CUI-J / Machine-Learning

The Assignment 1 use pure Python to make predictions on a Air Quaility dataset. And the Assignment 2 based on CIFAR-10 dataset to implement cat and dog classification.

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

Machine Learning

Description

1. Regularisation for Linear Regression

In this assignment 1 , we looking at Ridge Regression and devising equations to optimise the objective function in Ridge Regression using two methods: a closed-form derivation and the update rules for stochastic gradient descent(SGD). I will then use those update rules for making predictions on a Air Quaility dataset.

2. Image classification and denoising

In this assignment 2, we will work on the CIFAR-10 dataset collected by Alex Krizhevsky, Vinod Nair, and Geoffrey Hinton from the University of Toronto. This dataset consists of 60000 32x32 colour images in 10 classes, with 6000 images per class. Each image is a 3-channel colour images of 32x32 pixels in size. There are 50000 training images and 10000 test images. We need to extract the pictures of cats and dogs from this dataset, and implement cat and dog classification.

Requirements

  • Jupyter Notebook
  • torch
  • sklearn
  • matplotlib
  • pods
  • zipfile
  • numpy
  • pandas

About

The Assignment 1 use pure Python to make predictions on a Air Quaility dataset. And the Assignment 2 based on CIFAR-10 dataset to implement cat and dog classification.

License:MIT License


Languages

Language:Jupyter Notebook 100.0%