GRYDRA v2.0 is a complete, modular Ruby library for building, training, and deploying neural networks. NEW in v2.0: - Complete modular architecture with 29 organized files - Keyword arguments API for better readability - Full implementations (no more "simplified" versions) - 8 loss functions (MSE, MAE, Huber, Cross-Entropy, Hinge, Log-Cosh, Quantile) - 5 optimizers (Adam, SGD, RMSprop, AdaGrad, AdamW) - 6 training callbacks (EarlyStopping, LearningRateScheduler, ReduceLROnPlateau, ModelCheckpoint, CSVLogger, ProgressBar) - Complete LSTM implementation with backpropagation - Complete 2D Convolutional layer with padding and stride - Real PCA with eigenvalue decomposition using Power Iteration - Multiple activation functions (Tanh, ReLU, Leaky ReLU, Sigmoid, Swish, GELU, Softmax) - Regularization (Dropout, L1, L2) - Weight initialization (Xavier, He) - Data normalization (Z-Score, Min-Max) - Comprehensive metrics (MSE, MAE, Accuracy, Precision, Recall, F1, Confusion Matrix, AUC-ROC) - Advanced training (mini-batch, early stopping, learning rate decay, validation split) - Cross-validation and hyperparameter search - Text processing (vocabulary, binary vectorization, TF-IDF) - Model persistence (save/load with Marshal) - Network visualization and gradient analysis - Simplified EasyNetwork interface - 100% backward compatibility with v1.x Perfect for machine learning projects, research, and education in Ruby.
A ruby machine learning gem
Next-generation machine learning infrastructure
This is a simple machine learning library written in Ruby. It provides implementations of linear regression and multiclass perceptron and visualization and validation methods to verify results. Also included are helper methods to work with training and testing data.
High level plug-and-play interface for composing Machine Learning applications
Text2SQL is a gem designed to generate SQL queries from natural language inputs. It leverages machine learning models to interpret schema files and user inputs, generating SQL queries that can be executed and returning results in a human-readable format.
Algorithms for machine learning and artificial intelligence in Ruby.
Machine learning text classifier
Asagi evolved out of the ExperienceSequencer. Note that you'll still need to modify the output tree include certain forms of machine learning in the action script.
I've always wanted an alternative to Duolingo, but hadn't had the time. Then I realized I could make one with on and offline capabilities using simple machine learning and duck duck go search..
Duck Sum is a Compound Word Associational Network form of machine learning. This prints out a QR Code using RQRCode. Minimal data collection is done using Duckduckgo.
An infinite memorization algorithm for allowing self-modification. In practice, this would be used for storing different machine learning code in memory.
I use this process to train my language model as I flesh out my constructed language. Unlike training on a natural language, it is way simpler to actually train an algorithm on a fictional language, specifically with languages you train as you build the language. Still undecided on whether to incorporate this into LearnAnswer, as they completely reshapes how I do machine learning.
An AI-powered pair programmer. Provides a user-friendly interface for using AI API's to automatically repair broken code and suggest improvements. Simply provide the faulty code as input, and the gem will generate a corrected version using advanced machine learning techniques.
The ruby-amazon-bedrock gem offers Ruby developers an efficient and user-friendly interface to Amazon Bedrock, a powerful library for AI-driven text and image generation. This gem simplifies the process of connecting to Amazon Bedrock's APIs, enabling developers to easily harness the capabilities of advanced machine learning models for generating high-quality text and images.