Though it is more convenient to conduct TensorFlow framework in python, we also talked about how to apply Tensorflow in R here:https://charleshsliao.wordpress.com/tag/tensorflow/ We will talk about how to apply Recurrent neural network in TensorFlow on both of python and R. RNN might not be the best algorithm to deal with MNIST but this can be… Continue reading RNN in TensorFlow in Python&R, with MNIST
We know several essential recommenders' methods. If we want to recommend ourselves a book, we can do it 1. Based on our own exp 2. Based on our friends friends exp 3. Based on the catalog of the library 4. Based on the search engine's result We already talked a little about the first method… Continue reading Recommenders in R, Comparing Multiple Algorithms
We built the simple model in last article, we will build a more sophisticated model with TensorFlow. This article is more like practicing and the code comes from: https://rstudio.github.io/tensorflow/index.html The result is not optimal and we can add more iterations to improve the final accuracy.
This is an example for MNIST Neural Network model(DNN) with TensorFlow in R with API. Most of the code comes from https://rstudio.github.io/tensorflow/index.html
AWS provides us with approachable GPU based cloud computing capability with minimal cost. We will talk about the steps to take advantage of AWS EC2 to build GPU computing for our model training in R. 1. Register AWS account... 2. Find EC2 service 3. Click "launch instance" and go for this one labeled Free tier… Continue reading Train Deep Learning Model with R Studio in AWS EC2
Keras is a library of tensorflow, and they are both developed under python. We can approach to both of the libraries in R after we install the according packages. Of course, we need to install tensorflow and keras at first with terminal (I am using a MAC), and they can function best with python 2.7.… Continue reading CNN/DNN of KeRas in R, Backend Tensorflow, for MNIST
Please read this first: https://charleshsliao.wordpress.com/2017/04/14/identify-arguments-of-h2o-deep-learning-model-with-tuned-auto-encoder-in-r-with-mnist/ Following the auto encoder results of arguments in last article and a sample FNN model at the end of that article, we can build a full FNN model for MNIST.
Auto-encode can be trained to learn the deep or hidden features of data. These hidden features may be used on their own, such as to better understand the structure of data, or for other applications. Two common applications of auto-encoders and unsupervised learning are to identify anomalous data (for example, outlier detection, financial fraud) and… Continue reading Identify Arguments of H2O Deep Learning Model with Tuned Auto Encoder in R with MNIST
We use a deep auto-encoder model to analyze actimetry data from smartphones. You can find the data here: http://archive.ics.uci.edu/ml/datasets/Human+Activity+Recognition+Using+Smartphones. Why should we do this? An auto encoder can be useful for excluding unknown or unusual activities, rather than incorrectly classifying them, by examining whether any of the activities tend to have more or less anomalous values. We… Continue reading Auto Encoder to Detect Anomalous Cases in Smartphone Actimetry Data
Auto-encoders are trained to reproduce or predict the inputs--the hidden layers and neurons are not maps between an input and some other outcome, but are self (auto)-encoding. We can use auto encoders to conduct dimensions reduction, lift overfitting and so on. We will talk about it in the next article. h2o package of R provides… Continue reading Auto encoder with R, MNIST in Deep Learning