BoolQ
BoolQ is a dataset designed for evaluating natural language understanding and question-answering systems, featuring yes/no questions derived from Wikipedia articles.
Technology & Innovation
MixNeRF (neural radiance fields for mixed reality)
MixNeRF is a computational approach that integrates neural radiance fields with mixed reality applications to enable realistic rendering and interaction of 3D scenes. It leverages neural networks to model complex light transport and scene geometry, facilitating immersive augmented and virtual reality experiences.
Theano (software)
Theano is an open-source Python library designed for efficient numerical computation, particularly in large-scale machine learning tasks. It allows users to define, optimize, and evaluate mathematical expressions involving multi-dimensional arrays.
GET3D (generative 3D model)
GET3D is a generative 3D model designed to produce high-quality three-dimensional objects from 2D images. It leverages advances in machine learning to generate detailed 3D shapes and textures, enabling applications in graphics, gaming, and virtual reality.
Neural radiance flow (NeRF)
Neural radiance flow (NeRF) is a computer vision technique that models dynamic 3D scenes by combining neural radiance fields with scene flow estimation, enabling realistic rendering of complex motions and deformations from sparse input views.
Expectation–maximization for deep learning
Expectation–maximization for deep learning is a computational approach that integrates the EM algorithm into neural network training to handle incomplete data and latent variable models. It iteratively estimates missing data and optimizes model parameters, improving learning in unsupervised and semi-supervised contexts.
F1 score
The F1 score is a statistical measure used to evaluate the accuracy of a binary classification test by considering both precision and recall. It represents the harmonic mean of precision and recall, providing a balanced metric especially useful when the class distribution is uneven.
AlphaFold
AlphaFold is an artificial intelligence system developed to predict protein structures from amino acid sequences with high accuracy. It represents a significant advancement in computational biology, enabling faster and more reliable protein modeling than previous methods.
KPConv (kernel point convolution)
KPConv (kernel point convolution) is a convolutional operation designed specifically for deep learning on 3D point clouds. It enables the extraction of geometric features directly from irregular point data, improving tasks such as 3D shape understanding and segmentation.
Constrained decoding
Constrained decoding is a technique in natural language processing and machine learning that restricts the output of a generative model to satisfy specific constraints. This method is used to guide the generation process to produce valid, relevant, or contextually appropriate outputs according to predefined rules or conditions.