alex/copycat
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Spell checks draft.tex, adds sources

Browse Source
This commit is contained in:
LSaldyt
2017-12-09 18:44:25 -07:00
parent be921108ab
commit 6a826966a1
3 changed files with 8 additions and 17 deletions
Download Patch File Download Diff File Expand all files Collapse all files

3
papers/Makefile
View File

@ -1,6 +1,7 @@
all: all:
draft make draft
make clean
draft: draft:
pdflatex draft.tex pdflatex draft.tex

13
papers/draft.tex
View File

@ -39,8 +39,7 @@ Based on this cross-comparison, [Result Summary].
\section{Introduction} \section{Introduction}
This paper stems from Melanie Mitchell's (1993) and Douglas Hofstadter's \& FARG's (1995) work on the copycat program. This paper stems from Melanie Mitchell's \cite{analogyasperception} and Douglas Hofstadter's \& FARG's \cite{fluidconcepts} work on the copycat program.
\cite{geb}
This project focuses on effectively simulating intelligent processes through increasingly distributed decision-making. This project focuses on effectively simulating intelligent processes through increasingly distributed decision-making.
In the process of evaluating the distributed nature of copycat, this paper also proposes a "Normal Science" framework. In the process of evaluating the distributed nature of copycat, this paper also proposes a "Normal Science" framework.
Copycat's behavior is based on the "Parallel Terraced Scan," a humanistic-inspired search algorithm. Copycat's behavior is based on the "Parallel Terraced Scan," a humanistic-inspired search algorithm.
@ -118,9 +117,9 @@ Then, desirability of answer distributions can be found as well, and the followi
Note that this is more similar to the behavior of a GPU than a CPU. Note that this is more similar to the behavior of a GPU than a CPU.
This model doesn't work when code has to synchronize to access global variables. This model doesn't work when code has to synchronize to access global variables.
Notably, however, functional distributed code is turing complete just like imperative centralized code is turing complete. Notably, however, functional distributed code is Turing complete just like imperative centralized code is Turing complete.
Especially given the speed of modern computers, functional code cannot do anything that imperative code can't. Especially given the speed of modern computers, functional code cannot do anything that imperative code can't.
However, working in a mental framework that models the functionality of the human brain may assist in actually modelling its processes. However, working in a mental framework that models the functionality of the human brain may assist in actually modeling its processes.
\subsubsection{Local Descriptions} \subsubsection{Local Descriptions}
@ -174,7 +173,7 @@ Then, desirability of answer distributions can be found as well, and the followi
The remainder of the section discusses different formulas and their advantages/disadvantages. The remainder of the section discusses different formulas and their advantages/disadvantages.
Also, as a general rule, changing these formulas causes copycat to produce statistically significantly different answer distributions. Also, as a general rule, changing these formulas causes copycat to produce statistically significantly different answer distributions.
The original formula for curving probabilties in copycat: The original formula for curving probabilities in copycat:
\lstinputlisting[language=Python]{resources/original.py} \lstinputlisting[language=Python]{resources/original.py}
An alternative that seems to improve performance on the "abd:abd::xyz:\_" problem: An alternative that seems to improve performance on the "abd:abd::xyz:\_" problem:
@ -223,7 +222,7 @@ Then, desirability of answer distributions can be found as well, and the followi
Then, breaker-fizzling, an independent temperature-related feature was removed from the original branch and another $\chi^2$ comparison was made. Then, breaker-fizzling, an independent temperature-related feature was removed from the original branch and another $\chi^2$ comparison was made.
The same process was repeated for non-probability temperature-based adjustments, and then for the copycat stopping decision. The same process was repeated for non-probability temperature-based adjustments, and then for the copycat stopping decision.
Then, a temperature-less branch of the repository was created and tested. Then, a temperature-less branch of the repository was created and tested.
Then, a branch of the repostory was created that removed probability adjustments, value adjustments, and fizzling, and made all other temperature-related operations use a dynamic temperature calculation. Then, a branch of the repository was created that removed probability adjustments, value adjustments, and fizzling, and made all other temperature-related operations use a dynamic temperature calculation.
All repository branches were then cross compared using a $\chi^2$ distribution test. All repository branches were then cross compared using a $\chi^2$ distribution test.
\subsection{$\chi^2$ Distribution Testing} \subsection{$\chi^2$ Distribution Testing}
@ -273,7 +272,7 @@ Then, desirability of answer distributions can be found as well, and the followi
\subsection{Prediction} \subsection{Prediction}
Even though imperative, serial, centralized code is turing complete just like functional, parallel, distributed code, I predict that the most progressive cognitive architectures of the future will be created using functional programming languages that run distributedly and in true parallel. Even though imperative, serial, centralized code is Turing complete just like functional, parallel, distributed code, I predict that the most progressive cognitive architectures of the future will be created using functional programming languages that run distributively and in true parallel.
I also predict that, eventually, distributed code will be run on hardware closer to the architecture of a GPU than of a CPU. I also predict that, eventually, distributed code will be run on hardware closer to the architecture of a GPU than of a CPU.
\printbibliography \printbibliography

9
papers/sources.bib
View File

@ -39,12 +39,3 @@
url = "http://www-cs-faculty.stanford.edu/~uno/abcde.html", url = "http://www-cs-faculty.stanford.edu/~uno/abcde.html",
keywords = "latex,knuth" keywords = "latex,knuth"
} }
@inbook{knuth-fa,
author = "Donald E. Knuth",
title = "Fundamental Algorithms",
publisher = "Addison-Wesley",
year = "1973",
chapter = "1.2",
keywords = "knuth,programming"
}