Ecosyste.ms: Awesome
An open API service indexing awesome lists of open source software.
https://github.com/shubhamprajapati7748/ai-reseach-papers
https://github.com/shubhamprajapati7748/ai-reseach-papers
Last synced: 4 days ago
JSON representation
- Host: GitHub
- URL: https://github.com/shubhamprajapati7748/ai-reseach-papers
- Owner: shubhamprajapati7748
- Created: 2024-12-15T15:35:27.000Z (about 1 month ago)
- Default Branch: main
- Last Pushed: 2024-12-21T17:13:28.000Z (about 1 month ago)
- Last Synced: 2024-12-21T18:23:24.074Z (about 1 month ago)
- Size: 4.5 MB
- Stars: 0
- Watchers: 1
- Forks: 0
- Open Issues: 0
-
Metadata Files:
- Readme: Readme.md
Awesome Lists containing this project
README
# AI Research Papers
This repository includes a collection of foundational and comprehensive AI research papers that have significantly contributed to the field of deep learning and natural language processing.
## Papers
1. **Attention Is All You Need** [View Paper](https://arxiv.org/pdf/1706.03762)
- Introduces the Transformer model, revolutionizing sequence transduction tasks by replacing traditional recurrent networks with self-attention mechanisms.
2. **Universal Language Model Fine-tuning for Text Classification (ULMFiT)** [View Paper](https://arxiv.org/pdf/1801.06146)
- Demonstrates the power of transfer learning for NLP tasks using a universal language model fine-tuning approach.
3. **A Comprehensive Survey on Applications of Transformers for Deep Learning Tasks** [View Paper](https://arxiv.org/pdf/2306.07303)
- A survey exploring the vast applications of Transformer architectures across various deep learning domains.
4. **Neural Machine Translation by Jointly Learning to Align and Translate** [View Paper](https://arxiv.org/pdf/1409.0473)
- Proposes an attention mechanism to align and translate sequences, paving the way for modern machine translation systems.
5. **Sequence to Sequence Learning with Neural Networks** [View Paper](https://arxiv.org/pdf/1409.3215)
- Introduces the sequence-to-sequence framework for machine translation, employing encoder-decoder architectures with RNNs.