MNIST number dataseta set of 70,000 small images of digits handwrittenby high school students andemployees of the US Cen- sus Bureau. Each image is labeled with the digit it represents. This set has beenstudied so much that it is often called the”hello world”of Machine Learning: whenever people come up with a new classification algorithm they are curious to see how it will perform on MNIST, and anyone who learns Machine Learning tackles this dataset sooner or later.Instructions to explore this dataset are:1. Use Jupyter Notebook for interactive practice of Python and related Machine Learning packages.(5%)For installing jupyter notebook, could install anaconda first, as Anaconda is the most widely used Python distribution for data science and comes pre-loaded with all the most popular libraries andtools. virtual environment for each python projectFor installing libraries, creating a Jupyter notebook, refer to . (note always use kernel 3.X )Familiarize yourself with cells in jupyter notebook and practice mixing s and python coding.2. Always help.refer to book ‘hands-on machine learning with Scikit-Learn, Keras & TensorFlow’ for coding3. Specific tasks includedownload dataset(5%)explore the dataset and output information include(10%)how many imageshow many features and the range of feature values (e.g., histogram of the data value)how many categories/labels (discrete or continuous type)visualize randomly selected samples within each category (feel the variance of the data)visualize more data samples to see whether there are bad data samples need to be more data manipulation(10%)i. Explore PCA to reduce feature dimensions down to two dimensions and plot the resultStructureusing Matplotlib. You can use a scatterplot using 10 different colours to represent eachimage’s target class.Use t-SNE to reduce the MNIST dataset down to two dimensions and plot the result usingMatplotlib with scatterplot.Summary/conclude your discovery and insights.Computer ScienceEngineering & TechnologyPython Programming ITEC 203

Order your essay today and save 20% with the discount code ESSAYHELP