v1.0.0-alpha Release

[syncrostone]

This is the alpha pre-release of the stable v1.0.0 release. Below is a summary of changes and updates from the previous release, v0.4.

New Features

• Exhaustive documentation now available!
• Now compatible with both TF1 and TF2 (still uses tensorflow graphs).
• Add fixed weights feature-- can choose not to train certain weights in W_rec, W_in, W_out.
• Revamps Simulation to make it relevant and functional.
• Adds new MatchToCategory task.
• Add support for custom loss and regularization functions.

Other New Features

• Added options for constant uniform, constant gaussian, glorot gaussian, glorot uniform initializations.
• Automatically build and initialize in get_weights, save, test, train, train_curric. No model.build() calls needed from now on.
• Added train_curric function.

Breaking Changes

• No long supports TF < 1.13.1
• Refactors RDM Task--> PerceptualDiscrimination & changes some functionality.
• Refactors Romo Task--> DelayedDiscrimination & changes some functionality.
• Refactors Curriculum's self.stopTraining --> self. stop_training. This change should not affect most users since it is a variable used internally only by curriculum.py and rnn.py
• Removes sussillo regularizer because it was specific to the transfer-function used. Can be defined and used via the custom regularizer.
• Remove get_initial_weights function. Use get_weights instead.

Other changes (may affect results)

• Default random initialization changed to glorot gaussian from constant uniform. This may affect results.
• Unexpected behavior in Dale's fixed and Dale's setup moved into WeightInitializer. This should not affect most users but may affect results.
• Default training iters changed from 10000 to 50000

Other Changes (should not affect users)

• BasicScan internal implementation slightly change. Should not affect users unless users inherited BasicScan to make a custom Model.
• Use get_effective to get the weight matrices to regularize. Should not affect users.

Bug Fixes

• Bug in binary cross entropy loss function fixed.

[codecov[bot]]

Codecov Report

Merging #17 into master will increase coverage by 23.35%. The diff coverage is 72.41%.

@@             Coverage Diff             @@
##           master      #17       +/-   ##
===========================================
+ Coverage   52.87%   76.23%   +23.35%     
===========================================
  Files          13       14        +1     
  Lines         730      871      +141     
===========================================
+ Hits          386      664      +278     
+ Misses        344      207      -137     

Impacted Files	Coverage Δ
psychrnn/_version.py	0.00% <0.00%> (ø)
psychrnn/backend/curriculum.py	0.00% <0.00%> (ø)
psychrnn/tasks/delayed_discrim.py	0.00% <0.00%> (ø)
psychrnn/backend/loss_functions.py	83.33% <66.66%> (-4.17%)	:arrow_down:
psychrnn/backend/models/basic.py	81.25% <66.66%> (+81.25%)	:arrow_up:
psychrnn/backend/initializations.py	79.48% <78.48%> (+0.45%)	:arrow_up:
psychrnn/backend/rnn.py	85.36% <80.30%> (-3.77%)	:arrow_down:
psychrnn/tasks/perceptual_discrimination.py	90.24% <90.24%> (ø)
psychrnn/tasks/match_to_category.py	93.47% <93.47%> (ø)
psychrnn/backend/simulation.py	97.05% <98.82%> (+97.05%)	:arrow_up:
... and 11 more

---

Continue to review full report at Codecov.

Legend - Click here to learn more Δ = absolute <relative> (impact), ø = not affected, ? = missing data Powered by Codecov. Last update 9774bc3...6eea5a1. Read the comment docs.