1,720,970 research outputs found
IBM/ibm-materials-notebook: v0.1.9
No full text<p>Further updates to CMDL syntax an usability</p>
IBM/ibm-materials-notebook: v0.1.9
No full text<p>Continued updates to streamlining CMDL syntax and useability.</p>
IBM/regression-transformer: paper-reproduction
No full textDevelopmental codebase to facilitate reproduction of experiments shown in paper.
Not recommended to build upon for future research. This code version depends on an oldish version of transformers and does not include many functionalities and features that are provided via GT4SD. Code for the GT4SD implementation can be found on the gt4sd branch of this rep
IBM/api-aware-cloud-migration: EuroSys Artifact
No full textAtlas, a hybrid cloud migration advisor learns how each user-facing API utilizes different components to offer migration recommendations with customizable performance, cost and availability trade-offs
IBM/simulai: 0.99.15
No full textSanity check for the loss function, which avoids the usage the wrong loss functions for a given problem. The checker will interrupt the process when the choice is not proper and indicate the correct one :
Exception: The loss function used for this case (vaermse) is not the recommended (['rmse', 'wrmse']). Please, redefine it.
The automatically configured Variational Autoencoders (VAE) has the option shallow, which allows to define shallow bottleneck encoder-decoders (it means, simple linear operators) for the CNN-VAEs:
autoencoder = AutoencoderVariational(
input_dim=(None, 1, 32, 32),
latent_dim=l_d,
activation="relu",
architecture="cnn",
shallow=True,
name="KDV_VAE",
case="2d",
devices="gpu",
)
Improvemments were done in order to allow the usage of simulai.metrics.MinMaxEvaluation for evaluating minimum and maximum values of HDF5 objects in a lazzy way, which can be useful for normalization techniques.
A bug which was impeding the instantiation of automatically generated MLP VAEs was solved.
Updates in the documentation
IBM/SAX: open research europe
No full text<p>This is for the release of conbots related code, available at: https://github.com/IBM/SAX/tree/conbots-papers/Conbots/ICMI22</p>
IBM/simulai: 0.99.13
No full textCorrecting import errors from the previous releases.
Updating documentation
IBM/simulai: Initial public beta release
No full textThis is the very first public release of SimulAI. As we move to stabilize experimental features and add documentation, we will progressively converge to a major version bump, moving from beta to production stage. SimulAI is also available for installation from PyPI:
$ pip install simulai-toolki
IBM/SAX: open research europe paper
No full text<p>This is a release of code snippet available at: https://github.com/IBM/SAX/tree/main/Conbots/ICMI22</p>
- …
