Courses › Course05
Course05 · Deep Learning
Neural networks from first principles to transformers: build them, train them, debug them, and understand the hardware they run on.
42 days 42 written 42 complete
Days 197-203 · Neural Network Foundations 7/7 complete
- Day 197 The Perceptron complete
- Day 198 Activation Functions complete
- Day 199 Forward Propagation complete
- Day 200 Backpropagation complete
- Day 201 A Neural Network in Pure NumPy complete
- Day 202 PyTorch Tensors complete
- Day 203 Training MNIST from Scratch complete
Project: MNIST from Scratch — Implement a two-layer neural network in pure NumPy that reaches at least 95% accuracy on MNIST digits.
Days 204-210 · Training Deep Networks 7/7 complete
- Day 204 PyTorch: autograd and nn.Module complete
- Day 205 Datasets and DataLoaders complete
- Day 206 Optimizers: SGD to Adam complete
- Day 207 Learning Rate Schedules complete
- Day 208 Dropout, Batch Norm, and Regularization complete
- Day 209 Debugging Training Runs complete
- Day 210 A Disciplined Training Project complete
Project: Fashion-MNIST Classifier — Train a PyTorch classifier with a proper training loop, LR schedule, and regularization, beating a stated baseline.
Days 211-217 · Convolutional Networks and Vision 7/7 complete
- Day 211 Convolutions complete
- Day 212 CNN Architectures complete
- Day 213 Transfer Learning complete
- Day 214 Data Augmentation complete
- Day 215 Training a Vision Model End to End complete
- Day 216 Beyond Classification: Detection and Segmentation complete
- Day 217 Your Own Image Classifier complete
Project: Custom Image Classifier — Fine-tune a pretrained CNN on your own small image dataset with augmentation and an error-case gallery.
Days 218-224 · Sequences and Text 7/7 complete
- Day 218 Text Preprocessing and Tokenization complete
- Day 219 Word Embeddings complete
- Day 220 Recurrent Neural Networks complete
- Day 221 LSTMs and GRUs complete
- Day 222 Sequence-to-Sequence and Early Attention complete
- Day 223 Text Classification with Embeddings complete
- Day 224 A Sentiment Analysis Project complete
Project: Sentiment Analyzer — Build a review-sentiment model comparing bag-of-words, embeddings, and a small recurrent network.
Days 225-231 · Transformers 7/7 complete
- Day 225 “Attention Is All You Need” complete
- Day 226 Self-Attention, Step by Step complete
- Day 227 The Transformer Architecture complete
- Day 228 Encoder Models: BERT and Friends complete
- Day 229 Decoder Models: The GPT Family complete
- Day 230 Hugging Face Transformers in Practice complete
- Day 231 Fine-Tuning a Small Transformer complete
Project: Fine-Tuned Transformer — Fine-tune a small pretrained transformer on a text classification task with Hugging Face and report results honestly.
Days 232-238 · Training at Scale 7/7 complete
- Day 232 GPUs and AI Hardware complete
- Day 233 Mixed Precision and Performance complete
- Day 234 Distributed Training Concepts complete
- Day 235 Experiment Tracking complete
- Day 236 Quantization and Distillation complete
- Day 237 Scaling Laws and What They Bought Us complete
- Day 238 Section Project: Reproducing a Paper complete
Project: Section Project: Reproduce a Result — Reproduce a small published deep-learning result end to end, with experiment tracking and a reproduction report.