Chris Pollett > Students > Qiao

    Print View

    [Bio]

    [Blog]

    [CS 297 Proposal]

    [Del 1-Example Program]

    [Del 2-Introduction to Word Embedding]

    [Del 3-Data Preprocessing Program]

    [CS 297 Report_PDF]

    [CS 298 Proposal]

    [CS 298 Report PDF]

    [CS 298 Presentation PDF]

























Deliverable #1: An example program to run in TensorFlow.

This deliverable is an example program implemented in TensorFlow. This program uses softmax to recognize handwritten digits from the MNIST dataset. Besides a model is trained, TensorBoard is used for visualizing learning in this program. Prior to this implementation, I studied machine learning, neural network, Python, and Tensoflow.

The MNIST data is hosted on Yann LeCun's website, consists of 70,000 data points. Each data point consists of a label and an image of a handwritten digit. The label is a digit from 0 to 9. The image is 28 pixels by 28 pixels.

The softmax regression is commonly used in the multinomial regression. It is used to classify the handwritten digits.

References:

https://www.tensorflow.org/get_started/summaries_and_tensorboard

mnist_with_summaries.py

TensorBoard_Pic.zip