Quantization
, from 32-bit floating point to 8-bit integers), shrinking model size and speeding up inference with minimal accuracy loss.
5 resources across 1 library
Glossary Terms(5)
Federated Learning
Federated learning is a machine learning technique that trains a shared model across multiple decentralized devices or servers holding local data, without the…
Contrastive Learning
Contrastive learning is a self-supervised representation learning technique that trains a model to produce similar embeddings for semantically related (positiv…
Multi-Task Learning
Multi-task learning is a machine learning technique in which a single model is trained simultaneously on multiple related tasks, sharing internal representatio…
Quantization (ML)
Quantization is a model compression technique that reduces the numerical precision used to represent a neural network's weights and activations (e.g., from 32-…
Mixed Precision Training
Mixed precision training is a technique for training neural networks that uses lower-precision numerical formats (such as 16-bit floating point) for most compu…