Machine Learning Career Guide
0.1.0
Coding
Machine Learning Theory
Statistical Machine Learning
Deep Learning
The Fundamentals
The Big Picture
Gradient Descent
Backpropagation
Regularisation
Advanced Topics
Towards Theoretical Understanding of Representation Learning
Questions
Reinforcement Learning
Machine Learning Systems
Applied Machine Learning
Product System Design
General Skills
Non-Research Topics
Machine Learning Career Guide
Docs
»
Machine Learning Theory
»
Deep Learning
»
The Fundamentals
View page source
The Fundamentals
ΒΆ
The Big Picture
Probabilistic Framework
Defining the Probabilities
Usage of the Framework
Utilising the Observations
Gradient Descent
Nature of the Error Surface near Stationary Point
Gradient Descent
Batch Gradient Descent
Stochastic Gradient Descent
Mini-batch Gradient Descent
Convergence
Learning-Rate Schedule
Faster Covergence with Momentum
Adaptive Learning Rates
Managing Numerical Issues with Gradients
Weight & Bias Initialisation
Input normalisation
Weight normalisation
Resources
Backpropagation
Backprop Equations by Hand
Forward Pass
Backward Pass
AutoDiff
Regularisation
Inductive Bias
Weight Decay
Shrinkage
Consistent Reguraliser
Learning Curve
Early Stopping
Double Descent
Parameter Sharing
Hard-Sharing
Soft-Sharing
Residual Connections
Model Averaging