AI Factory Glossary

temporal consistency, multimodal ai

Temporal consistency ensures smooth transitions and coherent motion across video frames.

temporal consistency,video generation

Maintain coherent appearance across video frames.

temporal context, recommendation systems

Temporal context models time-dependent preferences like seasonal interests or daily patterns.

temporal contrastive learning, video understanding

Contrast nearby vs distant frames.

temporal ensembling, semi-supervised learning

Average predictions over training.

temporal event ordering,nlp

Order events chronologically.

temporal filtering, rag

Filter by date/time.

temporal filtering, rag

Temporal filtering limits retrieval to documents within date ranges.

temporal fusion transformer, time series models

Temporal Fusion Transformer combines LSTM encoder-decoder with multi-head attention for interpretable multi-horizon time series forecasting with covariates.

temporal graph networks,graph neural networks

GNNs for dynamic graphs.

temporal information extraction, healthcare ai

Extract time-related medical info.

temporal point process gnn, graph neural networks

Temporal point process GNNs model event sequences on graphs through learned intensity functions.

temporal point process, time series models

Temporal point processes model event sequences in continuous time by specifying conditional intensity functions governing event occurrence rates.

temporal random walk, graph neural networks

Temporal random walks respect edge timestamps when sampling paths for representation learning.

temporal reasoning in video, video understanding

Understand time-based relationships.

temporal reasoning,reasoning

Reason about time and sequences.

temporal segment networks, tsn, video understanding

Sample sparse frames from video.

temporal shift module, tsm, video understanding

Efficient temporal modeling.

temporal smoothing, graph neural networks

Temporal smoothing in dynamic graphs regularizes learned representations to change gradually over time.

temporary bonding for thinning, advanced packaging

Attach to carrier for processing.

temporary bonding, advanced packaging

Reversible bonding for processing.

tensile stress,cvd

Film pulls inward can cause cracking.

tensor contiguity, optimization

Memory layout of tensors.

tensor core,matrix unit

Tensor Cores (NVIDIA) accelerate matrix operations. Mixed precision (FP16/BF16 inputs, FP32 accumulate). Key for AI.

tensor cores, hardware

Specialized hardware for matrix operations.

tensor decomposition for chemistry, chemistry ai

Represent chemical tensors efficiently.

tensor decomposition, model optimization

Tensor decomposition factorizes weight tensors reducing parameters while maintaining capacity.

tensor factorization, recommendation systems

Tensor factorization extends matrix methods to higher-order tensors for context-aware recommendations.

tensor field network, graph neural networks

Tensor field networks achieve equivariance through tensor product operations on irreducible representations of rotation groups.

tensor field networks, scientific ml

Operate on geometric tensors.

tensor fusion, multimodal ai

Outer product of modality features.

tensor parallel,megatron,column

Tensor parallelism splits individual layers across GPUs. Megatron-style column/row parallel for attention and FFN.

tensor parallelism,model training

Split individual tensors/layers across devices.

tensor train, model optimization

Tensor train decomposition chains matrices through successive products for efficient compression.

tensorboard, mlops

TensorFlow's visualization toolkit.

tensorboard,visualize,training

TensorBoard visualizes training. Loss curves, histograms, graphs.

tensorf, 3d vision

Factorized tensor NeRF.

tensorflow lite, model optimization

TensorFlow Lite provides lightweight runtime for mobile and embedded deployment with optimization tools.

tensorflow profiler, infrastructure

Analyze TensorFlow performance.

tensorflow serving,google,production

TensorFlow Serving deploys TF models. High performance.

tensorrt-llm,deployment

NVIDIA's optimized library for LLM inference.

tensorrt, model optimization

TensorRT optimizes trained models for NVIDIA GPUs through fusion quantization and kernel selection.

tensorrt,deployment

NVIDIA's optimization library for fast inference.

tensorrt,inference optimization

TensorRT optimizes models for NVIDIA GPUs: layer fusion, precision calibration, kernel autotuning. Fastest inference.

tensorrt,optimization,nvidia

TensorRT optimizes models for NVIDIA GPUs. Kernel fusion, precision conversion. Fastest inference on NVIDIA.

teos (tetraethylorthosilicate),teos,tetraethylorthosilicate,cvd

Precursor for high-quality oxide CVD.

ter, ter, evaluation

Edit distance metric.

terahertz ellipsometry, metrology

Characterize carrier dynamics with THz.

termination resistor, signal & power integrity

Termination resistors match line impedance at receivers preventing reflections in high-speed links.

ternary gradients, distributed training

Quantize gradients to -1 0 +1.