ICP_Deep Learning 2 - PallaviArikatla/Python GitHub Wiki

INTRODUCTION: To work on neural networks,activation functions,Loss Functions and Minst datset of keras.

IMPLEMENTATION:

Question 1: Using the history object in the source code, plot the loss and accuracy for both training data and validation data.

  • Import all the necessary libraries to perform related operations.

  • Read the given data and split it to train and test.

  • Have to process the data and convert it to numeric form i.e., to 0 and 1.

  • Plot the image for trained data.

  • Encode the data and calculate loss and accuracy metrics.

  • Now the outputs will be as follows.

  • Output for trained data:

  • Outputs for loss and accuracy:

CODE:

Loss and Accuracy:

PLOTS:

Loss:

Accuracy:

Question 2: plot one of the images in the test data, and then do inferencing to check what is the prediction of the model on that single image in the test data.

  • Take the index value from the trained data followed by finding out predictions and plot the image as follows.

Question 3: We had used 2 hidden layers and Relu activation. Try to change the number of hidden layer and the activation to tanh or sigmoid and see the changes.

  • Create a network by adding additional given layers with activation tanh and sigmoid.
  • Train the model and make observations.

Loss Plot:

Accuracy Plot:

Question 4: Run the same code without scaling the images, how the accuracy changes.

  • Remove the scaling and train the model.
  • Infer the changes.

OUTPUT:

Inference:

After removal of scaling value of accuracy has decreased and loss value got increased.