27,049 technical terms and definitions
semiconductor industry carbon neutrality goals, semiconductor industry carbon, industry carbon neutrality, carbon neutrality goals, semiconductor industry, industry carbon, carbon neutrality
Semiconductor Industry Carbon Neutrality Goals Introduction & Motivation Semiconductor Industry Carbon Neutrality Goals addresses a central problem in sustainability process…
industry carbon neutral, industry carbon, carbon neutral
Industry Carbon Neutral Introduction & Motivation Industry Carbon Neutral addresses a central problem in sustainability process control and year prediction: how to Predict year…
industry carbon neutral goals, industry carbon neutral, carbon neutral goals, industry carbon, carbon neutral, neutral goals
Industry Carbon Neutral Goals Introduction & Motivation Industry Carbon Neutral Goals addresses a central problem in sustainability process control and target-year prediction: how…
manufacturing
Infant defect is a manufacturing defect caught during early testing phases — typically detected during wafer probe, package test, or burn-in, representing defects that would cause…
reliability, latent defect, burn-in, HTOL, bathtub curve, electrical screening, manufacturing defect root cause, factory scrap vs field failure cost, accelerated stress testing
Infant mortality is the early-life failure pattern where devices carrying latent manufacturing defects fail disproportionately soon after deployment — the first…
business & standards
Infant Mortality is the early-life failure regime driven by latent manufacturing and assembly defects - It is a core method in advanced semiconductor reliability engineering…
reliability
Infant mortality period is the early-life interval where failure rate is elevated because latent manufacturing defects surface soon after operation begins - Early defects are…
infant mortality screening prediction, infant mortality screening, mortality screening prediction, infant mortality, mortality screening, screening prediction
Infant Mortality Screening Prediction with Machine Learning Introduction & Motivation Infant Mortality Screening Prediction with Machine Learning addresses a central problem…
serving, deploy, llm serving, vllm, tgi, api, throughput, latency
LLM inference is the serving side of a large language model: taking a trained model and running its forward pass to answer real user requests, optimized for latency, throughput…
fast inference methods, model serving optimization, latency reduction inference, throughput optimization serving
Inference Acceleration Techniques are the specialized methods for reducing neural network inference time and increasing serving throughput — including algorithmic optimizations…
edge inference chip, neural engine int4, hardware sparsity support, always on ai chip, mcm edge ai chip
An inference chip is an accelerator optimized to run a trained neural network with low latency, high throughput, or low energy per request rather than to compute training…
deployment
Inference cost is the computational expense of generating outputs from a trained model during deployment, often exceeding training cost over the model's lifetime and driving major…
inference engine throughput prediction, inference engine throughput, engine throughput prediction, inference engine, engine throughput, throughput prediction
Inference Engine Throughput Prediction with Machine Learning Introduction & Motivation Inference Engine Throughput Prediction with Machine Learning addresses a central problem…
inference optimization and latency, inference optimization latency, inference optimization, optimization latency
Inference Optimization and Latency Introduction & Motivation Inference Optimization and Latency addresses a central problem in inference process control and latency-reduction…
inference optimization through quantization, inference optimization through, optimization through quantization, inference optimization, optimization through, through quantization
Inference Optimization through Quantization Introduction & Motivation Inference Optimization through Quantization addresses a central problem in ml-inference process control…
inference serving throughput and batching, inference serving throughput, serving throughput batching, inference serving, serving throughput, throughput batching
Inference Serving Throughput and Batching Introduction & Motivation Inference Serving Throughput and Batching addresses a central problem in ml-inference process control…
point estimation, point estimate, parameter estimation, central limit theorem, null hypothesis, p value
Inference statistics is the branch of statistics that uses a sample of data to make probability-based statements about the population from which the sample was drawn, and it is…
architecture
Infini-attention is the long-context attention approach that combines local attention with compressed memory mechanisms to approximate effectively unbounded context handling - it…
rdma, network, hpc, mellanox, cluster, latency
InfiniBand is a high-bandwidth, low-latency networking technology using RDMA for GPU cluster communication — providing 200-400 Gbps per port with microsecond latencies, InfiniBand…
infrastructure
RDMA (Remote Direct Memory Access) lets one computer's network card place data directly into another computer's memory without involving either machine's CPU or operating-system…
ib verbs programming, infiniband qp connection, infiniband subnet manager, ib transport layer
InfiniBand Architecture is the high-performance networking standard designed for low-latency, high-bandwidth interconnects in HPC and AI clusters — providing hardware-offloaded…
supply chain & logistics
Infinite Capacity Scheduling is scheduling that ignores capacity constraints to prioritize demand and due-date visibility - It provides a quick demand picture before feasibility…
