Showing 61-120 of 314 articles
DeBERTa
DeBERTa (Decoding-enhanced BERT with Disentangled Attention) is a family of pre-trained language models developed by Microsoft Research that improves BERT and...
MicrosoftNatural Language Processing
Decoder
See also: Encoder, Transformer, Machine learning terms A decoder is the component of a neural network that turns an internal, compressed, or abstract...
Machine LearningNeural Networks
Deep Learning
Deep learning is a subset of machine learning that uses artificial neural networks with multiple layers to automatically learn representations of data at...
Artificial IntelligenceMachine Learning
Deep Model
A deep model, also called a deep learning model or deep neural network, is an artificial neural network built from many stacked layers of processing units that...
Machine Learning
Deep Neural Network
A deep neural network (DNN) is an artificial neural network with multiple hidden layers of artificial neurons stacked between its input and output layers,...
Machine LearningNeural Networks
Deep Q-Network (DQN)
Deep Q-Network (DQN) is a reinforcement learning algorithm that uses a deep neural network to approximate the optimal action-value function (Q-function),...
Machine LearningReinforcement Learning
DeepLIFT
DeepLIFT (Deep Learning Important FeaTures) is a feature attribution method for deep neural networks introduced by Avanti Shrikumar, Peyton Greenside, and...
InterpretabilityMachine Learning
DeepLab
DeepLab is a family of deep convolutional neural network architectures for semantic segmentation, developed by Liang-Chieh Chen and collaborators at UCLA and...
Computer VisionGoogle
DeepNorm / DeepNet
DeepNorm is a normalization and weight initialization scheme for Transformer networks that makes the training of very deep models stable. It was introduced by...
Neural Networks
DeepSeek Sparse Attention (DSA)
DeepSeek Sparse Attention (DSA) is a trainable, fine-grained sparse attention mechanism introduced by the Chinese AI company DeepSeek in its experimental model...
Neural Networks
DeepSpeed
DeepSpeed is an open-source deep learning optimization library developed by Microsoft that makes distributed training and inference of large models efficient,...
AI InfrastructureMachine Learning
DeiT
DeiT (Data-efficient Image Transformers) is a family of vision transformer models that proved Vision Transformers can be trained to state-of-the-art image...
Computer VisionTransformer Models
Denoising
Denoising is the process of removing unwanted noise from data to recover a cleaner underlying signal, and in modern AI it doubles as a training principle: a...
Machine Learning
Dense Layer
A dense layer, also called a fully connected (FC) layer, linear layer, or affine layer, is a layer in an artificial neural network where every input neuron is...
Machine LearningNeural Networks
DenseNet
DenseNet (Densely Connected Convolutional Networks) is a convolutional neural network architecture that connects every layer to every other layer in a...
Computer VisionNeural Networks
Depth estimation
Depth estimation is the computer vision task of predicting how far each surface in a scene is from the camera, producing a dense per-pixel depth map from one...
Computer Vision
Diederik Kingma
Diederik Kingma is a Dutch machine learning researcher and a founding member of OpenAI who is best known as the first author of the Adam optimizer [1] and the...
Machine LearningPeople
Diffusion Forcing
Diffusion Forcing is a training paradigm for sequence generative modeling introduced in 2024 that assigns each token in a sequence its own independent,...
Generative AI
Diffusion model
A diffusion model is a type of generative model that produces data by learning to reverse a gradual noising process: it is trained so that if Gaussian noise is...
Computer VisionGenerative AI
Diffusion policy
Diffusion policy is a robot imitation-learning method, introduced in 2023 by Cheng Chi, Shuran Song, and collaborators at Columbia University, the Toyota...
Diffusion ModelsRobotics
Direct Preference Optimization (DPO)
Direct Preference Optimization (DPO) is a method for aligning large language models with human preferences that replaces the multi-stage reinforcement learning...
AI AlignmentMachine Learning
DistilBERT
DistilBERT is a compressed version of BERT released by Hugging Face in October 2019 that is 40% smaller and 60% faster than BERT-base while retaining 97% of...
AI ModelsNatural Language Processing
Double Descent
Double descent is a phenomenon in machine learning and statistical learning theory in which a model's test error, plotted against increasing model complexity,...
Machine Learning
Downsampling
Downsampling is the process of reducing the number of samples, the spatial resolution, or the number of data instances in a signal, image, or dataset in order...
Data & DatasetsMachine Learning
DreamBooth
DreamBooth is a subject-driven fine-tuning method for text-to-image diffusion models that personalizes a pretrained model to a specific subject, for example a...
Generative AI
Dropout
Dropout is a regularization technique for neural networks that randomly sets a fraction of neuron activations to zero during training, forcing the network to...
Training & Optimization
Dropout Regularization
Dropout regularization is a regularization technique for neural networks that prevents overfitting by randomly setting a fraction of neuron activations to zero...
Machine LearningTraining & Optimization
ELECTRA
ELECTRA, which stands for Efficiently Learning an Encoder that Classifies Token Replacements Accurately, is a pre-training method for natural language...
Natural Language ProcessingTransformer Models
Eager Execution
Eager execution is an imperative, define-by-run mode of running machine learning framework operations in which each operation is evaluated immediately as it is...
Machine LearningSoftware Development
Early Stopping
Early stopping is a regularization technique that halts the training of an iterative machine learning model as soon as its performance on a held-out validation...
