Free Information Center
PCT (point cloud transformer) is a deep learning architecture designed to process and analyze 3D point cloud data using transformer mechanisms. It enables efficient feature extraction and understanding of spatial relationships in unstructured 3D data for various applications.
The Penn Treebank is a linguistic resource that provides annotated text corpora for natural language processing and computational linguistics research.
OccNet (occupancy network for driving) is a deep learning framework designed to model and predict the spatial occupancy of dynamic environments for autonomous driving. It uses 3D occupancy representations to enhance perception and decision-making in self-driving systems.
CLIP is a neural network architecture designed to understand images and text simultaneously, enabling advanced applications in AI.
Octo is an open-source transformer model designed specifically for robotics applications. It facilitates advanced functionalities in robot learning and interaction.
An autoencoder is a type of artificial neural network used to learn efficient data encodings in an unsupervised manner. It consists of an encoder to compress the input and a decoder to reconstruct the original data from the compressed representation.
EPIC-KITCHENS is a large-scale egocentric video dataset designed for action recognition and video understanding in kitchen environments.
Neuro-symbolic AI combines neural networks and symbolic reasoning to enhance artificial intelligence capabilities, aiming for improved understanding and reasoning.
Codex is an AI system developed by OpenAI that translates natural language into computer code. It supports multiple programming languages and powers applications like GitHub Copilot.
LibriSpeech is a widely used dataset for training and evaluating automatic speech recognition systems, derived from audiobooks.