theory
The Infinite-Width Limit is a theoretical idealization in deep learning where the number of neurons in each hidden layer is taken to infinity — revealing that at this limit…
interpretability
Influence Functions are a technique from robust statistics applied to ML that measures how each training example affects a model's prediction — quantifying the change in a test…
explainable ai
Influence Functions are a technique from robust statistics applied to ML that measures how each training example affects a model's prediction — quantifying the change in a test…
Influence Functions for Training Data Attribution Introduction & Motivation Influence Functions for Training Data Attribution addresses a central problem in interpretability…
Influence Functions for Training Data Attribution (Extended Study) Introduction & Motivation Influence Functions for Training Data Attribution (Extended Study) addresses a central…
Influence Functions for Training Data Attribution (Extended Study) Introduction & Motivation Influence Functions for Training Data Attribution (Extended Study) addresses a central…
Influence Functions for Explanation Introduction & Motivation Influence Functions for Explanation addresses a central problem in explainability interpretation and model…
recommendation systems
Influence Functions Rec is training-data attribution methods estimating how individual examples affect recommendation outputs. - They trace problematic or beneficial…
Influence Functions for Training Sample Attribution Introduction & Motivation Influence Functions for Training Sample Attribution addresses a central problem in explainability…
Influence Maximization in Graphs Introduction & Motivation Influence Maximization in Graphs addresses a central problem in graph network representation…
recommendation systems
Influence Propagation is modeling how preferences or behaviors spread across user networks over time - It helps predict adoption and recommendation impact beyond isolated…
info fan-out package warpage prediction, info fan-out package, fan-out package warpage, package warpage prediction, info fan-out, fan-out package, package warpage, warpage prediction
InFO Fan-Out Package Warpage Prediction with Machine Learning Introduction & Motivation InFO Fan-Out Package Warpage Prediction with Machine Learning addresses a central problem…
info, integrated fan-out, advanced packaging
Integrated Fan-Out is TSMC's fan-out wafer-level packaging technology that redistributes die I/O to a larger area without a traditional package substrate. First used in Apple's…
disentangled gan, mutual information gan, controllable image generation, unsupervised disentanglement, generative adversarial network
InfoGAN is a generative adversarial network variant that learns disentangled and interpretable latent factors by maximizing mutual information between selected latent codes…
content creation
Infographic generation is the use of AI to automatically create visual information graphics — transforming data, statistics, processes, and concepts into compelling visual…
self-supervised learning
InfoNCE Loss is a contrastive learning objective that estimates mutual information between representations — by training a model to identify the correct "positive" sample from…
Information Criteria for Model Selection Introduction & Motivation Information Criteria for Model Selection addresses a central problem in timeseries forecasting…
information extraction structured, information extraction, extraction structured
Information Extraction Structured Introduction & Motivation Information Extraction Structured addresses a central problem in nlp process control…
reinforcement learning
Information Gain Exploration is an exploration strategy that rewards actions that maximize the information gained about the environment — the agent seeks states and actions that…
information retrieval bm25, information retrieval, retrieval bm25
Information Retrieval BM25 Introduction & Motivation Information Retrieval BM25 addresses a central problem in systems process control and relevance-ranking-effectiveness…
information retrieval ranking, information retrieval, retrieval ranking
Information Retrieval Ranking Introduction & Motivation Information Retrieval Ranking addresses a central problem in nlp process control and information-retrieval-document-ranking…
information retrieval relevance prediction, information retrieval relevance, retrieval relevance prediction, information retrieval, retrieval relevance, relevance prediction
Information Retrieval Relevance Prediction with Machine Learning Introduction & Motivation Information Retrieval Relevance Prediction with Machine Learning addresses a central…
entropy, mutual information, channel capacity, shannon theory, kl divergence
Information theory quantifies uncertainty, information, coding, and fundamental communication limits. It provides the language for compression, channel coding, storage, networks…
Information Theory: Entropy, Channel Capacity, and Coding Theorems Information theory, founded by Claude Shannon in 1948, provides the mathematical framework for quantifying…
Information Theory, Entropy, Divergence, and Channel Capacity 1. Information as uncertainty reduction Information theory quantifies uncertainty, compression, communication…
Information Theory: Foundations and Machine Learning Applications 1. Introduction to Information Theory Information theory provides mathematical foundations for quantifying…
time series models
Informer is a long-sequence transformer for time-series forecasting using probabilistic sparse attention. - It reduces quadratic attention cost so long-context forecasting becomes…
Informer with ProbSparse Self-Attention Mechanism Introduction & Motivation Informer with ProbSparse Self-Attention Mechanism addresses a central problem in timeseries forecasting…