cuDNN
cuDNN is a GPU-accelerated library developed by NVIDIA that provides optimized routines for deep neural networks. It is widely used to improve the performance of training and inference in deep learning frameworks.
Artificial Intelligence
Message passing neural network (MPNN)
A Message Passing Neural Network (MPNN) is a type of graph neural network designed to process graph-structured data by iteratively exchanging and aggregating information between nodes. It is widely used in fields such as chemistry, social network analysis, and recommendation systems.
Wake–sleep algorithm
The Wake–sleep algorithm is a computational method used in machine learning to train probabilistic generative models, particularly useful in unsupervised learning. It alternates between wake and sleep phases to refine model parameters and recognition networks.
Gaussian process (machine learning)
Gaussian processes are a powerful statistical tool used in machine learning for regression and classification tasks, offering probabilistic predictions.
Go-Explore (exploration algorithm)
Go-Explore is an exploration algorithm that enhances the efficiency of reinforcement learning in environments with sparse rewards by focusing on effective exploration strategies.
Timeline of artificial intelligence
The timeline of artificial intelligence traces the development of AI from early theoretical concepts to modern applications. It highlights key milestones in AI research, technology, and achievements across decades.
One-2-3-45 (3D reconstruction)
One-2-3-45 is a method used in 3D reconstruction technology aimed at improving the accuracy and efficiency of creating three-dimensional models from two-dimensional images. It is notable for its structured approach in processing image data to reconstruct depth and spatial information.
Pascal VOC
Pascal VOC is a benchmark in the field of computer vision, primarily used for object detection and segmentation tasks in images.
ESPnet (end-to-end speech processing toolkit)
ESPnet is an open-source toolkit designed for end-to-end speech processing, encompassing speech recognition, speech synthesis, and related tasks. It provides a unified platform leveraging deep learning architectures to streamline development and research in speech technologies.
DeepLabCut (animal pose estimation)
DeepLabCut is an open-source software tool for animal pose estimation using deep learning techniques.