Free Information Center
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 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.
Ashish Vaswani is a prominent figure in artificial intelligence, known for his contributions to deep learning and natural language processing.
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.
Source-free domain adaptation is a method in machine learning that adapts models to new domains without requiring labeled data from the original source domain.
ViT (Vision Transformer) is a deep learning architecture that applies the transformer model, originally designed for natural language processing, to computer vision tasks. It processes images by dividing them into patches and treating these patches as tokens, enabling the use of self-attention mechanisms for image understanding.
Berkeley DeepDrive is a research initiative at UC Berkeley focusing on deep learning and autonomous driving technologies. It aims to advance the field through collaboration and innovation.
The Vector Institute is a Canadian artificial intelligence research organization focused on advancing AI technology and fostering collaboration among academia, industry, and government. Established in Toronto, it supports AI innovation and talent development.
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.
The Compressive Transformer is a type of neural network architecture designed to improve long-range sequence modeling by compressing past hidden states to extend memory capacity. It enhances the Transformer model by maintaining a compressed memory of previous activations, enabling efficient handling of longer sequences.