https://github.com/marko19907/ml-assignments
Machine Learning assignments, Machine Learning (IE500618) course, fall 2022.
https://github.com/marko19907/ml-assignments
cifar100 confusion-matrix distributed-machine-learning ensamble-methods jyputer-notebook machine-learning mnist-dataset multilayer-perceptron-network mushroom-classification python resnet-50 transfer-learning
Last synced: 24 days ago
JSON representation
Machine Learning assignments, Machine Learning (IE500618) course, fall 2022.
- Host: GitHub
- URL: https://github.com/marko19907/ml-assignments
- Owner: Marko19907
- Created: 2022-12-23T01:27:11.000Z (over 2 years ago)
- Default Branch: main
- Last Pushed: 2022-12-25T14:11:18.000Z (over 2 years ago)
- Last Synced: 2025-02-17T03:30:44.595Z (4 months ago)
- Topics: cifar100, confusion-matrix, distributed-machine-learning, ensamble-methods, jyputer-notebook, machine-learning, mnist-dataset, multilayer-perceptron-network, mushroom-classification, python, resnet-50, transfer-learning
- Language: Jupyter Notebook
- Homepage:
- Size: 289 KB
- Stars: 0
- Watchers: 1
- Forks: 0
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
Awesome Lists containing this project
README
# ML assignments
This repository contains the mandatory assignments from NTNU's "Machine Learning" (IE500618) course, fall 2022.
These assignments are mandatory but do not count towards the final grade in the subject.
## Contents
### [A1: Mushroom Classification](/A1-Mushroom-Classification)
* [x] Use the [UCI Mushroom data set](https://archive.ics.uci.edu/ml/datasets/mushroom)
* [x] Use a multilayer perceptron (MLP) classifier.
* [x] Clean and split the data into training, validation, and testing.
* [x] Present the results:
* [x] Plot the accuracy and loss.
* [x] Create a confusion matrix.### [A2: Distributed ML](/A2-Distributed-ML)
* [x] Simulate distributed machine learning using ensemble learning and compare it to a monolithic model.
* [x] Use the [MNIST data set](http://yann.lecun.com/exdb/mnist/)
* [x] Use a multilayer perceptron (MLP) classifier.
* [x] For the ensemble model:
* [x] Divide the data into 3 local sections, by digits: 0-2, 3-5, and 5-9.
* [x] Train each local model with only one of the sections.
* [x] Aggregate the 3 local models into a single ensemble model.
* [x] Present the results:
* [x] Plot the accuracy and loss.
* [x] Create a confusion matrix.
* [x] Make comparisons between the ensemble model and the monolithic model trained on the full dataset.### [A3: ResNet50 (transfer learning) with CIFAR100](/A3-ResNet50-(transfer-learning)-with-CIFAR100)
* [x] Use the ResNet50 model (transfer learning) for classification.
* [x] Use the [CIFAR-100 data set](https://www.cs.toronto.edu/~kriz/cifar.html)
* [x] Present the results:
* [x] Plot the accuracy and loss.
* [x] Create a confusion matrix.