kurochkinalexey / antisymmetricrnn Goto Github PK
View Code? Open in Web Editor NEWPython implementation of paper "AntisymmetricRNN: A Dynamical System View on Recurrent Neural Networks"
Python implementation of paper "AntisymmetricRNN: A Dynamical System View on Recurrent Neural Networks"
I am trying to use the basic AntisymmetricRNN model to be able to make time series predictions. I am trying to train my model on sine and cos values. I am trying to train my model on 2sin() and 2cos() and try to predict 1.7sin() when the window contains 1.7cos(). I added a function before it that converts the data into a sliding window format for time series forecasting.
So I changed the model to have 1 output class instead. Rest of the method is still the same. Also since i'm doing regression instead of classification, i have changed both the optimizer and the loss functions to Adam and MSELoss() respectively. However, as given in the code, outs gives me the probability of the classes for a particular sample.
So I understand according to the problem statement of the paper, this is what is desired, probability and the predicted class but if i want to predict values using it , what is it that i should do to adjust to my problem?
A declarative, efficient, and flexible JavaScript library for building user interfaces.
๐ Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
An Open Source Machine Learning Framework for Everyone
The Web framework for perfectionists with deadlines.
A PHP framework for web artisans
Bring data to life with SVG, Canvas and HTML. ๐๐๐
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
Some thing interesting about web. New door for the world.
A server is a program made to process requests and deliver data to clients.
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
Some thing interesting about visualization, use data art
Some thing interesting about game, make everyone happy.
We are working to build community through open source technology. NB: members must have two-factor auth.
Open source projects and samples from Microsoft.
Google โค๏ธ Open Source for everyone.
Alibaba Open Source for everyone
Data-Driven Documents codes.
China tencent open source team.