README.md

Deep Learning Palantir

Welcome to Deep Learning Palantir! This repository serves as a comprehensive collection of implementations of cutting-edge deep learning research papers. Whether you're a researcher, a practitioner, or an enthusiast, you'll find valuable resources and insights here.

Table of Contents

1. Introduction
2. Implemented Papers
3. Installation
4. Usage
5. Contributing
6. Acknowledgments

Introduction

The Deep Learning Palantir is inspired by the mythical seeing-stones of Middle-earth, providing a window into the latest advancements and methodologies in deep learning.

Implemented Papers

Below is a list of the deep learning research papers currently implemented in this repository:

• Few Shot Learnig

  • Prototypical Networks for few shot learning

• Transformers and attention

  • Attention is all you need

• CNN Backbones

  • Network in Network

  • Deep Residual Learnig for Image Recognition

  • Alex Net

  • Inception

  • ShuffleNet: An Extremely Efficient Convolutional Neural Network for Mobile Devices

  • Squeeze-and-Excitation Networks

  • MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications

  • MobileNetV2: Inverted Residuals and Linear Bottlenecks

  • Searching for MobileNetV3

  • Aggregated Residual Transformations for Deep Neural Networks

• Security:

  • Fast Gradient Sign Method

• Others

  • Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift

  • Feature Pyramid Networks for Object Detection

• ... (more to be added)

Installation

To get started, clone this repository and install the necessary dependencies:

git clone https://github.com/MohamedAlaaAli/DeepLearning-Palantir.git
cd deep-learning-palantir
pip install -r requirements.txt

Usage

Each implementation comes with a detailed Jupyter notebook demonstrating the steps and results. You can run the notebooks locally or use them as a reference for your projects.

jupyter notebook

Navigate to the notebook of interest and follow the instructions provided.

Contributing

We welcome contributions from the community! If you'd like to add a new paper implementation or improve existing ones, please follow these steps:

1. Fork the repository
2. Create a new branch (git checkout -b feature-branch)
3. Commit your changes (git commit -am 'Add new feature')
4. Push to the branch (git push origin feature-branch)
5. Create a new Pull Request

Acknowledgments

• J.R.R. Tolkien for the inspiration
• The deep learning community for continuous innovation and sharing of knowledge