 1,
+  training_frame = train.h2o,
+  activation = "RectifierWithDropout",
+  input_dropout_ratio = 0.2,
+  balance_classes = TRUE,
+  hidden = c(1024,1024,1024),
+  l1 = 1e-5,
+  classification_stop = 0.001,
+  epochs = 100
+)
+test.h2o = h2o.importFile("test.csv")
+pred.h2o = h2o.predict(nnmodel.h2o, newdata = test.h2o)
+testdat = as.data.frame(test.h2o)
+pred = as.data.frame(pred.h2o)
+par(mfrow = c(10,10), mar = c(0,0,0,0))
+for (i in 1:100) {
+  y = as.matrix(testdat[i,])
+  dim(y) = c(28,28)
+  image(y[,28:1],col = gray(255:0/255), axes = FALSE)
+  text(0.2, 0, pred[i,1], cex = 3, col = 2, pos = c(3,4))
+}
+</code>