R-CNN
R-CNN is a family of machine learning models designed to perform object detection tasks by combining region proposal methods with convolutional neural networks.
Ray RLLib
Ray RLLib is a scalable reinforcement learning library designed for distributed execution and training of machine learning models.
RealNVP
RealNVP is a deep learning model used for density estimation and generative modeling through invertible neural networks.
Recurrent Neural Network
A Recurrent Neural Network (RNN) is a type of artificial neural network designed to recognize patterns in sequences of data, such as time series or natural language.
RegNet
RegNet is a type of convolutional neural network (CNN) architecture designed to improve flexibility, scalability, and performance in deep learning tasks.
REINFORCE
Reinforce is the process of strengthening or supporting something to make it more effective or resilient.
Relation Networks
Relation Networks are neural network architectures designed to model and reason about relationships between entities.
ReLU
ReLU is an activation function in neural networks that outputs the input directly if it is positive, otherwise, it outputs zero.
Reptile
A reptile is a cold-blooded vertebrate animal that typically lays eggs and has skin covered in scales or scutes.
ResNet
ResNet is a deep neural network architecture known for its ability to train very deep networks using residual learning.
Restricted Boltzmann Machine
A Restricted Boltzmann Machine (RBM) is a type of artificial neural network that is used for unsupervised learning, particularly for feature learning and dimensionality reduction.
RetinaNet
RetinaNet is a deep learning model designed for object detection tasks, known for its ability to handle the class imbalance problem effectively using a focal loss function.
RNN Transducer
The RNN Transducer is a type of neural network architecture designed for sequence-to-sequence tasks, often used in speech recognition.
RoBERTa
RoBERTa is a robustly optimized BERT approach, designed to improve the performance of NLP models by fine-tuning hyperparameters and training on more data.