neuralnetlib 3.3.7

• docs: remove useless comments
• fix(Transformer): too much things to tell
• feat: even more precise floating point for metrics and loss
• refactor: special tokens now passed via init for Transformer
• feat: enhance beam search and token prediction mechanisms
• docs: update readme
• fix(Transformer): vanishing gradient fix
• fix(Transformer): still on it (wip)
• fix(Transformer): another fix
• fix(Transformer): special token indices
• fix(Transformer): normalization IS the issue
• docs: update readme
• fix(Transformer): cross attention weights
• fix: LearningRateScheduler
• fix: LearningRateScheduler
• fix: normalization in data preparation
• fix: different vocab size for different tokenizations
• fix(PositionalEncoding): scaling
• fix(AddNorm): better normalization
• fix(TransformerEncoderLayer): huge improvements
• perf(SequenceCrossEntropy): add vectorization
• fix(Tokenizer+Transformer): tokenization alignement for special tokens
• fix(transformer): investigate and address gradient instability and explosion
• fix(sce): label smoothing
• refactor: gradient clipping
• fix(Transformer): gradient explosion
• fix(Transformer): tokens padding and max sequence
• test: tried with a better dataset
• fix(sce): y_pred treated as logits instead of probs
• fix(TransformerEncoderLayer): remove arbitrary scaling
• fix(Transformer): sce won't ignore sos and eos tokens
• fix: sce extending lossfunction
• fix(sce): softmax not necessary
• feat: add BLEU, ROUGE-L and ROUGE-N scores
• fix: validation data in fit method and shuffle in train_test_split
• docs: modifies example to use validation split and bleu score
• fix(PositionalEncoding): better positional scaling
• ci: bump version to 3.3.7

neuralnetlib 3.3.6

• feat: add Transformer model and layer architecture (wip)
• fix(Transformer): gradient propagation between layers
• fix(Transformer): tokenization, sequence handling and shapes
• fix(callbacks): now compatible with every model architecture
• fix_later: find why the Transformer output won't work
• ci: bump version to 3.3.6

neuralnetlib 3.3.5

• feat(autoencoder): add VAE image generation
• refactor: imports organization
• refactor: examples folder tree organization
• docs: fix typo
• feat(preprocessing): add ImageDataGenerator
• ci: bump version to 3.3.5

neuralnetlib 3.3.4

• docs: update readme
• docs: remove useless comments
• fix(convolution): stride parameter
• feat(layer): add UpSampling2D"
• docs: update readme
• perf: changed NCHW to NHWC for CPU efficiency
• docs: update readme
• perf: switch from NCL to NLC for CPU efficiency
• ci: bump version to 3.3.4

neuralnetlib 3.3.3

• fix(example): weight init
• docs(examples): fresh run
• docs: update readme
• fix(layers): encoder and decoder layers
• fix(conv2d): align output shape calculation between im2col and convolve
• ci: bump version to 3.3.3

neuralnetlib 3.3.2

• fix(model): save method
• docs: update readme
• docs: update readme
• feat(autoencoder): add variational autoencoder (VAE)
• ci: bump version to 3.3.2

neuralnetlib 3.3.1

• docs: update todo
• feat(preprocessing): add cosine similarity
• docs: update todo
• feat(callbacks): add LearningRateScheduler
• ci: bump version to 3.3.1

neuralnetlib 3.3.0

• docs: update readme
• docs: update readme
• docs: update readme
• docs: remove useless comments
• docs: update readme
• docs: update readme
• refactor: code cleanup and formatting
• fix(config): layers and model config
• fix(metrics): pr auc and roc auc
• refactor(PCA): add explained variance ratio
• feat(Model): add autoencoder model
• feat(preprocessing): add t-SNE
• feat(layers): update compatibility dict
• ci: bump version to 3.3.0

neuralnetlib 3.2.2

• docs: update readme
• refactor: change model -> models for future implementations
• ci: bump version to 3.2.1
• ci: bump version to 3.2.2

neuralnetlib 3.2.1

• docs: update readme
• refactor: change model -> models for future implementations
• ci: bump version to 3.2.1