v0.9.2

• README enhancements
• Test of integration with File Exchange

v0.9.1

• Promoted PyTorch input code to an "example" and noted in README
• Moved installation instructions in README
• Moved fMRI to "other" example and removed from REAME
• Update LiveScript links

v0.9.0

• New workflow for TensorFlow model imports using tools in Matlab 2024a and later
• Demonstrates TensorFlow model imports in examples/other/tiny_ophys_inference_detailed.mlx

v0.8.1

• Small updates to the README
• Moved Datastore into the deepinterp namespace

v0.8.0

Organizing pretrained models, namespace, object implementation

• Pretrained model data is now in the pretrainedModel folder with a manifest as pretrained.json
• There is a namespace deepinterp to reduce potential name collisions with other toolboxes
• There is a new object implementation deepinterp.Net that allows interpolation now and will allow training soon.
• README file is reorganized and updated with more intuition about the algorithm.

v0.7.0

New features

• All demos available as links from README.md
• (Evaluation of normalization code (issue #15) )
• Small bug fix for Matlab Online for tiny_fMRI_inference (issue #40))

(Related to issue #16 )

v0.6.1

Fixes lack of precomputed answers in LiveScripts

v0.6.0

New features added to this release:

• Add direct downloads if the model files are available from the repository, and automatic downloads from Dropbox if not;
• Support the 'Open in MATLAB Online' workflow;
• Add a gateway livescript describing the various examples, with relative links to each.
• Add example that reads from a custom datastore
• Add an fMRI example

Other improvement:

• Remove the pop-up for adding the current working directory to the path.

v0.5.0

The first release of the MATLAB implementation of the DeepInterpolation general-purpose algorithm, used to denoise data by removing independent noise. This first release implements four key workflow examples, which are analogues of those from the reference implementation by the Allen instutute.

The examples, implemented as live scripts, are:

• Inference with ephys (optical physiology) data
• Inference with ophys (electrophysiology) data
• Training (and subsequent inference) with ephys data
• Training (and subsequent inference) with ophys data

Pre-trained networks and sample data are provided for each example