mirror of
https://github.com/saymrwulf/nvidia-AI.summerschool17-notebooks.git
synced 2026-11-16 08:48:39 +00:00
130 lines
2.8 KiB
TeX
130 lines
2.8 KiB
TeX
\documentclass{book}
|
|
\usepackage{graphicx}
|
|
\usepackage{appendix}
|
|
\usepackage{hyperref}
|
|
\usepackage{listings}
|
|
\usepackage{color}
|
|
\definecolor{mylight}{rgb}{0.9,0.9,0.9}
|
|
\definecolor{mygreen}{rgb}{0,0.6,0}
|
|
\definecolor{myblue}{rgb}{0,0,0.6}
|
|
\definecolor{mygray}{rgb}{0.6,0.6,0.6}
|
|
\definecolor{myviolet}{rgb}{0.6,0,0.6}
|
|
\lstset{ %
|
|
backgroundcolor=\color{mylight}, %
|
|
basicstyle=\ttfamily\fontsize{8pt}{8pt}, %
|
|
breakatwhitespace=false, %
|
|
breaklines=true, %
|
|
captionpos=b, %
|
|
commentstyle=\color{mygreen}, %
|
|
frame=single, %
|
|
keywordstyle=\color{myblue}, %
|
|
language=Python, %
|
|
numbers=left, %
|
|
numbersep=5pt, %
|
|
numberstyle=\tiny\color{mygray}, %
|
|
showspaces=false, %
|
|
tabsize=2, %
|
|
stringstyle=\color{myviolet} %
|
|
}
|
|
\parindent0ex
|
|
\parsep1ex
|
|
\parskip1ex
|
|
\title{Neural Computation and Self Organization \\ Lecture Notes}
|
|
\author{Thomas M. Breuel}
|
|
\begin{document}
|
|
\maketitle
|
|
\tableofcontents
|
|
|
|
\part{Neural Computation}
|
|
|
|
\chapter{Neurons}
|
|
\include{01-neurons}
|
|
|
|
\chapter{Neurophysiology}
|
|
\include{02-neurophysiology}
|
|
|
|
\chapter{Neuron Models}
|
|
\include{03-computational-models-of-neurons}
|
|
|
|
\chapter{Computational Universality}
|
|
\include{04-linear-threshold-units}
|
|
|
|
\chapter{Dynamics of Coupled Neurons}
|
|
\include{06-dynamics-of-networks}
|
|
|
|
\chapter{Associative Memories}
|
|
\include{08-associative-memories}
|
|
|
|
\part{Supervised Learning}
|
|
|
|
\chapter{Bayesian Decision Theory}
|
|
\include{12-bayesian-decision-theory}
|
|
\include{14-bayesian-parameter-estimation}
|
|
|
|
\chapter{Introduction to Perceptrons}
|
|
\include{09-linear-threshold-classification}
|
|
|
|
\chapter{Review: Bayesian Decision Theory}
|
|
\include{10-bayesian-decision-theory}
|
|
|
|
\chapter{Perceptron Learning}
|
|
\include{12-linear-threshold-classification}
|
|
\include{13-perceptrons}
|
|
|
|
\chapter{Linear Least Squares}
|
|
\include{15-linear-lsq}
|
|
|
|
\chapter{Logistic Regression}
|
|
\include{16-logistic-regression-grad}
|
|
|
|
\chapter{Multilayer Perceptrons}
|
|
\include{19-mlp-background}
|
|
\include{20-intro-mlp}
|
|
|
|
\chapter{Posterior Probabilities from Multilayer Perceptrons}
|
|
\include{25-mlp-posterior}
|
|
|
|
\chapter{Maximum Likelihood Estimation}
|
|
\include{90-bayesian-parameter-estimation}
|
|
\include{30-mlp-ml}
|
|
|
|
\chapter{Convolutional Neural Networks}
|
|
\include{50-simple-convnnet}
|
|
\include{51-simple-convnet-threshold}
|
|
\include{55-conv-multilayer2}
|
|
|
|
\part{Unsupervised Learning}
|
|
|
|
\chapter{Principal Component Analysis}
|
|
\include{30-pca}
|
|
\include{35-incremental-pca}
|
|
|
|
\chapter{$k$-Means and Expectation Maximization}
|
|
\include{40-kmeans-2d}
|
|
\include{41-em-example}
|
|
\include{42-kmeans-and-incremental}
|
|
\include{44-kmeans-again}
|
|
|
|
\chapter{Self-Organizing Maps}
|
|
\include{46-som-full}
|
|
|
|
\part{Additional Materials}
|
|
|
|
\appendix
|
|
|
|
\chapter{Deskewing}
|
|
\include{91-mnist-deskew}
|
|
|
|
\chapter{Outline and Review}
|
|
\include{92-outline-review}
|
|
|
|
%\chapter{Game Theory}
|
|
%\include{95-game-theory}
|
|
|
|
\chapter{Sequence Learning}
|
|
\include{98-sequence-learning-tasks}
|
|
|
|
\chapter{Sequence Modeling}
|
|
\include{97-sequence-modeling}
|
|
|
|
\end{document}
|