User Tools

Site Tools


help:machine_learning:keras:rot

Differences

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

Link to this comparison view

help:machine_learning:keras:rot [2020/07/07 11:43]
gerhard ↷ Page moved from help:keras:rot to help:machine_learning:keras:rot
help:machine_learning:keras:rot [2020/07/07 11:43] (current)
gerhard ↷ Links adapted because of a move operation
Line 64: Line 64:
 ====== Example Multilayer Perceptron (MLP) in TensorFlow 2 ====== ====== Example Multilayer Perceptron (MLP) in TensorFlow 2 ======
  
-I have implemented the MLP Neural Network on the paper sheet break data set I have used in my previous articles (see [[extreme-rare-event-classification-using-autoencoders-in-keras-a565b386f098|Extreme Rare Event Classification using Autoencoders in Keras]]).+I have implemented the MLP Neural Network on the paper sheet break data set I have used in my previous articles (see [[help:keras:extreme-rare-event-classification-using-autoencoders-in-keras-a565b386f098|Extreme Rare Event Classification using Autoencoders in Keras]]).
  
 In this implementation, we will see examples for the elements we mentioned in the above rules-of-thumb. In this implementation, we will see examples for the elements we mentioned in the above rules-of-thumb.
Line 70: Line 70:
 The implementation is done in TensorFlow 2. I highly recommend migrating to TensorFlow 2, if not already. It has all the simplicity of Keras and significantly better computational efficiency. The implementation is done in TensorFlow 2. I highly recommend migrating to TensorFlow 2, if not already. It has all the simplicity of Keras and significantly better computational efficiency.
  
-Follow [[step-by-step-guide-to-install-tensorflow-2-0-67bc73e79b82|Step-by-Step Guide to Install Tensorflow 2]] for installation.+Follow [[help:keras:step-by-step-guide-to-install-tensorflow-2-0-67bc73e79b82|Step-by-Step Guide to Install Tensorflow 2]] for installation.
  
 In the following, I am not attempting to find the best model. The idea is to learn the implementations. No step is skipped to favor brevity. Instead, the steps are verbose to help the reader apply them directly. In the following, I am not attempting to find the best model. The idea is to learn the implementations. No step is skipped to favor brevity. Instead, the steps are verbose to help the reader apply them directly.
Line 439: Line 439:
   * If the model performance built with these rules-of-thumb does not have some minimal performance. Tuning further may not bring much improvement. Try another approach.   * If the model performance built with these rules-of-thumb does not have some minimal performance. Tuning further may not bring much improvement. Try another approach.
   * The article shows steps to implement the neural network in TensorFlow 2.   * The article shows steps to implement the neural network in TensorFlow 2.
-  * If you do not have TensorFlow 2, it is recommend to migrate to it as it brings the ease of (keras) implementation and high performance. See instructions here, [[step-by-step-guide-to-install-tensorflow-2-0-67bc73e79b82|Step-by-Step Guide to Install Tensorflow 2]].+  * If you do not have TensorFlow 2, it is recommend to migrate to it as it brings the ease of (keras) implementation and high performance. See instructions here, [[help:keras:step-by-step-guide-to-install-tensorflow-2-0-67bc73e79b82|Step-by-Step Guide to Install Tensorflow 2]].
  
  
help/machine_learning/keras/rot.txt · Last modified: 2020/07/07 11:43 by gerhard