YouTube Series
PyTorch Series
A practical PyTorch series covering fundamental concepts and real-world machine learning workflows. Learn how to build, train, and deploy machine learning models using PyTorch and modern ML engineering tools.
PyTorch Fundamentals
Build a strong foundation in PyTorch by learning how to install it, work with tensors, define models, initialize parameters, and manage model state.
Training Fundamentals
Learn the core components of a PyTorch training workflow, including batches, epochs, optimizers, DataLoaders, gradients, custom loss functions, and training and evaluation loops.
ML Engineering & MLOps
Move from model development to production by exploring experiment tracking, pipeline orchestration, containerized inference, cloud deployment, and Kubernetes-based ML workloads.
Neural Network Fundamentals
Explore fundamental neural network components and architectures, from activation functions such as Softmax and ReLU to recurrent neural networks and normalization.
RNN & Gradient
Understand how gradients behave in recurrent neural networks and explore the concepts behind gradient propagation through sequential architectures.