Disentanglement
multimodal ai
Disentanglement is learning representations where independent latent factors correspond to separate semantic attributes - It improves interpretability and controllability…
15,414 technical terms and definitions
multimodal ai
Disentanglement is learning representations where independent latent factors correspond to separate semantic attributes - It improves interpretability and controllability…
disjoint set union advanced, disjoint set union, set union advanced, disjoint set, set union, union advanced
Disjoint Set Union Advanced Introduction & Motivation Disjoint Set Union Advanced addresses a central problem in data-structures process control and union-by-size-optimization…
dislocation density prediction, dislocation density, density prediction
Dislocation Density Prediction with Machine Learning Introduction & Motivation Dislocation Density Prediction with Machine Learning addresses a central problem in dislocation…
dislocation density threading defect prediction, dislocation density threading, density threading defect, threading defect prediction, dislocation density, density threading
Dislocation Density Threading Defect Prediction with Machine Learning Introduction & Motivation Dislocation Density Threading Defect Prediction with Machine Learning addresses…
fairness
Disparate impact is a legal and fairness concept describing a situation where a model, algorithm, or policy disproportionately affects one demographic group compared to another…
Disparate Impact and Equalized Odds Fairness Audit Introduction & Motivation Disparate Impact and Equalized Odds Fairness Audit addresses a central problem in explainability…
dispatch rule performance drift prediction, dispatch rule performance, rule performance drift, performance drift prediction, dispatch rule, rule performance, performance drift
Dispatch Rule Performance Drift Prediction with Machine Learning Introduction & Motivation Dispatch Rule Performance Drift Prediction with Machine Learning addresses a central…
display backplane pixel defect prediction machine learning, display backplane, pixel defect prediction, tft, display backplane pixel defect prediction, display backplane pixel
Display Backplane Pixel Defect Prediction with Machine Learning Introduction & Motivation Display Backplane Pixel Defect Prediction with Machine Learning addresses a central…
display backplane tft uniformity prediction, display backplane tft, backplane tft uniformity, tft uniformity prediction, display backplane, backplane tft, tft uniformity
Display Backplane TFT Uniformity Prediction with Machine Learning Introduction & Motivation Display Backplane TFT Uniformity Prediction with Machine Learning addresses a central…
display driver ic gamma drift prediction, display driver ic, driver ic gamma, ic gamma drift, gamma drift prediction, display driver, driver ic, ic gamma, gamma drift
Display Driver IC Gamma Drift Prediction with Machine Learning Introduction & Motivation Display Driver IC Gamma Drift Prediction with Machine Learning addresses a central problem…
foundation model
DistilBERT is a smaller, faster, and lighter version of BERT produced through knowledge distillation — a model compression technique where a smaller "student" model is trained…
Distillation for Cross-Modal Transfer Introduction & Motivation Distillation for Cross-Modal Transfer addresses a central problem in reducing the size and cost of compression…
Distillation for Cross-Modal Transfer (Extended Study) Introduction & Motivation Distillation for Cross-Modal Transfer (Extended Study) addresses a central problem in reducing…
Distillation for Cross-Modal Transfer (Extended Study) Introduction & Motivation Distillation for Cross-Modal Transfer (Extended Study) addresses a central problem in reducing…
generative models
Distilled diffusion models is the student diffusion models trained to match outputs of a stronger multi-step teacher using fewer inference steps - they compress generation…
model distillation llm, teacher student llm, distillation training data, distilled language model
LLM Distillation is the process of training a smaller student language model to mimic the behavior of a larger teacher model — using the teacher's output distributions, reasoning…
model compression
Distilling reasoning ability is transferring reasoning behavior from a stronger teacher model into a smaller student model - The student is trained on teacher outputs, traces…
graph neural networks
DistMult is a knowledge graph embedding model based on bilinear factorization with diagonal relation matrices — scoring entity-relation-entity triples by computing…
graph neural networks
DistMult is a bilinear knowledge graph embedding model that scores triples with relation-specific diagonal matrices - It models compatibility through element-wise interactions…
distributed architecture latency reduction prediction, distributed architecture latency, architecture latency reduction, latency reduction prediction, latency reduction
Distributed Architecture Latency Reduction Prediction with Machine Learning Introduction & Motivation Distributed Architecture Latency Reduction Prediction with Machine Learning…
distributed batch normalization statistics and synchronization, distributed batch normalization, batch normalization statistics, normalization statistics synchronization
Distributed Batch Normalization Statistics and Synchronization Introduction & Motivation Distributed Batch Normalization Statistics and Synchronization addresses a central problem…
distributed caching redis, distributed caching, caching redis
Distributed Caching Redis Introduction & Motivation Distributed Caching Redis addresses a central problem in cloud process control and cache-hit-rate-optimization prediction: how…
coordinated checkpoint, restartable distributed jobs, state snapshot orchestration, failure recovery runtime
Distributed Checkpointing is the fault tolerance method that periodically snapshots distributed application state for restart after failures. What It Covers Core concept…
distributed clock synchronization, distributed clock, clock synchronization
Distributed Clock Synchronization Introduction & Motivation Distributed Clock Synchronization addresses a central problem in distributed-systems process control…
distributed configuration management, distributed configuration, configuration management
Distributed Configuration Management Introduction & Motivation Distributed Configuration Management addresses a central problem in programming process control…
