glit
neural architecture search
GLiT is global-local integrated transformer architecture search for hybrid convolution-attention models. - It balances long-range attention and local convolutional bias in one…
1,045 technical terms and definitions
neural architecture search
GLiT is global-local integrated transformer architecture search for hybrid convolution-attention models. - It balances long-range attention and local convolutional bias in one…
voltage clock glitching, differential fault analysis, fault injection countermeasure
Glitch Attack and Fault Injection A side-channel attack passively listens to a chip's power or timing to extract a secret it's already computing correctly. A glitch attack does…
clock switching glitch, clock mux, clock domain crossing clock tree, pll bypass switching, clock gating wakeup
A glitch-free clock multiplexer is what a chip needs whenever it switches between two clock sources that are not already synchronized to each other — a plain combinational…
glob-top encapsulation void prediction, glob-top encapsulation void, encapsulation void prediction, glob-top encapsulation, encapsulation void, void prediction
Glob-Top Encapsulation Void Prediction with Machine Learning Introduction & Motivation Glob-Top Encapsulation Void Prediction with Machine Learning addresses a central problem…
self-supervised learning
Global and local views in self-supervised learning are the paired perspective constraints where full-scene crops and part-level crops must map to consistent semantic…
distributed training
Global batch is the total number of samples contributing to one optimizer update across all devices and accumulation passes - it is the optimizer-facing batch size that determines…
computer vision
Global Context (GC) Block is a simplified and efficient version of the Non-Local block — observing that Non-Local attention maps are nearly identical for different query…
metrology
Spectroscopic ellipsometry and inline optical wafer metrology constitute the non-destructive physical measurement and defect detection disciplines that govern yield control across…
gpu dram, cuda memory
Global Memory in GPU architecture refers to the main off-chip DRAM accessible by all threads across all streaming multiprocessors (SMs). What Is Global Memory? Capacity: 4GB…
graph neural networks
Global pooling is the aggregation of all node embeddings into a single graph-level representation - Operations such as sum, mean, max, or attention pooling compress variable-size…
routing algorithm, routing resource, maze routing, routing stages
Global Routing and Detail Routing are the two-stage process that determines the physical paths of all metal wires connecting logic cells on a chip — where global routing plans…
global routing layer utilization congestion prediction, global routing layer, routing layer utilization, layer utilization congestion, utilization congestion prediction
Global Routing Layer Utilization Congestion Prediction with Machine Learning Introduction & Motivation Global Routing Layer Utilization Congestion Prediction with Machine Learning…
SHAP Feature Dependence Plots with Interaction Coloring Introduction & Motivation SHAP Feature Dependence Plots with Interaction Coloring addresses a central problem…
global shutter pixel architecture, parasitic light sensitivity cmos sensor
A global shutter CMOS pixel adds a second storage node inside every pixel so the whole array captures the same instant, trading away some of the light-sensing area that a cheaper…
global shutter pixel crosstalk prediction, global shutter pixel, shutter pixel crosstalk, pixel crosstalk prediction, global shutter, shutter pixel, pixel crosstalk
Global Shutter Pixel Crosstalk Prediction with Machine Learning Introduction & Motivation Global Shutter Pixel Crosstalk Prediction with Machine Learning addresses a central…
Global Surrogate Model Explanations Introduction & Motivation Global Surrogate Model Explanations addresses a central problem in interpretability and explanation of xai…
Global Surrogate Model Explanations (Extended Study) Introduction & Motivation Global Surrogate Model Explanations (Extended Study) addresses a central problem in interpretability…
Global Surrogate Model Explanations (Extended Study) Introduction & Motivation Global Surrogate Model Explanations (Extended Study) addresses a central problem in interpretability…
design & verification
Global Variation is die-to-die or wafer-level variation components that affect broad regions similarly - It drives systematic shifts across many paths or devices at once. What Is…
GlobalFoundries GF, GF foundry, 22FDX, GlobalFoundries silicon photonics, GlobalFoundries RF
GlobalFoundries (GF) is a leading global pure-play semiconductor foundry specializing in feature-rich, differentiated process technologies across automotive, smart mobile devices…
gals, design
Globally asynchronous locally synchronous (GALS) is the architecture pattern where each subsystem runs with its own local clock while inter-domain communication uses asynchronous…
infrastructure
Gloo is the collective communication backend designed for flexible CPU and network environments - it provides portable distributed primitives and often serves as a fallback…
define terms, jargon, concept
AI/ML Glossary Core LLM Concepts A-F Term Definition Alignment Training AI to be helpful, harmless, and honest Attention Mechanism for tokens to consider other tokens BPE Byte…
manufacturing operations
