aehabV/Building-Gradient-Descent-Methods-from-Scratch aehabV/Building-Gradient-Descent-Methods-from-Scratch

  • Stars
    star
    1
  • Language
    Jupyter Notebook
  • License
    Other
  • Created over 1 year ago
  • Updated over 1 year ago
Twitter logo Share LinkedIn logo Share Facebook logo Share
aehabV/Building-Gradient-Descent-Methods-from-Scratch
github

aehabV

Reviews

There are no reviews yet. Be the first to send feedback to the community and the maintainers!

Repository Details

Implemented optimization algorithms, including Momentum, AdaGrad, RMSProp, and Adam, from scratch using only NumPy in Python. Implemented the Broyden-Fletcher-Goldfarb-Shanno (BFGS) optimizer and conducted a comparative analysis of its results with those obtained using Adam.

More Repositories

1

AirlineDW

Data Vault model for analyzing the flight activity and reservation processes of a major airline company. Provides SQL scripts, queries, and reports for gaining insights into business operations and improving performance.
1
star
2

Face-Generation-using-GANs

The CelebA dataset was used to train a DCGAN (Deep Convolutional Generative Adversarial Network). The project was broken down into a series of tasks, from loading in data to defining and training adversarial networks. The trained network generated new images of faces that seemed to be fairly realistic with reduced noise
Jupyter Notebook
1
star
3

Paint-Brush-Applet

Paint Brush is an Applet-based drawing app that uses OOP design. It enables users to draw basic shapes with different colors and line strokes, and includes a Clear All button. The app also supports saving and loading drawings as images, making it a useful tool for sharing and archiving artwork.
Java
1
star
4

Indeed-fake-job-posting-prediction

A machine learning model is built using PySpark's MLlib library to automatically flag suspicious job postings on Indeed.com. The dataset includes 18,000 job descriptions, out of which about 800 are fake.
Jupyter Notebook
1
star