Machine-Learning-Lab

Universität Hildesheim - Machine Learning Lab Implementation

1. Lab 01: Python warmup exercises which includes word count and image blurring problems. Next, implementation of linear regression using the exact form (Normal Equation).

2. Lab 02: Exploratory analysis on real world data using pandas and matplotlib, and then linear regression using Gaussian elimination technique.

3. Lab 03: Gradient descent on the Rosenbrock function, linear regression with the gradient descent as an optimization strategy and implementation of two steplength controlling algorithm including backtracking, bold driver and look ahead optimizer.

4. Lab 04: Dataset preprocessing, logistic regression with gradient descent and logistic regression with Netwon's algorithm

5. Lab 05: Backward search algorithm for variable selection, regularization for logistic regression and Hyperband algorithm for logistic regression.

6. Lab 06: Dataset preprocessing, generalized linear models with Scikit learn, higher order polynomial regression and implementation of coordinate descent.

7. Lab 07: Dataset preprocessing, dataset imputation with KNN, time series classification with various distance measures and accelerating K-Nearest Neighbour classifier with partial distances and local sensitive hashing.

8. Lab 08: Optical character recognition via neural networks and End-to-End self driving via convolutional neural networks using Pytorch.

9. Lab 09: Implementation of decision tree and ensemble of gradient boosted decision trees

10. Lab 10: Statistical analysis of datasets, implementation of basic matix factorization technique for recommender systems and implementation of Scikit learn matrix factorization for recommender systems.

11. Lab 11: Dataset preprocessing using NLTK, implementation of naive bayes classifier for text data and implementation of SVM classifier via Scikit learn.