Technical Content

  Goal: To improve the average accuracy of ten classes in CIFAR10 classifier. Following link has detailed description of initial code: https://pytorch.org/tutorials/beginner/blitz/cifar10_tutorial.html#sphx-glr-beginner-blitz-cifar10-tutorial-py Background: W e will use the CIFAR10 dataset.   It has the classes: ‘airplane’, ‘automobile’, ‘bird’, ‘cat’, ‘deer’, ‘dog’, ‘frog’, ‘horse’, ‘ship’, ‘truck’. The images in CIFAR-10 are of size 3x32x32, i.e. 3-channel color images of 32x32 pixels in size. As part of initial code, following steps are done in order: Loading and normalizing the CIFAR10 training and test datasets using torchvision Defining a Convolutional Neural Network Defining a loss function Training the network on the training data Testing the network on the test data Basic Definitions: CNN are made up of neurons that have weight and biases. These are mainly applied to image networks. They consist of convolutional layers followed by activation filters and pooling layers...

   Problem:   Titanic - Machine Learning from Disaster Following link has detailed problem description: h ttps://www.kaggle.com/c/titanic/overview/description Observation:  Firstly I analyzed if there are missing values in different columns of train_data and test_data dataset by verifying the count of values present in each column. I could see that there are missing values in Age column of train_data and test_data dataset. Also, there are missing values in Fare column of test_data  dataset. Secondly, it can be noted that Cabin and Name columns are not being used for our calculation of passenger’s survival. Analysis: Based on the observations made I applied median value to missing values of these columns. I dropped these columns from our train_data and test_data. Also, using the boxplot, I could see that there are outliers in Age column of  train_data dataset. I removed the rows having outlier values in this dataset as well. Code: Outcome: Above analyzed cha...