Advanced Programme

Deep Learning

Tensors to transformers, and making one cheap enough to ship.

Mode: Online, self-paced Duration: 18 Weeks, 126 Lessons Level: Python and some ML assumed
Read Week One Free Download the 499-page workbook

Why Deep Learning?

Neural networks are the default answer now. The valuable skill is knowing when they are the right one.

Almost every deep learning tutorial ends where the interesting part begins: the model trains, the loss goes down, and nothing is said about whether it beat a simpler method, whether the improvement survives a change of random seed, or what it costs to run. This course builds attention, transformers, GANs and diffusion from the components up, and then measures all of it, including the times the measurement was unflattering.

What Makes This Course Different?

This course publishes the results that did not go the way the textbook says. Every number below came from code run on a real machine, and is printed on the lesson page next to the technique it undercuts.

Quantisation made inference slower, not faster, and week 16 shows the timings
Pruning to 90 percent sparsity saved nothing without a sparse runtime
Distillation lost to the plain student across five alpha values and two seeds

What This Programme Delivers

✓ 126 day-by-day lessons across 18 weeks
✓ PyTorch as the main framework, with Keras written alongside and compared
✓ Attention and transformers built from scratch before any library is used
✓ GANs and diffusion measured on mode coverage, not shown as demos
✓ Quantisation, pruning, distillation and ONNX export, each timed
✓ 144 self-assessment questions with worked answers

Skills You Will Build

Technical Skills

  • Tensors, shapes, autograd and the five-step training loop
  • nn.Module architectures that are not a straight line
  • Momentum, Adam, schedules, clipping and batch size
  • Convolutional networks, ResNets and transfer learning
  • RNN, LSTM and GRU with padding handled properly
  • Scaled dot-product attention built by hand, then multi-head
  • Transformer encoders and decoders, and a character-level language model
  • Frozen features, fine-tuning and LoRA
  • Autoencoders, VAEs, GANs and DDPM diffusion
  • Contrastive self-supervision and linear probing
  • Quantisation, pruning, distillation, ONNX export and serving

Judgement

  • Recognising the shape of a failing training run from its curve
  • Telling a real improvement from seed variance
  • Knowing when transfer beats training from scratch
  • Choosing between frozen features, fine-tuning and LoRA on cost
  • Measuring generative models rather than eyeballing samples
  • Deciding when a smaller model is the correct answer

PyTorch First, Keras Alongside

Week 15 writes the same models twice and measures both, rather than arguing about which framework is better.

Aspect PyTorch (main framework) Keras (written alongside)
Training loop Written by hand, every step visible fit() handles it
Best for Understanding what the library does Getting a standard model running fast
Debugging Step into any tensor at any point Callbacks and inspection hooks
Custom layers Ordinary Python classes Subclassing with more ceremony
Research code What most papers ship Less common
Course role Weeks 1 to 14 and 16 to 18 Week 15, then used where it wins
Export ONNX, measured at four times faster SavedModel and TFLite

18-Week Learning Roadmap

View Detailed Week-by-Week Curriculum →

1

Foundations

Weeks 1 to 4. Tensors and automatic differentiation, nn.Module, optimisation and the failure shapes worth recognising, then regularisation.

2

Vision

Weeks 5 and 6. Convolution built up from one kernel to a full CIFAR-10 model, why depth stopped working, and the residual connection that fixed it.

3

Sequences

Week 7. Carrying state across a sequence with RNN, LSTM and GRU, padding done properly, and next-element prediction.

4

Transformers

Weeks 8 to 11. Attention from scratch, the full transformer, a character-level language model trained end to end, then fine-tuning and LoRA.

5

Generative and Self-Supervised

Weeks 12 to 14. Autoencoders and VAEs, GANs and diffusion measured against each other, and training an encoder with no labels at all.

6

Production and Capstone

Weeks 15 to 18. Keras compared directly, making a model cheap enough to ship, deployment and monitoring, then a capstone on untouched data.

What You Build Along The Way

CIFAR-10 From One Kernel Up

Convolution implemented by hand, then built into a network that actually classifies, with each architectural change measured separately.

PyTorch

A Transformer That Generates Text

Attention written from scratch, stacked into a decoder, and trained into a character-level language model with the baselines it has to beat.

From scratch

A Diffusion Sampler

A DDPM built end to end, then compared with a GAN on mode coverage. The diffusion model scored slightly lower, and the lesson keeps that result.

DDPM

An Exported Model, Timed

Quantisation, pruning and distillation each measured, then ONNX export, which is the one that actually ran four times faster.

ONNX

What The Capstone Asks Of You

Framing

Data the course has not touched

No CIFAR-10, no course dataset. Something you found, with the messiness that comes with it.

A stated non-neural baseline

Name what you have to beat before you start, and measure it.

Measurement

Seed variance before improvements

The capstone measures run-to-run spread first, at 0.0147, which turned out wider than five of six proposed improvements.

Cost as a reported number

Parameters, latency and memory alongside accuracy, because a model nobody can afford to run has not shipped.

Handover

A repository that reproduces

Installs, runs and reproduces your numbers on a machine that is not yours.

An honest write-up

What worked, what did not survive a second seed, and what you would try next.

Finish With

A convolutional network you built from the kernel up
A transformer language model you trained
A working diffusion sampler
An exported model with measured latency
A GitHub repository somebody else can run
Certificate of Completion

Where This Material Leads

The roles this course is written for:

Deep Learning Engineer
ML Engineer (Vision or NLP)
Research Engineer
Applied Scientist
MLOps Engineer

Written for people who will be asked why the model costs what it costs, not only whether it works.

Tools & Technologies

Core Tools

Python PyTorch NumPy

Also Covered

Keras TensorFlow ONNX Runtime torchvision Matplotlib GitHub

Every tool used is free and open source. Nothing on this course needs a paid licence.

Who This Is For

ML Practitioners

Comfortable with scikit-learn, moving to neural networks

Python Developers

Confident with classes and functions

Anyone Tired Of Black Boxes

Attention gets built by hand before it gets imported

Assumes Python and some machine learning. Start with the Machine Learning course if that is not you yet.

Certificate of Completion

Certificate of Completion in Deep Learning

Issued by EDUSHARK TRAINING once you finish the eighteen weeks and submit your capstone. It records what you built, not a grade.

Start With Tensors

Eighteen weeks from a single tensor to a model small enough to deploy.

Start: Any day. Week one is already published
Mode: Online, self-paced
Cost: Free to read in full
Start Week One