Comments (4)
Going to extra lengths to indicate the final index, which it is having difficulty doing for the Rule 1 case especially.
TAPE 0░ 1░ 2░ 3█ 4░ 5░ 6░ 7█ 8█ 9█
PRINT 1/9 ░ ░ ░ █ ░ ░ ░ █ █ █
INDEX 1=9 DONE
PRINT 0/9 ░ █ ░ ░ ░ █ ░ ░ ░ ░
PRINT 1/9 ░ ░ ░ █ ░ ░ ░ █ █ █
It's tripping so hard that it's willing to write 1=9
before thinking to continue looping.
from turing.
I may cheat, and simply add Rule 1 to the training set, and whatever it is missing it should learn, but it would be more elegant for it to learn it without cheating.
I'm thinking it might be the proximity to the other PRINT
statement.
from turing.
It weirdly had just never seen a 1 != 9
comparison before, since no training examples had 9 steps, and for the Rule 1 case, it would for, whatever reason, think one is equal to nine.
Adding a single case for the number of steps we plan to test solved this, since it had seen 1/9 not complete. I will add two to be safe.
from turing.
The majority of the issues that needed extra labeling for the index seem to have been caused by it having no 10-step (9-max-index) examples. I added several and tightened up the tape syntax, which is like 5-10% lighter.
from turing.
Related Issues (3)
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from turing.