Skip to content

nmwiley808/csci167

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

142 Commits
 
 
 
 
 
 

Repository files navigation

CSCI 167 – Introduction to Deep Learning

California State University, Fresno
Student: Noah Wiley


Repository Overview

This repository contains my coursework, notebooks, experiments, and projects for CSCI 167 – Introduction to Deep Learning at Fresno State.

The purpose of this repository is to document my progress, experiments, and implementations throughout the semester, focusing on neural networks and modern deep learning architectures.


Course Description

CSCI 167 introduces the fundamental principles of machine learning and deep learning, including:

  • Machine learning fundamentals
  • Logistic regression
  • Neural networks and backpropagation
  • Vanishing / diminishing gradients
  • Optimization techniques and normalization
  • Batch normalization
  • Residual Networks (ResNets)
  • Convolutional Neural Networks (CNNs)
  • Recurrent Neural Networks (RNNs)
  • Experimental evaluation of deep learning models

The course emphasizes both theoretical understanding and hands-on experimentation using modern deep learning frameworks.


Repository Structure

CSCI167/
│
├── notebooks/                          # Programming Assignments (Jupyter Notebooks)
├── projects/                           # Course Projects
├── data/                               # Datasets used in assignments and projects
├── models/                             # Saved models and checkpoints
└── README.md                           # Repository Documentation
└── csci167 Textbook - Mastering PyTorch
└── csci167 Textbook - Understanding Deep Learning.pdf

Technologies & Tools

This repository may include:

  • Python
  • Jupyter Notebook
  • NumPy
  • Matplotlib / Seaborn
  • PyTorch and/or TensorFlow
  • scikit-learn

Skills Developed

Throughout this course, I am developing skills in:

  • Designing and training neural networks
  • Implementing forward and backward propagation
  • Applying optimization algorithms
  • Handling overfitting and regularization
  • Building CNN and RNN architectures
  • Model evaluation and performance tuning
  • Experimental analysis of deep learning systems

How to Run Notebooks

Most assignments are completed using Jupyter Notebook.

To run locally:

pip install -r requirements.txt
jupyter notebook

Some experiments may require GPU acceleration for training deep learning models.


Notes

  • This repository is for academic coursework.
  • Code is written for learning and experimentation.
  • Large datasets and trained model files may not be included due to size limitations.

Academic Integrity

All work in this repository is my own unless otherwise stated.
This repository is maintained for academic and portfolio documentation purposes only.

About

A coursework repository from undergrad Deep Learning course at Fresno State. It contains Python Jupyter notebooks covering core DL concepts like neural networks, CNNs, RNNs, backpropagation, and optimization techniques. Experiments and projects were built using PyTorch and TensorFlow with NumPy and scikit-learn.

Topics

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

 
 
 

Contributors