Comments (3)
Hi @BooBSD! The best s-value depends on the task, and different values yields different effects. A larger s provides more fine-grained patterns, while a smaller s may in some cases give more robust patterns (https://www.ijcai.org/proceedings/2022/616). I usually start with trying out 2.5, 5.0, 10.0 and 20.0, to learn more about what works well for the data. If you print out the clauses, you can also look at how they grow with increasing s. Did that clarify the role of s?
from tmu.
@olegranmo Thank you.
I tried to get the best result on MNIST classification and found out that I got better accuracy with S > 10 (up to 20) if I have more than 2000 clauses. And If I have 2000 clauses or less, for example 500, I got better accuracy if I use S ~= 10.
Is there some formula relationship between number of clauses and S? Like best T param for MNIST is sqrt(clauses_num/2)
.
from tmu.
Interesting! Finding such relationships, empirically and formally, are important steps ahead in the TM research. Feel free to report any findings here :-)
from tmu.
Related Issues (20)
- ModuleNotFoundError: No module named 'tmu.tmulib' HOT 3
- ModuleNotFoundError: No module named 'tmu.tmulib' HOT 1
- Saving and loading trained classifiers HOT 3
- Return of class_sums also for the TMCoalescedClassifier HOT 1
- Support for integrated hyperparam search
- Request for a «set_TA_action” method HOT 5
- Issues with import and thresholding of FashionMNIST and KuzushijiMNIST datasets
- Request for maximum/minimum weight parameter
- TMComposite merge HOT 1
- Add support for training multiple TMs with common feedback signals.
- Compilation error on Mac HOT 3
- IMDbWordEmbeddingDemo.py not working HOT 1
- AutoEncoder has stopped learning
- Int type used as dataset index - does not work with large datasets
- Build error on Linux Ubuntu using pip3 install -e . HOT 1
- Type conversion of X to uint32 missing in fit HOT 5
- If all classes are '0' in Y, fit goes into infinite loop HOT 1
- get_encoded_data does not refresh with new data HOT 2
- ndarray is not C-contiguous
- Sparse not working HOT 1
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 tmu.