Transfer Learning with R | Artificial Intelligence & Deep Learning Applications

Provides a case study of applying transfer learning with CIFAR10 data for image recognition and classification using pre-trained ResNet50 network. Uses TensorFlow (by Google) as backend. R file: https://drive.google.com/open?id=1GF0DK6uSGbAzZthHY5pgi4qVgbjrbVsz Machine Learning videos: https://goo.gl/WHHqWP Reference: Rai BK, (2019). “Advanced Deep Learning with R: Become an expert at designing, building, and improving advanced neural network models using R”, Packt Publishing. Timestamp: 00:00 What is transfer learning? 03:26 Identify image with ResNet 50 08:18 CIFAR10 image dataset 11:23 Sample CIFAR10 image 12:03 Identify 2nd CIFAR10 image with pre-trained network 13:39 Preprocess data 17:00 Model with ResNet50 21:27 Compile model 22:15 Fit model 23:58 Model evaluation, prediction and confusion matrix Transfer learning is an important tool for Image Classification & Recognition. R is a free software environment for statistical computing and graphics, and is widely used by both academia and industry. R software works on both Windows and Mac-OS. It was ranked no. 1 in a KDnuggets poll on top languages for analytics, data mining, and data science. RStudio is a user friendly environment for R that has become popular.