Glove Box is a sealed handling enclosure that maintains inert or ultra-dry atmospheres during sensitive wafer operations - It is a core method in modern semiconductor wafer…
gdms, bulk trace analysis
Read glow discharge mass spectrometry through a bulk-depth, sputter-coupled lens rather than a solution-digestion lens. This perspective shift transforms how we interpret…
Glow Invertible Network Introduction & Motivation Glow Invertible Network addresses a central problem in generative generation and invertibility-preservation synthesis: how…
audio & speech
GlowTTS is a flow-based text-to-speech model with monotonic alignment search. - It combines invertible generative modeling with robust alignment for parallel speech synthesis.…
glu, architecture
GLU (Gated Linear Unit) is a gating mechanism that splits the input into two halves — one serves as the "content" and the other as the "gate" — implemented as where is…
glu, neural architecture
Activation functions are the reason depth means anything. Stack a hundred linear layers with no nonlinearity between them and the whole thing collapses algebraically into a single…
glue, evaluation
GLUE is a benchmark collection for evaluating general language understanding across multiple classic NLP tasks - It is a core method in modern AI evaluation and safety execution…
glue, evaluation
GLUE (General Language Understanding Evaluation) is a collection of 9 diverse NLU tasks (QA, NLI, Sentiment, Paraphrasing) combined into a single benchmark metric — introduced…
glue, general language understanding evaluation, evaluation
GLUE (General Language Understanding Evaluation) is a benchmark suite of nine natural language understanding tasks designed to evaluate and compare the general linguistic…
gm over id, transconductance efficiency, moderate inversion mosfet, analog sizing methodology, weak inversion strong inversion
The gm/Id methodology is what analog designers reach for once the square-law MOSFET equation from a textbook stops matching the transistors an actual process delivers. Modern…
gmf, recommendation systems
GMF is generalized matrix factorization that models user-item interaction with learned element-wise embedding products - A neural output layer maps multiplicative latent…
computer vision
gMLP is the gated MLP architecture that injects spatial interaction through a Spatial Gating Unit while keeping the model attention free - it multiplies one feature branch by…
gmlp, gated mlp, llm architecture
gMLP (Gated MLP) is an MLP-based architecture that introduces a gating mechanism to the spatial mixing operation, using a Spatial Gating Unit (SGU) that modulates token…
gmt, graph neural networks
GMT is graph multiset transformer pooling for hierarchical graph-level representation learning. - It pools node sets into compact graph embeddings using learned attention-based…
gnn, graph neural networks
GNN Expressiveness is the ability of a graph neural network to distinguish structures and represent target graph functions - It determines whether architecture choices can…
higher-order graph neural networks, graph neural networks
Higher-Order GNN is a graph model family that propagates information over tuples or subgraphs beyond first-order neighbors - It improves structural sensitivity by encoding…
reinforcement learning advanced
Go-Explore is an exploration framework that returns to promising states and then explores outward repeatedly - Archive and return mechanisms preserve discovered stepping stones…
ai agents
Goal Achievement is the verification process that confirms an agent has satisfied the intended objective - It is a core method in modern semiconductor AI-agent engineering…
Goal-Conditioned Reinforcement Learning Introduction & Motivation Goal-Conditioned Reinforcement Learning addresses a central problem in reinforcement policy learning…
reinforcement learning
Goal-Conditioned RL is a reinforcement learning framework where the policy takes both a state and a goal as input — learns to reach any specified goal , enabling a single policy…
reinforcement learning advanced
Goal-Conditioned RL is reinforcement learning where policies are conditioned on explicit target goals. - It enables one agent to solve many objectives by changing goal inputs…
CoinRun, Langosco et al. 2022, Shah et al. 2022, inner alignment, distribution shift, capability generalization, mesa-optimization
Goal misgeneralization is a failure mode in which a learned system keeps its competence when the environment changes but pursues the wrong goal, one that agreed with the intended…
ai agents
Goal Stack is a last-in-first-out structure that tracks active goals and nested subgoals during execution - It is a core method in modern semiconductor AI-agent planning…
goal test, goal formulation, goal-based agent, STRIPS goals, multiple goals, intention, agent goals
A goal state is a state of the world in which the problem solver's objective is satisfied, and the goal of a search problem is the set of all such states. It is one of the five…
arithmetic, fine tune
GOAT (Good at Arithmetic Tasks) is a Llama-based language model fine-tuned specifically for arithmetic calculation, demonstrating that targeted synthetic data training can solve…
code ai
God Class Detection identifies the anti-pattern where a single class accumulates so many responsibilities, dependencies, and lines of code that it effectively controls…
golang concurrency goroutines, golang concurrency, concurrency goroutines
Golang Concurrency Goroutines Introduction & Motivation Golang Concurrency Goroutines addresses a central problem in programming process control…