Disentangled Representations
representation learning
Disentangled Representations are learned data representations where independent, interpretable factors of variation in the data (such as shape, color, size, position, style) are…
1,686 technical terms and definitions
representation learning
Disentangled Representations are learned data representations where independent, interpretable factors of variation in the data (such as shape, color, size, position, style) are…
multimodal ai
Disentanglement is learning representations where independent latent factors correspond to separate semantic attributes - It improves interpretability and controllability…
cmp dishing, copper dishing, metal dishing, dishing and erosion, dual damascene dishing, cmp planarization, cmp
CMP dishing is the undesirable formation of a concave recessed surface profile in metal interconnect lines during chemical mechanical planarization, occurring when the polishing…
nlp
Disinformation detection is the AI/NLP task of identifying deliberately false information created and spread with the intent to deceive, manipulate, or cause harm. Unlike…
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…
process
Dislocation Loops are closed circular line defects enclosing an extra half-plane or missing half-plane of atoms in the crystal lattice — formed by condensation…
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…
production
Dispatching is the decision logic that determines which waiting lot a tool should process next. Good dispatching rules maximize throughput and on-time delivery while respecting…
operations
Dispatching rules is the decision logic that determines which waiting lot a tool processes next under competing priorities and constraints - rule quality directly affects…
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, ddic, lcd driver, oled driver, source driver, gate driver, timing controller
Display driver converts digital pixel data and timing into the voltages or currents that address a display panel. Display driver ICs determine refresh, brightness uniformity…
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…
quality
Disposition Decision is the formal engineering and quality judgment that determines the fate of non-conforming semiconductor material — evaluating whether held wafer lots should…
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…
distilbert knowledge distillation, distilbert knowledge, knowledge distillation, bert ce glue kl ml nlp
DistilBERT - Knowledge Distillation Introduction & Motivation DistilBERT: distilled BERT via knowledge distillation. 40% smaller, 60% faster than BERT. Applications: mobile…
student teacher, compress
Knowledge distillation is a model-compression technique in which a small, cheap "student" model is trained to reproduce the behavior of a large, accurate "teacher" model. Instead…
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…
soft target, kd, temperature, kl divergence
Knowledge distillation loss matches student model outputs to teacher model soft targets — using the probability distributions (soft labels) from a larger teacher model rather than…
computer vision
Distillation token is a special learnable embedding used in DeiT (Data-efficient Image Transformers) that learns from a CNN teacher model's predictions — enabling Vision…
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…
reinforcement learning advanced
Distral is distillation and transfer framework for multi-task reinforcement learning with shared policy priors. - It encourages task-specific agents to stay near a common…
hash, table, DHT, peer-to-peer, consistent, hashing
Distributed Hash Table DHT Parallel is a decentralized data structure storing key-value pairs across network of machines without central server, enabling scalable, fault-tolerant…
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…
mapreduce paradigm, spark parallel, dask distributed, parallel data processing
Distributed Computing Frameworks are the software platforms that abstract the complexity of executing parallel computations across clusters of networked machines — handling task…
distributed configuration management, distributed configuration, configuration management
Distributed Configuration Management Introduction & Motivation Distributed Configuration Management addresses a central problem in programming process control…
raft algorithm, paxos, leader election
Distributed Consensus — algorithms that ensure multiple nodes in a distributed system agree on a single value or sequence of values, despite network failures and delays, forming…
raft algorithm, paxos consensus, leader election distributed, consensus protocol
Distributed Consensus is the fundamental problem of getting multiple distributed nodes to agree on a single value or sequence of values — despite node failures and network…
Raft optimization, Multi-Paxos, consensus performance
Advanced Distributed Consensus covers optimized implementations and variants of consensus protocols (Raft, Multi-Paxos, and beyond) that achieve high throughput and low latency…
paxos raft protocol, distributed agreement, consensus replication, fault tolerant consensus
Distributed Consensus Algorithms are protocols that enable multiple nodes in a distributed system to agree on a single value or sequence of values despite node failures…
paxos raft leader election, byzantine fault tolerance, state machine replication consensus, two phase commit distributed
Distributed Consensus Algorithms are protocols that enable multiple nodes in a distributed system to agree on a single value or sequence of values despite node failures…
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…
raft consensus, paxos consensus, distributed agreement, consensus algorithm
Distributed Consensus Protocols are the algorithms that enable a group of distributed nodes to agree on a single value or sequence of operations despite node failures and network…
paxos, raft consensus, byzantine fault tolerance, consensus algorithm, distributed agreement
Distributed Consensus Protocols is the family of algorithms that enable a group of distributed processes to agree on a single value or sequence of decisions despite individual…
paxos consensus algorithm, leader election distributed, replicated state machine, fault tolerant consensus
Distributed Consensus Protocols — Raft and Paxos — Distributed consensus protocols enable a group of networked nodes to agree on a single value or sequence of values despite node…
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…