https://github.com/ruoheng-du/applied-deep-learning

Applied Deep Learning | Fall 2024
https://github.com/ruoheng-du/applied-deep-learning

Last synced: about 1 month ago
JSON representation

Applied Deep Learning | Fall 2024

• Host: GitHub
• URL: https://github.com/ruoheng-du/applied-deep-learning
• Owner: ruoheng-du
• Created: 2024-10-01T02:18:33.000Z (8 months ago)
• Default Branch: main
• Last Pushed: 2025-02-08T07:04:08.000Z (3 months ago)
• Last Synced: 2025-02-08T08:17:55.742Z (3 months ago)
• Language: Jupyter Notebook
• Homepage:
• Size: 1.59 MB
• Stars: 0
• Watchers: 1
• Forks: 0
• Open Issues: 0
• Metadata Files:
  • Readme: README.md

Awesome Lists containing this project

README

        
# Applied Deep Learning | Fall 2024

This repository contains the deep learning model implementations done in Applied Deep Learning course during Fall 2024. The course emphasizes building, training, and fine-tuning deep learning models to address real-world challenges across various domains. The goal of the course is to have hands-on experience with deep learning architectures like CNNs, RNNs, GPT, and BERT, and understand advanced concepts such as attention mechanisms, LoRA, and language modeling. The repository includes the following notebooks:

1. **XOR_MLP.ipynb**  

   Building an MLP to solve the XOR problem, demonstrating the power of non-linear activation functions in deep learning.



2. **CBOW.ipynb**  

   Implementation of the Continuous Bag-of-Words (CBOW) model for learning word embeddings.



3. **MLP_Classification.ipynb**  

   Training a Multi-Layer Perceptron (MLP) for classification tasks on structured data.



4. **CNN_MNIST.ipynb**  

   Developing a Convolutional Neural Network (CNN) for image classification using the MNIST dataset.



5. **RNN_LM_Bigram_LM.ipynb**  

   Developing RNN-based language models and a bigram language model, for sequential text data.



6. **GPT_LM.ipynb**  

   Utilizing GPT models for language modeling tasks, focusing on generating coherent text.



7. **Gated_CNN_LM_Attention_RNN_LM.ipynb**  

   Exploration of gated CNNs and attention-based RNN language models for text generation and language modeling.



8. **GPT_Text_Classification.ipynb**  

   Applying GPT for text classification tasks and understanding its performance with large-scale pre-trained models.



9. **BERT_LORA_Text_Classification.ipynb**  

   Fine-tuning BERT with Low-Rank Adaptation (LoRA) for efficient and accurate text classification tasks.



Please feel free to email me at [email protected] for any more information.