Projects
ArtificialEconomist.com Economoose.com YetiPredict.com
Notes
Logic, the natural numbers and computability Algebra Mathematical analysis Geometry
Classical mechanics Computer science and C Data structures and algorithms, and Lisp
Univariate probability Multivariate probability Univariate time series Multivariate time series Neural networks Statistics for specific domains
Physics Biology Engineering Electronics CPUs and the Von Neumann architecture
Unix Networks Single-node databases Graphics and audio Advanced computer architecture C++ and objects Java, garbage collection, process virtual machines and Kotlin System virtual machines and hardware emulation
Other C-family languages including Rust Other Lisp-family languages Functional languages Javascript and dynamic typing Python R Other languages
Windows Distributed computing Integrated Development Environments (IDEs)Reverse engineering
Decision and game theory General equilibrium Industrial organisation Money, banking and finance Microeconomics Macroeconomics Public choice History Epistemology and ontology Political science and philosophy

GitHub
LinkedIn

Neural networks

Supervised neural networks

Multi-layer perceptrons with sigmoids and backpropagation

Regularising neural networks

Normalising neural networks

Addressing gradient problems with the Rectified Linear Unit (ReLU)

Supervised neural networks cont.

Alternatives to backpropagation

Multi-class neural networks

Probabilistic neural networks

Pre-training neural networks

Convolutional layers for neural networks

Attention in neural networks

Generative neural networks

Autoencoders and Variational Autoencoders (VAE)

Restricted Boltzmann Machines (RBMs)

Self-organising maps

Generative neural networks

Estimating time series models

Recurrent neural networks

Recurrent Neural Network (RNN) encoders and decoders

Please select a chapter from the left.

Preface

This is a live document, and is full of gaps, mistakes, typos etc.