Skip to content

This is a repository collecting my implementation of different tasks during my learning at UCLA, including but not limited to Machine Learning, Deep Learning, Reinforcement Learning.

Notifications You must be signed in to change notification settings

8Dis-like/UCLALearning

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

49 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

UCLALearning

This is a repository collecting my implementation of different tasks during my learning at UCLA, including but not limited to Machine Learning, Deep Learning, Reinforcement Learning.

Resources come from Machine Learning (CM146), Deep Learning (ECE C147/247), Reinforcement Learning (CS260R), Kinematics of Robots (MECH&AE C263A), and Data and Business Analysis (ENG213). Typically, they can be respectively well distinguished by file names.

However, for some projects or tasks situated at the intersection of many courses or topics, the relevant files are organized in a combined style spanning objective-oriented programming(OOP) and software engineering.

Some of the files are directly derived from platforms and communities such as Google Colab, PyCharm, Kaggle, Hugging Face, and, of course, GitHub.

Up till now, most of the files are classified as Python/Jupyter Notebook, which indicates a certain commonality and advantages. But resources aren't necessarily ubiquitous, while they indeed share different purposes.

Here are the brief introductions for datasets and packages mainly used in each course, respectively:

CM146: The dataset is adapted from the UCI Machine Learning Repository and it contains descriptions of hypothetical samples corresponding to 23 species of gilled mushrooms. Each mushroom is described in terms of physical characteristics, and the goal is to classify mushrooms as edible or poisonous.

C147/247A: The CIFAR-10 dataset is a foundational, widely used computer vision resource consisting of 60,000 color images (32 * 32 pixels) divided into 10 distinct classes (e.g., planes, cars, birds, cats, dogs). It is split into 50,000 training images and 10,000 testing images, often used for benchmarking machine learning algorithms and deep neural networks. 

C163A/C263A: Q8Bot

CS260R: OpenAI Gym, Metadrive

ENG213: Alpha Vantage is used to crawl public business data while some data is loaded by executing sql script.

About

This is a repository collecting my implementation of different tasks during my learning at UCLA, including but not limited to Machine Learning, Deep Learning, Reinforcement Learning.

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published