paxos consensus algorithm, paxos consensus, consensus algorithm
Paxos Consensus Algorithm Introduction & Motivation Paxos Consensus Algorithm addresses a central problem in distributed-systems process control and consensus-latency-rounds…
paxos consensus algorithm, leader election distributed, log replication consensus, split brain prevention
Distributed Consensus Protocols are algorithms that enable a group of distributed nodes to agree on a single value or sequence of values despite node failures and network…
distributed control system, distributed control, control system
Distributed Control System Introduction & Motivation Distributed Control System addresses a central problem in control-systems process control and control-latency-milliseconds…
pytorch ddp training, gradient synchronization ddp, ddp communication overlap, multi gpu data parallel
Distributed Data Parallel (DDP) is the PyTorch framework for synchronous multi-GPU and multi-node training where each process maintains a full model replica and processes…
Distributed Data Parallel DDP with Ring-AllReduce Introduction & Motivation Distributed Data Parallel DDP with Ring-AllReduce addresses a central problem in optimization algorithm…
design, esd protection network, rail clamp, esd
Electrostatic Discharge (ESD) protection constitutes the dedicated on-chip network of high-current shunting devices engineered to safeguard sensitive gate dielectrics, thin tunnel…
distributed feedback laser mode hop prediction, distributed feedback laser, feedback laser mode, laser mode hop, mode hop prediction, distributed feedback, feedback laser
Distributed Feedback Laser Mode Hop Prediction with Machine Learning Introduction & Motivation Distributed Feedback Laser Mode Hop Prediction with Machine Learning addresses…
allreduce gradient synchronization, ring allreduce training, gradient compression communication, parameter server aggregation
Distributed Gradient Aggregation is the process of combining gradient updates computed independently across multiple workers (GPUs or nodes) during distributed deep learning…
gradient quantization, communication reduction training, sparse gradient
Distributed Gradient Compression is the technique of reducing the volume of gradient data communicated between workers during distributed deep learning training, addressing…
model serving distributed, inference parallelism, model sharding serving, inference load balancing
Distributed Inference Serving is the systems engineering discipline of deploying large neural network models across multiple GPUs, multiple machines, or heterogeneous accelerator…
distributed key generation, distributed key, key generation
Distributed Key Generation Introduction & Motivation Distributed Key Generation addresses a central problem in cryptography process control and key-generation-distributed-secret…
distributed ledger consensus protocol prediction, distributed ledger consensus, ledger consensus protocol, consensus protocol prediction, distributed ledger
Distributed Ledger Consensus Protocol Prediction with Machine Learning Introduction & Motivation Distributed Ledger Consensus Protocol Prediction with Machine Learning addresses…
distributed lock management, distributed lock, lock management
Distributed Lock Management Introduction & Motivation Distributed Lock Management addresses a central problem in distributed-systems process control and lock-acquisition-latency…
message passing model, halo exchange, ghost cells, parallel domain decomp, mpi domain decomposition
Distributed Memory Programming and Domain Decomposition is the parallel computing methodology where a large computational domain is partitioned into subdomains, each processed…
designing distributed power delivery networks for advanced nodes, designing distributed power, distributed power delivery, power delivery networks, delivery networks advanced
Designing distributed power delivery networks for advanced nodes Introduction & Motivation Designing distributed power delivery networks for advanced nodes addresses a central…
distributed real-time synchronization, distributed real-time, real-time synchronization
Distributed Real-Time Synchronization Introduction & Motivation Distributed Real-Time Synchronization addresses a central problem in real-time process control…
memory consistency model, coherence protocol, dsm system
Distributed Shared Memory (DSM) and Consistency Models define how memory operations across multiple processors are ordered and made visible to other processors, establishing…
distributed computing, cap theorem, consensus protocol, fault tolerance, distributed training
Distributed systems is the engineering discipline of building reliable, scalable computing services across multiple networked machines that coordinate to appear as a single…
distributed tracing correlation, distributed tracing, tracing correlation
Distributed Tracing Correlation Introduction & Motivation Distributed Tracing Correlation addresses a central problem in ml-ops process control…
distributed tracing latency, distributed tracing, tracing latency
Distributed Tracing Latency Introduction & Motivation Distributed Tracing Latency addresses a central problem in cloud process control and trace-sampling-rate-accuracy prediction…
ddp, fsdp
Distributed Training Training Paradigms Data Parallel (DDP) Each GPU has full model copy, processes different data: Model Parallel Split model across GPUs: Tensor Parallel: Split…
data parallel training, ddp, fsdp, tensor parallel, pipeline parallel, expert parallel, nccl
Distributed training coordinates optimization across multiple accelerators and often multiple nodes. Large language, vision, recommendation, scientific, and multimodal models…
data parallel training pytorch, ddp distributed data parallel, gradient synchronization training, data parallel scaling efficiency
Data Parallel Distributed Training is the most widely used strategy for scaling deep learning training across multiple GPUs or nodes by replicating the entire model on each…
horovod distributed, pytorch distributed, deepspeed training, distributed ml framework
Distributed Training Frameworks are the software systems that coordinate the training of large machine learning models across multiple GPUs and multiple machines — handling data…
hierarchical all-reduce algorithm, multi-level allreduce
Hierarchical all-reduce is the two-level collective strategy that reduces gradients within nodes first, then across nodes - it exploits faster intra-node links and minimizes…