Deep Learning
Artificial Neural Networks
Build a neural network from scratch in NumPy, then again in PyTorch, and understand every number in it.
- Intermediate
- About 12 hours
- 4 modules
- 14 lessons
- Free
This course is not released yet. We publish courses one at a time, each one complete. The full syllabus is below.
What you will learn
- ArchitectureNetwork Architecture, Weights and Biases, Layers: Input, Hidden, Output and more
- TrainingThe Training Loop, Batches and Epochs, Initialising Weights and more
- RegularisationDropout, Weight Decay, Batch Normalisation and more
- ProjectProject: Neural Network From Scratch, Project: Handwritten Digit Recognition
Course syllabus
Not released yet · full syllabus below
- 1
Architecture
4 lessons- 1Network ArchitectureSoon
- 2Weights and BiasesSoon
- 3Layers: Input, Hidden, OutputSoon
- 4Counting ParametersSoon
- 2
Training
4 lessons- 5The Training LoopSoon
- 6Batches and EpochsSoon
- 7Initialising WeightsSoon
- 8Vanishing and Exploding GradientsSoon
- 3
Regularisation
4 lessons- 9DropoutSoon
- 10Weight DecaySoon
- 11Batch NormalisationSoon
- 12Early StoppingSoon
- 4
Project
2 lessons- 13Project: Neural Network From ScratchSoon
- 14Project: Handwritten Digit RecognitionSoon