Lab09

Lab 9

---

Project: ATNN_2024_Assignment_4.pdf

1. Noisy CIFAR
2. LLM-based Subject Tagging
3. Mu-SHROOM, the Multilingual Shared-task on Hallucinations

---

For self-study (all students):

• Annotated deep learning papers: https://github.com/labmlai/annotated_deep_learning_paper_implementations
• LSTM:
  • intro: https://www.analyticsvidhya.com/blog/2021/03/introduction-to-long-short-term-memory-lstm/
  • code: https://nn.labml.ai/lstm/index.html
• RNN vs GRU vs LSTM: https://medium.com/analytics-vidhya/rnn-vs-gru-vs-lstm-863b0b7b1573
• Multi-Headed Attention implementation from Attention Is All You Need.

Advanced (for students who want to learn more):

• LSTM paper: https://deeplearning.cs.cmu.edu/F23/document/readings/LSTM.pdf
• Attention Is All You Need: https://arxiv.org/abs/1706.03762
• Attention Is ALl You Need video: https://www.youtube.com/watch?v=iDulhoQ2pro

---

References:

• RNN tutorial: https://pytorch.org/tutorials/intermediate/char_rnn_classification_tutorial.html
• https://jalammar.github.io/illustrated-transformer/
• https://jalammar.github.io/visualizing-neural-machine-translation-mechanics-of-seq2seq-models-with-attention/