Skip to content

maancham/AI-Introduction

Repository files navigation

AI-Introduction

Table of contents

General info

Course projects related to Artificial intelligence course. All projects are coded using Python and popular libraries such as Pandas and Numpy.

Technologies

There are six projects within this repository which are as follows:

  • Computer Assignment 0: Introductory material on Python's most used AI libraries, such as Pandas and Numpy. Also, some plotting was carried out to understand the data better.

  • Computer Assignment 1: Search problems in AI and ways to tackle them. Uninformed search methods such as BFS, DFS, and IDS were implemented. Next, Informed search methods like heuristic solutions were tried, and their results were compared against each other.

  • Computer Assignment 2: Logical gate analysis with genetic algorithm. Defined chromosomes, mutation, crossover, and similar genetic-related algorithms to find the solution to a logic gate. About 1024 possible combinations were available, and time constraints were forced.

  • Computer Assignment 3: Text classification on persian user reviews using bag of words method.

  • Computer Assignment 4: Using machine learning techniques to predict housing prices. Became familiar with concepts such as handling outliers and missing values, encoding non-numeric values into machine-readable data, and choosing the best subset of features based on specific criteria. Lastly, some regression methods such as linear regression, KNN, Decision trees, Random forests, and Voting regressor were applied and compared against each other.

  • Computer Assignment 5: A two-part project, the first part was about coding an entire neural network from scratch and getting hands-on subjects such as activation functions, layers, and forwarding methods. Later, the resulting feed-forward neural network was used to tune multiple parameters such as learning rate, batch size, number of epochs, and the combination of layers. The second part of this final project was classifying images into three categories using Keras and Tensorflow Libraries.

Additional info

Course Prof was Dr.Moradi
Dr.Moradi profile: link