blanketglossary

Vision transformer

Definition

A vision transformer (ViT) is a transformer designed for computer vision. A ViT decomposes an input image into a series of patches, serializes each patch into a vector, and maps it to a smaller dimension with a single matrix multiplication. These vector embeddings are then processed by a transformer encoder as if they were token embeddings.

Related concepts

15.ai AI agent AI alignment AI anthropomorphism AI boom AI bubble AI data center AI effect AI literacy AI nationalism AI safety AI slop AI takeover AI veganism AI winter Action selection Activation function Adobe Firefly Adversarial machine learning Agent2Agent Aidan Gomez Alan Turing AlexNet Alex Graves (computer scientist)Alex Krizhevsky Allen Newell AlphaFold AlphaGo AlphaZero Andrej Karpathy Andrew Ng Anomaly detection Applications of artificial intelligence Artificial Intelligence Act Artificial Intelligence Cold War Artificial general intelligence Artificial human companion Artificial intelligence Artificial intelligence and elections Artificial intelligence arms race Artificial intelligence in architecture Artificial intelligence in education Artificial intelligence in fiction Artificial intelligence in healthcare Artificial intelligence in mental health Artificial intelligence in video games Artificial intelligence visual art Artificial superintelligence Ashish Vaswani Attention (machine learning)Attention Is All You Need Aurora (text-to-image model)AutoGPT Autoencoder Automated reasoning Automated theorem proving Autonomous driving Autoregressive model BERT (language model)BLOOM (language model)Backpropagation Batch normalization Bernard Widrow Bias–variance tradeoff Byte pair encoding COCO (dataset)Cell Painting Chatbot psychosis Chinchilla (language model)Christopher D. Manning Claude (language model)Claude Shannon Cliff Shaw Cluster analysis Co-occurrence matrix Competition in artificial intelligence Computer vision Conjugate gradient method Contrastive Language-Image Pre-training Convolution Convolutional neural network Cross-entropy DALL-E DBRX Daniel Kokotajlo (researcher)Data augmentation David Silver (computer scientist)DeepSeek (chatbot)Deep learning Deep learning speech synthesis Deepfake Demis Hassabis Denoising autoencoder DenseNet Differentiable neural computer Diffusion model Diffusion process Double descent Dream Machine (text-to-video model)Echo state network EfficientNet ElevenLabs Environmental impact of artificial intelligence Ethics of artificial intelligence Explainable artificial intelligence Facial recognition system Fei-Fei Li Floating point operations per second Flux (text-to-image model)Frank Rosenblatt François Chollet Frontier (supercomputer)GPT-3 GPT Image Gated recurrent unit Gating mechanism Gemini (chatbot)Gemini (language model)Gemma (language model)Generative AI Generative adversarial network Generative engine optimization Generative pre-trained transformer Genie (world model)Geoffrey Hinton GloVe Glossary of artificial intelligence Gradient descent Gram matrix Graph neural network Grok (chatbot)Hallucination (artificial intelligence)Handwriting recognition Herbert A. Simon Highway network History of artificial intelligence Huawei PanGu Human image synthesis Humanity's Last Exam Hyperparameter (machine learning)IBM Granite IBM Watson IBM Watsonx Ian Goodfellow Ideogram (text-to-image model)Ilya Sutskever ImageNet Image classification Image recognition Image segmentation Image synthesis Imagen (text-to-image model)Imitation learning Inceptionv3 Inductive bias Intelligent agent James Goodnight Jan Leike John Hopfield John McCarthy (computer scientist)John Schulman John von Neumann Joseph Weizenbaum Jürgen Schmidhuber Kling AI Knowledge distillation Kunihiko Fukushima LaMDA Language model Language models Large language model Latent diffusion model Latent space LayerNorm Lethal autonomous weapon List of artificial intelligence companies List of artificial intelligence projects Llama (language model)Long short-term memory Loss functions for classification Lotfi A. Zadeh Machine learning Mamba (deep learning architecture)Marvin Minsky Matrix multiplication Meta AI Midjourney Ming-Hsuan Yang MiniMax (company)Model Context Protocol MuZero Multilayer perceptron Music and artificial intelligence Mustafa Suleyman Nathaniel Rochester (computer scientist)Natural language processing Neural Turing machine Neural machine translation Neural network (machine learning)Noam Shazeer Normalization (machine learning)Oasis (Minecraft clone)Object detection Oliver Selfridge OpenAI Five Optical character recognition Oriol Vinyals Overfitting PaLM Parameter Paul Werbos Perceiver Percy Liang Pixel Policy gradient method Pooling layer Precautionary principle Project Debater Projection (linear algebra)Prompt engineering PyTorch Pyramid (image processing)Q-learning Quasi-Newton method Quoc V. Le Qwen RGB color model Reasoning model Recraft Rectifier (neural networks)Recurrent neural network Recursive self-improvement Reflection (artificial intelligence)Regression analysis Regularization (mathematics)Regulation of artificial intelligence Regulation of artificial intelligence in the United States Reinforcement learning Reinforcement learning from human feedback Residual neural network Retrieval-augmented generation Riffusion Robot control Rotary positional embedding Runway (company)Seedance 2.0 Self-driving car Self-supervised learning Seppo Linnainmaa Seq2seq Seymour Papert Shun'ichi Amari Sigmoid function Softmax function Sora (text-to-video model)Speech recognition Stable Diffusion State–action–reward–state–action Stephen Grossberg Stochastic gradient descent Suno (platform)Supervised learning Symbolic artificial intelligence T5 (language model)Takeo Kanade TensorFlow Text-to-image model Text-to-video model Timeline of artificial intelligence Training, validation, and test data sets Transfer learning Transformer (deep learning)Transformer (deep learning architecture)Transformer (machine learning model)Udio Uncanny valley Variational autoencoder Vector quantization Vector space Veo (text-to-video model)Vibe coding Virtual politician Vit Walter Pitts Warren Sturgis McCulloch WaveNet Weak artificial intelligence Weather forecasting Weight initialization Whisper (speech recognition system)Word2vec Word embedding Workplace impact of artificial intelligence World model (artificial intelligence)Xiaomi MiMo Yann LeCun Yoshua Bengio

15 concepts already in your glossary