Machine LearningTraining & Optimization
EfficientNet
EfficientNet is a family of convolutional neural network architectures and a model-scaling method that uniformly scales network depth, width, and input...
Computer VisionNeural Networks
Embedding Space
An embedding space is a continuous, typically high-dimensional vector space in which data objects (words, sentences, images, users, audio clips, code, or other...
Machine Learning
Embeddings
Embeddings are dense vector representations of data in a continuous vector space, where semantically similar items are mapped to nearby points. An embedding...
Information RetrievalMachine Learning
Embodied AI
Embodied AI is artificial intelligence that perceives, reasons about, and acts within physical or simulated environments through a body, using sensors to...
Artificial IntelligenceReinforcement Learning
Encoder
An encoder in machine learning is a neural network component that transforms input data (text, an image, audio, or code) into a compressed, structured...
Model Architecture
Epoch
An epoch in machine learning is one complete pass through the entire training dataset, during which every example is presented to the model exactly once to...
Machine LearningNeural Networks
Estimator (tf.estimator)
See also: TensorFlow, Keras, deep learning, machine learning tf.estimator is a high-level TensorFlow API that encapsulates the complete lifecycle of a machine...
Developer ToolsMachine Learning
Expert Choice routing
Expert Choice routing (often abbreviated EC) is a routing method for mixture of experts (MoE) layers in neural networks, introduced by researchers at Google in...
Neural Networks
Exploding Gradient Problem
See also: Machine learning terms, Vanishing gradient problem, Gradient clipping, Backpropagation The exploding gradient problem is a training failure in deep...
Machine LearningNeural Networks
Faster R-CNN
Faster R-CNN is a two-stage object detection model introduced by Shaoqing Ren, Kaiming He, Ross Girshick, and Jian Sun in the 2015 NeurIPS paper Faster R-CNN:...
Computer Vision
Federated Learning
Federated learning is a machine learning technique that trains a shared model across many decentralized devices or servers without moving their raw data to a...
AI EthicsMachine Learning
Feedforward Neural Network (FFN)
A feedforward neural network (FFN), also called a multilayer perceptron (MLP) when it has multiple layers, is a type of artificial neural network in which...
Machine LearningNeural Networks
Few-Shot Learning
Few-shot learning is a branch of machine learning in which a model learns to recognize new classes or perform new tasks from only a very small number of...
Machine Learning
Fine Tuning
Fine-tuning is a machine learning technique that takes a pre-trained model and further trains it on a smaller, task-specific dataset, adjusting the model's...
Machine LearningTraining & Optimization
Focal loss
Focal loss is a loss function that reshapes standard cross-entropy loss by adding a (1 - pt)^gamma modulating factor, which down-weights well-classified (easy)...
Computer VisionMachine Learning
François Chollet
François Chollet (born 20 October 1989) is a French software engineer and artificial intelligence researcher best known as the creator of the Keras...
People
Full Softmax
Full softmax (also called the standard softmax or exact softmax) is the softmax computation that calculates a probability for every possible output class in a...
Machine LearningNatural Language Processing
Fully Connected Layer
A fully connected layer (also called a dense layer or linear layer) is a layer in an artificial neural network in which every input value connects to every...
Machine LearningNeural Networks
Fully Sharded Data Parallel (FSDP)
Fully Sharded Data Parallel (FSDP) is a distributed training technique implemented in PyTorch that shards a model's parameters, gradients, and optimizer states...
AI InfrastructureDeveloper Tools
GAN
GAN stands for generative adversarial network, a class of deep learning generative models in which two neural networks are trained against each other: a...
Generative AI
GELU (Gaussian Error Linear Unit)
The Gaussian Error Linear Unit (GELU) is a smooth, non-monotonic activation function defined as GELU(x) = x · Φ(x), where Φ(x) is the cumulative distribution...
Artificial IntelligenceNeural Networks
GNoME
GNoME (Graph Networks for Materials Exploration) is a deep-learning system from Google DeepMind that predicts the thermodynamic stability of inorganic crystals...
AI for ScienceGoogle DeepMind
GPTQ
GPTQ (Generative Pre-trained Transformer Quantization) is a one-shot post-training quantization method that compresses the weights of large language models to...
AI Inference
GPU computing
GPU computing is the use of a graphics processing unit (GPU) to perform general-purpose computation that was traditionally handled by the central processing...
AI HardwareAI Infrastructure
Gated DeltaNet
Gated DeltaNet is a linear attention sequence model that augments the delta rule, a key-value error-correction update used in the earlier DeltaNet...
Neural Networks
Gaussian Splatting
Gaussian splatting is a method for real-time radiance field rendering that represents a 3D scene as a collection of millions of anisotropic 3D Gaussian...
Computer Vision
Generalization
See also: Machine learning terms, Bias-variance tradeoff Generalization in machine learning is the ability of a trained model to perform accurately on new,...
Machine LearningModel Evaluation
Generative Model
See also: Machine learning terms, Discriminative model A generative model is a class of statistical and machine learning model that learns the joint...
Generative AIMachine Learning
Generative adversarial network
A generative adversarial network (GAN) is a class of machine learning model in which two neural networks, a generator and a discriminator, are trained...
Generative AIMachine Learning
Grad-CAM
Grad-CAM (Gradient-weighted Class Activation Mapping) is a technique for producing visual explanations from convolutional neural network (CNN) models by using...
Computer VisionInterpretability