Deep Learning Projects

A curated collection of Deep Learning for Natural Language Processing (DLNLP) practical notebooks covering foundational NLP workflows, transformer-based models, prompt engineering, and modern LLM fine-tuning techniques.

Repository Overview

This repository contains Jupyter notebooks created as part of DLNLP practical coursework and hands-on exploration.

Included Notebooks

• 23AIML019_DLNLP_PR01.ipynb
• 23AIML019_DLNLP_PR10.ipynb
• 23AIML019_DLNLP_Practical_05.ipynb
• 23AIML019_DLNLP_Practical_3.ipynb
• 23AIML019_DLNLP_Practical_4_A.ipynb
• 23AIML019_DLNLP_Practical_4_B.ipynb
• 23AIML019_PRAC7_BERT_SSL_Practical (1).ipynb
• 23AIML019_PRAC7_BERT_SSL_Practical.ipynb
• 23AIML019_PRAC8_DLNLP_Core_Applications (1).ipynb
• 23AIML019_PRAC9_FineTuning_RLHF_Practical.ipynb
• BERT_SSL_Practical.ipynb
• DLNLP_Core_Applications (2).ipynb
• Effective_Prompting_Techniques_LLMs.ipynb

Topics Covered

• Text preprocessing and NLP pipelines
• Classical and deep learning NLP workflows
• BERT and self-supervised learning fundamentals
• Core DLNLP applications
• Prompt engineering techniques for LLMs
• Fine-tuning and RLHF practical concepts

Tech Stack

• Python 3.x
• Jupyter Notebook
• Common NLP/DL libraries (e.g., NumPy, Pandas, PyTorch/Transformers where applicable)

Getting Started

1. Clone the repository:

   git clone https://github.com/AnshGajera/Deep_Learning_Projects.git
   cd Deep_Learning_Projects

2. Create and activate a virtual environment (recommended).
3. Install dependencies used in your notebooks.
4. Launch Jupyter:

   jupyter notebook

Notes

• Some notebooks may require dataset files and additional package installations.
• File names are preserved as originally maintained for submission/practical tracking.

Author

Ansh Gajera