Fundamentals of deep learning applied in Python: artificial neural networks, loss functions, gradient descent, backpropagation, and training-optimization techniques; canonical architectures (multi-layer perceptrons, CNNs, RNNs, LSTMs/GRUs, attention, and transformers) implemented in PyTorch; exposure to pre-trained large language models and other foundation models, few-shot learning, and reasoning, culminating in a final project.

Level

grad

Department

CDS

Credits

4