https://github.com/ashwinpn/binary-classification-using-tensorflow

https://github.com/ashwinpn/binary-classification-using-tensorflow

deep-learning machine-learning multilayer-perceptron-network neural-network research statistical-analysis tensorflow tensorflow-examples tensorflow-experiments tensorflow-tutorials

Last synced: 13 days ago
JSON representation

• Host: GitHub
• URL: https://github.com/ashwinpn/binary-classification-using-tensorflow
• Owner: ashwinpn
• Created: 2020-02-29T01:00:13.000Z (over 4 years ago)
• Default Branch: master
• Last Pushed: 2020-02-29T03:01:46.000Z (over 4 years ago)
• Last Synced: 2024-10-11T08:42:08.146Z (about 1 month ago)
• Topics: deep-learning, machine-learning, multilayer-perceptron-network, neural-network, research, statistical-analysis, tensorflow, tensorflow-examples, tensorflow-experiments, tensorflow-tutorials
• Language: Jupyter Notebook
• Size: 14.6 KB
• Stars: 1
• Watchers: 2
• Forks: 1
• Open Issues: 0
• Metadata Files:
  • Readme: README.md

Awesome Lists containing this project

README

        
# Binary-Classification-using-Tensorflow

## Terminology

* Batch Size

  It is a hyperparameter which defines the number of samples the algorithm would work through before the internal parameters are updated.

* Epoch

  Number of epochs reflects the number of iterations the learning algorithm will undergo while working through the entire dataset.

* Perceptrons

  A machine learning construct usually used for classification tasks.

* Stochastic Gradient Descent

  When the batch_size = 1.

* Batch Gradient Descent

  When epoch = 1.

## Important considerations

* What should be the batch_size?

* Gradient descent vs stochastic gradient descent vs mini-batch gradient descent

## Common questions / issues

* Can we use np.mean instead of tf.reduce_mean? Is there a difference?

  The functionality is the same. However, tf.reduce_mean would work only within a session.

  

  Try this:

   

  ```

  c = np.array([[3.,4], [5.,6], [6.,7]])

  print(np.mean(c,1))

  Mean = tf.reduce_mean(c,1)

  with tf.Session() as sess:

  result = sess.run(Mean)

  print(result)

    

  ```

  Output:

  

  ```

  [ 3.5  5.5  6.5]

  [ 3.5  5.5  6.5]

  ```

  

## Results

  | Batch size |    Cost       | Accuracy|

  |------------|---------------|---------|

  |    32      |  0.079790163  | 0.97696 |

  |    100     |  0.073474707  | 0.98096 |

  

  

## Checklist

- [x] Classification (normally distributed clusters)

- [ ] Plot learning curve of model vaildation error against training time

- [ ] Tune batch size and learning rate