1 %% -*- mode: latex; mode: reftex; mode: flyspell; coding: utf-8; tex-command: "pdflatex.sh" -*-
3 %% Any copyright is dedicated to the Public Domain.
4 %% https://creativecommons.org/publicdomain/zero/1.0/
5 %% Written by Francois Fleuret <francois@fleuret.org>
7 \documentclass[11pt,a4paper,oneside]{article}
8 \usepackage[paperheight=15cm,paperwidth=8cm,top=2mm,bottom=15mm,right=2mm,left=2mm]{geometry}
9 %\usepackage[a4paper,top=2.5cm,bottom=2cm,left=2.5cm,right=2.5cm]{geometry}
10 \usepackage[utf8]{inputenc}
11 \usepackage{amsmath,amssymb,dsfont}
12 \usepackage[pdftex]{graphicx}
13 \usepackage[colorlinks=true,linkcolor=blue,urlcolor=blue,citecolor=blue]{hyperref}
16 \usetikzlibrary{arrows,arrows.meta,calc}
17 \usetikzlibrary{patterns,backgrounds}
18 \usetikzlibrary{positioning,fit}
19 \usetikzlibrary{shapes.geometric,shapes.multipart}
20 \usetikzlibrary{patterns.meta,decorations.pathreplacing,calligraphy}
21 \usetikzlibrary{tikzmark}
22 \usetikzlibrary{decorations.pathmorphing}
23 \usepackage[round]{natbib}
24 \usepackage[osf]{libertine}
25 \usepackage{microtype}
27 \usepackage{mleftright}
30 \setlist[itemize]{leftmargin=0pt,itemindent=1em,itemsep=2ex}
31 \setlist{nosep} % or \setlist{noitemsep} to leave space around whole list
33 \newcommand{\setmuskip}[2]{#1=#2\relax}
34 \setmuskip{\thinmuskip}{1.5mu} % by default it is equal to 3 mu
35 \setmuskip{\medmuskip}{2mu} % by default it is equal to 4 mu
36 \setmuskip{\thickmuskip}{3.5mu} % by default it is equal to 5 mu
38 \setlength{\parindent}{0cm}
39 \setlength{\parskip}{1ex}
40 %\renewcommand{\baselinestretch}{1.3}
41 %\setlength{\tabcolsep}{0pt}
42 %\renewcommand{\arraystretch}{1.0}
44 \def\argmax{\operatornamewithlimits{argmax}}
45 \def\argmin{\operatornamewithlimits{argmin}}
47 %%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
49 \def\given{\,\middle\vert\,}
50 \def\proba{\operatorname{P}}
51 \newcommand{\seq}{{S}}
52 \newcommand{\expect}{\mathds{E}}
53 \newcommand{\variance}{\mathds{V}}
54 \newcommand{\empexpect}{\hat{\mathds{E}}}
55 \newcommand{\mutinf}{\mathds{I}}
56 \newcommand{\empmutinf}{\hat{\mathds{I}}}
57 \newcommand{\entropy}{\mathds{H}}
58 \newcommand{\empentropy}{\hat{\mathds{H}}}
59 \newcommand{\ganG}{\mathbf{G}}
60 \newcommand{\ganD}{\mathbf{D}}
61 \newcommand{\ganF}{\mathbf{F}}
63 \newcommand{\dkl}{\mathds{D}_{\mathsf{KL}}}
64 \newcommand{\djs}{\mathds{D}_{\mathsf{JS}}}
66 \newcommand*{\vertbar}{\rule[-1ex]{0.5pt}{2.5ex}}
67 \newcommand*{\horzbar}{\rule[.5ex]{2.5ex}{0.5pt}}
69 \def\positionalencoding{\operatorname{pos-enc}}
70 \def\concat{\operatorname{concat}}
71 \def\crossentropy{\LL_{\operatorname{ce}}}
78 {\Large Self-Generated Culture}
86 \centerline{\color{red}(work in progress, to be updated)}
90 \centerline{\url{https://fleuret.org/public/culture/culture.pdf}}
94 \section{Introduction}
96 The hypothesis behind this experiment is that high-level abstract
97 thinking is fueled by social competition. A group of communicating
98 agents that try to demonstrate their cognitive superiority would end
99 up developing a rich and consistent culture.
