BayesOpt
CNTK
BayesOpt | CNTK | |
---|---|---|
1 | 1 | |
379 | 17,435 | |
- | 0.0% | |
1.1 | 0.0 | |
about 1 year ago | about 1 year ago | |
C++ | C++ | |
GNU Affero General Public License v3.0 | GNU General Public License v3.0 or later |
Stars - the number of stars that a project has on GitHub. Growth - month over month growth in stars.
Activity is a relative number indicating how actively a project is being developed. Recent commits have higher weight than older ones.
For example, an activity of 9.0 indicates that a project is amongst the top 10% of the most actively developed projects that we are tracking.
BayesOpt
-
The Evolutionary Computation Methods No One Should Use
Very interesting to see how wide spread this is. Stumbled upon it myself by accident when comparing my algorithm to a popular Bayesian optimisation algorithm (https://github.com/rmcantin/bayesopt). Almost every run it would sample the exact centre of the optimisation space. At first I was blown away by the performance until I found it suspicious that the precise optimum was found so often. Shifting the optimum away from the centre greatly reduced the algorithms performance.
CNTK
What are some alternatives?
Pytorch - Tensors and Dynamic neural networks in Python with strong GPU acceleration
Theano - Theano was a Python library that allows you to define, optimize, and evaluate mathematical expressions involving multi-dimensional arrays efficiently. It is being continued as PyTensor: www.github.com/pymc-devs/pytensor
tensorflow - An Open Source Machine Learning Framework for Everyone
Recast/Detour - Industry-standard navigation-mesh toolset for games
AI-Toolbox - A C++ framework for MDPs and POMDPs with Python bindings
Caffe - Caffe: a fast open framework for deep learning.
tiny-cnn - header only, dependency-free deep learning framework in C++14
Keras - Deep Learning for humans
btsk - Behavior Tree Starter Kit
scikit-learn - scikit-learn: machine learning in Python