Nexora is a revolutionary library created specifically for Scratch that turns the process of developing neural networks into an intuitive and accessible constructor. Now you can create your models without leaving your favorite platform! What does Nexora offer? 1. Layers for building architecture: (Dense, Dropout, BatchNorm, Activation, Embedding) 2. Powerful optimizers: (SGD with Momentum, Adam with bias correction) 3. A wide choice of activation functions: (ReLU, Tanh, Sigmoid, SiLU, GELU, ELU, Softmax, Linear) 4. A full-fledged training stack thanks to (Fit, WipeTrainData and InsertExample) with support for shuffling examples(shuffle) during training and the ability to use batches(batch_size)! 5. Intuitive and easy sequence support with the new Embedding layer! 6. Work with multiple models simultaneously: name them as you create them and recall them intuitively—Nexora hides all the complexity under the hood. Why choose Nexora? - Nexora is the first Scratch library that provides such capabilities for creating neural networks. - Thanks to its intuitive interface and powerful core, creating and training models has become accessible even to beginners. - Flexibility: You can experiment with different combinations of layers, optimizers, and activation functions, finding the ideal architecture for your task. - Open: Nexora uses an open license (CC-BY-SA 2.0), so you can safely use this framework in your projects!
last modified: {26.11.2025} Updated: -Load and save functions accept two parameters (model and load name) -Nexora can now store more than one model in RAM and switch between them without re-initializing the model or loading it. modified: {26.10.2025} Fixed: - An issue where the Dense and BatchNorm layers did not fully initialize their parameters, leaving most of the parameters empty. - A backpropagation hang when using the Embedding layer. modified: {18.10.2025} Updated: -The documentation now includes descriptions and examples of working with new layers (BatchNorm, Activation)! -The project description has been updated to reflect current information! Added: -Added a new Embedding layer for working with sequences! modified: {07.10.2025} Added: -Added a new layer BatchNorm with moving averages (mean, var) and parameters (gamma, beta)! modified: {28.09.2025} Updated: -Splitting a monolithic kernel into a modular kernel! Fixed: -Fixed errors with the activation layer. -Fixed errors with transferring network settings during model creation. modified: {15.08.2025} Fixed: -Fixed incorrect copying of examples for fit! modified: {10.08.2025} Added: -Added support and processing of batches of different sizes! modified: {09.08.2025} Added: -Added training with fit! Added functions: Fit, WipeTrainData, InsertExample! -Additional configurable delay between layers. -New Activation layer for transforming outputs using activation functions! -New Linear activation function. Important: -The batchsize function does not work yet! modified: {03.08.2025} Fixed: -The delay algorithm has been corrected for correct data transmission. modified: {02.08.2025} Fixed: -Neural network prediction algorithm. -Propagation of error to previous layers. Improved: -Delays for correct list retrieval. -Initialization of weights is close to He initialization.
