Psiz

This release has no feature additions. It merely bumps the TensorFlow and TensorFlow Probability requirements to the latest versions and updates the PsiZ codebase to be compatible with the latest versions.

This release adds some new features, but primarily focuses on reorganization of the core functionality of PsiZ into easy-to-use percept, proximity, and behavior modules.

Major Changes

* Source code related to architecting a "similarity function" has been reorganized to reflect the more general notion of a "proximity function" (which subsumes the notion of similarity, dissimilarity, kernel, and distance).
* Added new abstract `Proximity` layer which includes optional `activation` argument.
* Updated `Minkowski` and `MinkowskiStochastic` layer to inherit from `Proximity`
* Recommended approach is to use `activation` argument to modify output of Minkowski distance.
* Added experimental `CosineSimilarity` layer (which inherits from `Proximity`)
* Added experimental `InnerProduct` layer (which inherits from `Proximity`)
* Added experimental `GeneralizedInnerProduct` layer (which inherits from `Proximity`)
* `DistanceBased` layer is now deprecated in favor of using "activation" argument of `Proximity`
* Some functions have been re-homed as "activation" layers.
* Moved to `psiz.keras.layers.activations.ExponentialSimilarity`
* Moved to `psiz.keras.layers.activations.HeavyTailedSimilarity`
* Moved to `psiz.keras.layers.activations.InverseSimilarity`
* Moved to `psiz.keras.layers.activations.StudentsTSimilarity`
* `RankSimilarity` and `RateSimilarity` have been deprecated in favor of `SoftRank` and `Logistic`. In practice, this change means that users have increased responsibility for wiring up the layers, but model readability is now better. Examples, tutorials, and tests have all been updated to reflect these changes. To update code please see the examples.
* Cell-based layers have been moved to `experimental` until a stable API can be determined.

Minor Changes
* New `SoftRank` layer includes optional temperature parameter for controlling determinism.

* Add missing `name_scope` attribute in serialization of behavior layers.

A minor, mostly cosmetic release.

Breaking changes

* Removed deprecated objects.

Other changes

* Fixed missing autodoc generated API on readthedocs.

* Fix bug in psiz.data.Group where float type check generates an error in older NumPy versions.
* Add Begginer Tutorial - Part 2.
* Polish tutorials and docs.
* Add auto-generated API docs to readthedocs.

Summary
This release refocuses the package on essential modeling components. Some modules and functionality has been deprecated or reworked since that functionality is better provided by a third-party. This policy shift will smoothen the road to a stable 1.0 release.

Breaking Changes
* Sub-classed models
* Designing and maintaining specific models for a given behavior is brittle and has high maintenance costs (e.g., Issue 14).
* Moving forward, specific behaviors are implemented as Keras `Layer`.
* The existing `Rank` and `Rate` models are now deprecated, but their functionality is easily reproduced using Keras subclassed `Model` or Functional API. Check out the updated tutorial and examples to see how.
* Variational inference should be implemented using an abstract class `psiz.keras.models.StochasticModel`. It closely follows TF `Model`, but adds repeated sampling of the batch axis.
* Layers
* The `RankBehavior` and `RateBehavior` similarity layers have been deprecated and will be removed in the next minor version. Use `RankSimilarity` and `RateSimilarity` layers instead.
* Data management strategy
* Deprecated `psiz.trials` module, use `psiz.data` module instead.
* The `psiz.trials` module was unintuitive and was expensive to maintain.
* Much of the functionality provided by the `psiz.trials` module has been redistributed to existing functionality outside of `psiz`, such as the versatile `tf.data.Dataset` pipeline.
* Hosting of previously collected datasets will now be handled by a new python package `psiz-datasets`.
* Model restarter logic
* Custom restarter logic has been removed since the functionality can mostly be achieved by other packages such as Keras Tuner. The subclassed callbacks originally added as a hack have been removed since they are no longer necessary (Issue 27 ).
* Removed `psiz.keras.Restarter` class
* Removed `psiz.utils.FitTracker` class
* Removed `psiz.keras.callbacks.EarlyStoppingRe` class
* Removed `psiz.keras.callbacks.TensorBoardRe` class
* Gating layers
* Subnet gating has been replaced with a new set of classes to enable enhanced features.
* Combined `psiz.keras.layers.Gate` and `psiz.keras.layers.GateMulti` functionality into a new class `psiz.keras.layers.BraidGate` to denote networks that separate and later rejoin. This new class can handle inputs that are a single tensor or a list. The internals of the new class have been re-worked to be cleaner, easier to understand, and more powerful.
* Added `psiz.keras.layers.BranchGate` to allow branching networks (networks that separate and do not rejoin).
* Repurposed `Gate` as a new class of the same name that represents an abstract class that performs gating. Both `BranchGate` and `BraidGate` inherit from `Gate`.
* Added a `GateAdapter` class which allows dependency injection for formatting a dictionary of Tensor inputs as a list of Tensors.
* Simulating behavior
* Deprecated `psiz.agents` module. Agent simulation functionality can easily be achieved with custom code. For an example, see `psiz/examples/rank/mle_1g.py`.
* Utility functions
* The `pairwise_similarity` function has been deprecated since users should create their own model.
* Nomenclature
* Embedding layers that receive stimulus indices are now referred to as `percept` rather than `stimuli`. This better reflects cognitive modeling semantics.

Changes
* Bumped TensorFlow version requirement to >=2.10 < 2.11 (and TensorFlow Probability to 0.18.0).
* Necessary because `Model` `get_config` has since been updated to address some issues that impact common PsiZ use cases.
* Refactored examples to reflect updated PsiZ best practice.

New Features
* Added foundational support for sequence modeling.
* Added a new `psiz.data` module that provides lightweight classes that serve as an intuitive on-ramp for marshaling data into a model-consumable format.