neural-program-learning-project's Introduction
This program is attempt to adapt NPI (Neural Program Interpreter https://arxiv.org/pdf/1511.06279.pdf) implementation. The codes for the projects were adapted and made needed changes from the https://github.com/siddk/npi Package required: * Tensorflow * Tflearn * Numpy (if not already installed) * Pickle (if not already installed) You can use NPI_Country_Region.ipynb file and having all other files in the same folder except for the separate folder for model named as model. The cells header of the .ipynb file explains the use of the cell i.e. generate data, train, plot, evaluate or test. Alternatively, the files description can be as follows: create_program_data -> for creating the trace of the data train.py -> for training the data eval.py -> for testing or evaluating of the data on randomly picked data Note that to continue press โcโ while running the eval.py or testing/evaluation cell in .ipynb file. Example of trace from the cell would be: To find: Angola -------- Environment ---------- > Angola None > Nepal Asia > India Asia > China Asia > Peru North America > Brazil North America > UK Europe > Sudan Africa > Italy Europe > Sweden Europe > Mexico North America > USA North America > Angola Africa > Bangladesh Asia > Japan Asia > Egypt Africa > Nigeria Africa > None None ----------------------------------- Step: FIND, Arguments: [], Terminate: False Continue? c Step: INCREMENT, Arguments: [], Terminate: False Continue? c Step: INCREMENT, Arguments: [], Terminate: False Continue? c Step: INCREMENT, Arguments: [], Terminate: False Continue? c Step: INCREMENT, Arguments: [], Terminate: False Continue? c Step: INCREMENT, Arguments: [], Terminate: False Continue? c Step: INCREMENT, Arguments: [], Terminate: False Continue? c Step: INCREMENT, Arguments: [], Terminate: False Continue? c Step: INCREMENT, Arguments: [], Terminate: False Continue? c Step: INCREMENT, Arguments: [], Terminate: False Continue? c Step: INCREMENT, Arguments: [], Terminate: False Continue? c Step: INCREMENT, Arguments: [], Terminate: False Continue? c Step: INCREMENT, Arguments: [], Terminate: False Step: INCREMENT, Arguments: [], Terminate: True > Angola None > Nepal Asia > India Asia > China Asia > Peru North America > Brazil North America > UK Europe > Sudan Africa > Italy Europe > Sweden Europe > Mexico North America > USA North America > Angola Africa > Bangladesh Asia > Japan Asia > Egypt Africa > Nigeria Africa > None None Pointer at 12 -------- KB Environment ---------- > Angola None > Nepal Asia > India Asia > China Asia > Peru North America > Brazil North America > UK Europe > Sudan Africa > Italy Europe > Sweden Europe > Mexico North America > USA North America > Angola Africa > Bangladesh Asia > Japan Asia > Egypt Africa > Nigeria Africa > Africa None -------------------------------------------------------------------------- Model Output: Africa Correct Out : Africa Correct!
neural-program-learning-project's People
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
๐ 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. ๐๐๐
-
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 โค๏ธ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.