Version 2.5.0

This release contains many new features and fixes. It is the first release with a mature solution for Brain Dynamics Operator Customization on both CPU and GPU platforms.

New Features

1. Add synapse projection with Delta synapse models through brainpy.dyn.HalfProjDelta and brainpy.dyn.FullProjDelta.
2. Add brainpy.math.exprel, and change the code in the corresponding HH neuron models to improve numerical computation accuracy. These changes can significantly improve the numerical integration accuracy of HH-like models under x32 computation.
3. Add brainpy.reset_level() decorator so that the state resetting order can be customized by users.
4. Add brainpy.math.ein_rearrange, brainpy.math.ein_reduce, and brainpy.math.ein_repeat functions
5. Add brainpy.math.scan transformation.
6. Rebase all customized operators using Taichi JIT compiler. On the CPU platform, the speed performance can be boosted ten to hundred times. On the GPU platforms, the flexibility can be greatly improved.
7. Many bug fixes.
8. A new version of brainpylib>=0.2.4 has been released, supporting operator customization through the Taichi compiler. The supported backends include Linux, Windows, MacOS Intel, and MacOS M1 platforms. Tutorials please see https://brainpy.readthedocs.io/en/latest/tutorial_advanced/operator_custom_with_taichi.html

What's Changed

• [docs] Add taichi customized operators tutorial by @Routhleck in #545
• [docs] Optimize tutorial code in operator_custom_with_taichi.ipynb of documentations by @Routhleck in #546
• [running] fix multiprocessing bugs by @chaoming0625 in #547
• [docs] Fix typo in docs by @Routhleck in #549
• ⬆️ Bump conda-incubator/setup-miniconda from 2 to 3 by @dependabot in #551
• updates by @chaoming0625 in #550
• brainpy.math.defjvp and brainpy.math.XLACustomOp.defjvp by @chaoming0625 in #554
• ⬆️ Bump actions/setup-python from 4 to 5 by @dependabot in #555
• Fix brainpy.math.ifelse bugs by @chaoming0625 in #556
• [math & dyn] add brainpy.math.exprel, and change the code in the corresponding HH neuron models to improve numerical computation accuracy by @chaoming0625 in #557
• Update README by @chaoming0625 in #558
• [doc] add conductance neuron model tutorial by @chaoming0625 in #559
• Doc by @chaoming0625 in #560
• add brainpy.math.functional_vector_grad and brainpy.reset_level() decorator by @chaoming0625 in #561
• [math] change the internal implementation of surrogate function by @chaoming0625 in #562
• Math by @chaoming0625 in #563
• [doc] update citations by @chaoming0625 in #564
• add support for multi-class margin loss by @charlielam0615 in #566
• Support for Delta synapse projections by @chaoming0625 in #568
• [math] Add taichi customized operators(event csrmv, csrmv, jitconn event mv, jitconn mv) by @Routhleck in #553
• fix doc by @chaoming0625 in #571
• Fix default math parameter setting bug by @chaoming0625 in #572
• fix bugs in brainpy.math.random.truncated_normal by @chaoming0625 in #574
• [doc] fix doc by @chaoming0625 in #576
• fix bugs in truncated_normal; add TruncatedNormal init. by @charlielam0615 in #575
• [Dyn] Fix alpha synapse bugs by @ztqakita in #578
• fix brainpy.math.softplus and brainpy.dnn.SoftPlus by @chaoming0625 in #581
• add TruncatedNormal to initialize.py by @charlielam0615 in #583
• Fix _format_shape in random_inits.py by @charlielam0615 in #584
• fix bugs in truncated_normal by @charlielam0615 in #585
• [dyn] fix warning of reset_state by @chaoming0625 in #587
• [math] upgrade variable retrival by @chaoming0625 in #589
• [math & dnn] add brainpy.math.unflatten and brainpy.dnn.Unflatten by @chaoming0625 in #588
• [math] add ein_rearrange, ein_reduce, and ein_repeat functions by @chaoming0625 in #590
• [math] Support taichi customized op with metal cpu backend by @Routhleck in #579
• Doc fix and standardize Dual Exponential model again by @chaoming0625 in #591
• update doc, upgrade reset_state, update projection models by @chaoming0625 in #592
• [taichi] Make taichi caches more transparent and Add clean caches function by @Routhleck in #596
• [test] remove test skip on macos, since brainpylib supports taichi interface on macos by @chaoming0625 in #597
• [dyn] add clear_input in the step_run function. by @chaoming0625 in #601
• [math] Refactor taichi operators by @Routhleck in #598
• [math] fix brainpy.math.scan by @chaoming0625 in #604
• disable_ jit support in brainpy.math.scan by @chaoming0625 in #606
• [math] Remove the logs that taichi.init() print by @Routhleck in #609
• Version control in Publish.yml CI by @chaoming0625 in #610

New Contributors

• @charlielam0615 made their first contribution in #566

Full Changelog: V2.4.6...V2.5.0