Comments (4)
@Ohay-Angah Happy to hear that!
TPSR is building on the Transformer symbolic regression models. As these models are pretrained with millions of synthetic math functions, their power is in learning strong priors for this task (numeric-to-symbolic mapping) rather than the exact recovery of expressions. We noticed that in most cases predicted expressions with pretrained priors are close to true expressions after simplification or can generalize well to OOD data which signifies that the learned mathematical relations might be good approximation of true math relations. I hope this helps!
from tpsr.
The explanation helps, @parshinsh! I close this issue as it's been resolved!
from tpsr.
Hi @Ohay-Angah ,
Thank you for your interest in TPSR!
It seems like the AttributeError you're encountering is related to the signal.SIGALRM
attribute, which is not available on Windows platforms. If you're using Windows, this could be the cause of the problem. I couldn't replicate this error on the Unix-based system.
If the operating system is Windows, probably need to consider an alternative approach like multithreading
to create a similar effect. If you have access to a Unix-based system, try running the script there and let us know if the issue persists.
from tpsr.
It works on Unix-based systems like a charm. I can also run your code on Windows if commenting timeout(10)
property on the top of rescale_function
.
How do you understand the eval_results, 'cause running the symbolicregression skeleton seems to give me very different expression outcomes from the expectations?
python run.py --eval_mcts_on_pmlb True \
--pmlb_data_type feynman \
--target_noise 0.0 \
--lam 0.1 \
--horizon 200 \
--width 3 \
--num_beams 1 \
--rollout 3 \
--no_seq_cache False \
--no_prefix_cache True \
--max_input_points 200 \
--max_number_bags 10 \
--save_results True
I put a snippet of my current results here.
from tpsr.
Related Issues (2)
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 tpsr.