Category

Training & Optimization

136 articlesRSS

Showing 121-136 of 136 articles

Swarm intelligence

Swarm intelligence (SI) is a branch of artificial intelligence concerned with the collective behavior of decentralized, self-organized systems, in which many...

AI AgentsArtificial Intelligence

Tensor Parallelism

Tensor parallelism (TP) is a distributed training technique that splits the individual weight matrices of a neural network layer across multiple devices, so...

AI InfrastructureLarge Language Models

Termination condition

See also: Machine learning terms A termination condition, also called a stopping criterion, convergence criterion, or halting condition, is a rule that decides...

Machine Learning

Test-Time Training (TTT)

Test-Time Training (TTT) is a family of machine learning techniques in which a model updates a subset of its own parameters at inference time, optimizing a...

AI InferenceMachine Learning

Training loss

In machine learning, training loss is the value of the loss function computed on the training data during model training, and it is the exact quantity that the...

Training run

A training run is a single, deliberate instance of training a neural network from scratch (or from a prior checkpoint) on a specified dataset, with a fixed...

Machine Learning

Unsloth

Unsloth is an open-source Python library that fine-tunes large language models up to two times faster while using up to 70 percent less GPU memory and, in its...

Developer ToolsOpen Source AI

VeRA (Vector-based Random Matrix Adaptation)

Vector-based Random Matrix Adaptation (VeRA) is a parameter-efficient fine-tuning (PEFT) method for adapting large pretrained neural networks to downstream...

Large Language Models

WRAP (Web Rephrase Augmented Pre-training)

WRAP (Web Rephrase Augmented Pre-training) is a synthetic-data pre-training method introduced in the paper "Rephrasing the Web: A Recipe for Compute and...

Data & DatasetsLarge Language Models

Wasserstein Loss

Wasserstein loss is a loss function for training generative models that measures the distance between two probability distributions as the Wasserstein-1...

Generative AIMachine Learning

Weight Decay

Weight decay is a regularization technique used in training neural networks that shrinks every parameter toward zero by a small fraction on each update step,...

Machine Learning

Whole-body control

Whole-body control (WBC) is a class of robotics control techniques that coordinates all of a robot's degrees of freedom at once to achieve multiple prioritized...

Humanoid RobotsRobotics

ZeRO (Zero Redundancy Optimizer)

ZeRO (Zero Redundancy Optimizer) is a family of memory-optimization techniques for training large neural networks introduced by Samyam Rajbhandari, Jeff...

Deep LearningMicrosoft

muP (Maximal Update Parametrization)

muP, short for Maximal Update Parametrization (often written muP, μP, or mu-P), is a parametrization scheme for deep neural networks in which a small set of...

Deep Learning

rsLoRA (Rank-Stabilized LoRA)

rsLoRA (rank-stabilized LoRA) is a one-line modification to the low-rank adaptation fine-tuning method for large neural networks. It replaces the conventional...

Large Language Models

torch.compile

torch.compile is the just-in-time graph capture and compilation feature introduced in PyTorch 2.0, a release first announced at the PyTorch Conference on...

Deep LearningDeveloper Tools