Deep Learning with Neural Networks
Forty lessons from the perceptron to shipped transformers — backprop by hand, attention arithmetic, LLM training pipelines, PyTorch debugging, and a capstone you can defend line by line
Deep learning is not a bag of architectures — it is one chain of ideas: the chain rule makes layers learn, scale makes gradient descent survive depth, convolutions and attention are two answers to the same locality-and-relationship problem, and every training run since 2015 is the same loop with better bookkeeping.
This advanced course walks that chain end to end in forty lessons across ten modules. Modules 1–5 build the foundations and the vision/sequence/transformer stack with hand-computable arithmetic at every step. Modules 6–10 go where most courses stop: embeddings and contrastive learning, the full LLM training pipeline (data, tokenizer, scaling laws, post-training), decoding and diffusion, PyTorch as an engineering system (autograd, data loops, AMP, checkpointing), and finally the economics — compression, serving, honest evaluation, and a capstone design document with every number attached.
Who this is for: final-year students and engineers who can already train a model with a tutorial and now want to know exactly what happens inside it — and to pass the interviews that ask.
What you will be able to do
- Derive forward and backward passes with the chain rule
- and verify them against autograd
- Choose optimizers
- schedules
- initialization and regularization with quantified justificat
- Design CNN
- ResNet and transfer-learning pipelines using receptive-field
- Explain RNN/LSTM dynamics and hand-compute gate updates and
- Derive multi-head self-attention
- causal masking
- and the FLOPs/memory budgets of any transformer
- Build and evaluate embeddings with similarity
What is included
- 10 modules
- 40 lessons
- 15 hr of material
- Certificate on completion
₹99 ₹49