Machine Learning
◫ Deep Learning
Layered, trainable function approximators — how neural networks are built and trained via backpropagation.
4 concepts— start at the top and work your way down
- 1→
Neural Networks
Layers of simple weighted-sum-plus-nonlinearity units, chained together and trained by backpropagation — the architecture behind modern deep learning.
- 2→
Gradient Descent
An iterative optimisation algorithm that repeatedly moves in the direction of the negative gradient to find a local minimum of a loss function.
- 3→
Chain Rule
How to differentiate composite functions — the most frequently used rule in calculus, underpinning substitution in integration.
- 4→
Logistic Regression
Modelling the probability of a binary outcome using the sigmoid function — fitting by maximum likelihood or gradient descent.