101 The experiment is designed with a group of GPTs that alternatively
102 learn to solve quizzes and generate new ones.
104 A ``quiz'' is a triplet of the form $(A, d, B)$ where $A$ and $B$ are
105 two sequences and $d$ is a token indicating if the direction is
106 forward or backward. Given $(A, d)$, the challenge is to generate $B$.
108 The experiments starts with a set of quizzes, that is going to be
109 progressively enriched.
113 The initial set of quizzes consist of predicting the dynamics of a
114 very simple world: A $6 \times 8$ grid with three colored ``birds'' moving in
115 a straight line, possibly bouncing on the grid's borders. There are
116 ten different colors.
119 \includegraphics[scale=0.35]{pics/examples_train.png}
125 In each on these quizzes, $A$ is the left image serialized in
126 raster-scan order as a sequence of $6 \times 8 = 48$ tokens, $d$ is
127 either the token ``forward'' or the token ``backward'', and $B$ is the
128 right image, also serialized. The direction of prediction is chosen at
131 \section{Generating Quizzes}
133 Given a set of $N$ GPTs, we can generate new quizzes as follows:
134 Select one of the models, and use it to generate the $97$ tokens of a
137 Then with each one of the $N-1$ other models, predict $B$ from $(A,
138 d)$, and $A$ from $(B, d')$ where $d'$ is the direction token opposite
141 A quiz is validated if \textbf{all the other GPTs but one predict it
142 deterministically correctly in both directions.}
144 This criterion assures that the new quizzes are both solvable and
145 sophisticated, and incrementally complexify the culture. Imposing both
146 direction prevents the generation of quizzes which are not trivial
147 only because the prompt has been randomly degraded.
149 \section{Overall Process}
151 The overall process consists of training the GPTs from scratch by
152 iterating the following steps:
156 \item select the GPT with the lowest recorded test accuracy, train it through one epoch,
158 \item if its test accuracy gets above $97.5\%$, generate $1'000$ new
159 quizzes, add them to the training set, re-compute the accuracy of
166 This procedure results in the discovery of patterns which are not
167 present in the original quizzes:
172 \includegraphics[scale=0.35]{pics/4_birds_1.png}
173 \includegraphics[scale=0.35]{pics/5_birds_1.png}
175 \includegraphics[scale=0.35]{pics/6_birds_1.png}
178 \textbf{New bird shapes}
182 \includegraphics[scale=0.35]{pics/other_shapes_2.png}
183 \includegraphics[scale=0.35]{pics/other_shapes_3.png}
189 \includegraphics[scale=0.35]{pics/other_shapes_1.png}
190 \includegraphics[scale=0.35]{pics/occlusions_1.png}
195 The code is available at
199 \centerline{\url{https://fleuret.org/git/culture}}
201 The experiments are done with a GTX 4090.
203 The GPT used has 37M parameters and the following structure:
207 \texttt{dim\_model} & 512 \\
208 \texttt{dim\_keys} & 64 \\
209 \texttt{dim\_hidden} & 2048 \\
210 \texttt{nb\_heads} & 8 \\
211 \texttt{nb\_blocks} & 12
215 Adam, $\eta = 1e-4$, no scheduling.
217 There are $N_{\text{train}}=250'000$ original quizzes for training and
218 $N_{\text{test}} = 10'000$ for test.
220 At each epoch, for both train and test samples, we mix original
221 quizzes and the generated ones.
223 For training for instance, if there are less than $N_{\text{train}}/2$
224 new quizzes, we take all of them, otherwise we sample
225 $N_{\text{train}}/2$ of them without replacement, and then we sample
226 without replacement enough original quizzes to get $N_{\text{train}}$
229 We proceed similarly to get $N_{\text{test}}$ samples for test.