NAME

RAMINENI,PARDHA SARADHI

CLASS ID

32

SOURCE CODE

https://umkc.box.com/s/10nrlk6216fncengv7qxbbw5o9vgc3hs

In class programming:

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

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

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 what happens

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

ANSWER))

In this ICP we worked on plotting Loss & Accuracy curve, updating the dense layers and observing the changes in loss & accuracy with different activation methods.

For Task 2 Plotting Digit from Test Data & Predicting using Model

For task3 We added few more hidden layers and changed the activation method to tanh, Sigmoid and calulated the accuracy and loss for the model.

The loss value changed to 0.1011 from 0.152 and accuracy remained same. For task4 Now we removed the scaling operation on the data and evaluated the model.

The Accuracy dropped to 97.6% from 97.8%.