https://github.com/saman-nia/multiclass-classification

Deep Learning VS. Machine learning
https://github.com/saman-nia/multiclass-classification

classification deep-learning logistic-regression multi-class-classification multi-classify-with-tensorflow one-vs-rest scikit-learn tensorflow text-features

Last synced: about 1 month ago
JSON representation

Deep Learning VS. Machine learning

• Host: GitHub
• URL: https://github.com/saman-nia/multiclass-classification
• Owner: saman-nia
• Created: 2019-04-04T14:03:05.000Z (almost 6 years ago)
• Default Branch: master
• Last Pushed: 2019-04-20T18:21:57.000Z (almost 6 years ago)
• Last Synced: 2024-11-13T09:44:53.715Z (3 months ago)
• Topics: classification, deep-learning, logistic-regression, multi-class-classification, multi-classify-with-tensorflow, one-vs-rest, scikit-learn, tensorflow, text-features
• Language: Jupyter Notebook
• Homepage:
• Size: 2.94 MB
• Stars: 1
• Watchers: 2
• Forks: 0
• Open Issues: 0
• Metadata Files:
  • Readme: README.md

Awesome Lists containing this project

README

        
# Multi-Class Classification Features with Tensorflow an Scikit Learn Logistic Regression

# One vs. All: 

Here, you can see the performance of Deep Learning Vs. Machine Learning: 


![alt text](https://github.com/saman-nia/MultiClass-Classification/blob/master/data/Result.png) 


Here, you can see the performance of deep multi class classification: 


![alt text](https://github.com/saman-nia/Deep-Learning-MultiClass-Classification/blob/master/data/Image_Performance.png) 


Concept from: https://developers.google.com/machine-learning/crash-course/multi-class-neural-networks/one-vs-all 


One vs. all provides a way to leverage binary classification. Given a classification problem with N possible solutions, a one-vs.-all solution consists of N separate binary classifiers—one binary classifier for each possible outcome. During training, the model runs through a sequence of binary classifiers, training each to answer a separate classification question. For example, given a picture of a dog, five different recognizers might be trained, four seeing the image as a negative example (not a dog) and one seeing the image as a positive example (a dog). That is: 


Is this image an apple? No. 


Is this image a bear? No. 


Is this image candy? No. 


Is this image a dog? Yes. 


Is this image an egg? No. 


This approach is fairly reasonable when the total number of classes is small, but becomes increasingly inefficient as the number of classes rises. 


We can create a significantly more efficient one-vs.-all model with a deep neural network in which each output node represents a different class. The following figure suggests this approach: 


![alt text](https://developers.google.com/machine-learning/crash-course/images/OneVsAll.svg)