Natural Language Processing with Deep Learning

1. Background

1.1. Algebra and Statistics [Slides]
1.2. Tokenization and Embeddings [Slides]
1.3. Perceptron and Deep Neural Networks [Slides]
1.4. Convolutional Neural Networks [Slides]
1.5. Layers [Slides]

2. Recurrent Neural Networks and Language Models

2.1. Vanilla RNN [Slides]
2.2. Long Short-Term Memory [Slides]
2.3. Bidirectional Approach and Other Layers [Slides]

3. Transformers

3.1. Encoder-Decoder Architectures (Seq2Seq) [Slides]
3.2. Attention Mechanisms [Slides]
3.3. Transformer Architecture [Slides]
3.4. Vision Transformers [Slides]

4. Transformer-Based Language Models

4.1. Bidirectional Encoder Representation for Transformers [Slides]
4.2. Pre-Trained Language Models and Fine-Tuning [Slides]
4.3. Sentence Transformers [Slides]
4.4. Large Language Models (incl. Quantization) [Slides]
4.5. Small Language Models [Slides]
4.6. Evaluation Strategies [Slides]

5. Retrieval-Augmented Generation (RAG)

5.1. Vanilla RAG [Slides]
5.2. GraphRAG [Slides]
5.3. Other RAG Strategies (incl. Hyde) [Slides]

6. Advanced Topics

6.1. Graph Neural Networks [Slides]
6.2. Multimodal Learning [Slides]
6.3. Contrastive Learning [Slides]