BYOL (bootstrap your own latent)
BYOL (bootstrap your own latent) is a self-supervised learning method in machine learning that enhances representation learning without labeled data.
Neural networks
Tacotron
Tacotron is a neural network architecture designed for text-to-speech synthesis, generating natural-sounding speech directly from text input. Developed by Google researchers, it represents a significant advancement in end-to-end speech synthesis systems.
Jürgen Schmidhuber
Jürgen Schmidhuber is a German computer scientist known for his pioneering work in artificial intelligence, particularly in the development of deep learning and neural networks. His research has significantly influenced the fields of machine learning and artificial intelligence.
Point-E
Point-E is a machine learning model designed to generate three-dimensional point clouds from two-dimensional images or text prompts. It emphasizes fast and efficient 3D shape generation using neural networks, targeting applications in 3D modeling and computer graphics.
Generative query network (GQN)
Generative query networks (GQNs) are neural network models designed to learn representations of 3D scenes from 2D observations. They enable the generation of novel views of a scene without explicit 3D modeling.
WeNet (production-first speech recognition)
WeNet is an open-source speech recognition toolkit designed with a production-first approach, emphasizing real-world deployment efficiency and scalability. It integrates advanced neural network architectures to facilitate end-to-end speech recognition for various languages and applications.
Artificial neuron
An artificial neuron is a mathematical model inspired by biological neurons, used as the fundamental unit in artificial neural networks. It processes input data by applying weights, summing them, and passing the result through an activation function to produce an output.
Bernard Widrow
Bernard Widrow is an American electrical engineer and professor known for his pioneering work in adaptive signal processing and neural networks, particularly as co-inventor of the LMS algorithm and the ADALINE network.
Conditional neural process
Conditional neural processes (CNPs) are a class of machine learning models designed to efficiently learn distributions over functions, combining the flexibility of neural networks with the data efficiency of Gaussian processes. They provide a framework for rapid adaptation to new tasks by conditioning on observed data.
AlexNet
AlexNet is a pioneering convolutional neural network architecture that significantly advanced image recognition technology. Developed in 2012, it demonstrated the effectiveness of deep learning in large-scale visual tasks.