988 technical terms and definitions
instrumentation profiling sampling, instrumentation profiling, profiling sampling
Instrumentation Profiling Sampling Introduction & Motivation Instrumentation Profiling Sampling addresses a central problem in programming process control…
weak joint, solder volume, fatigue crack growth, fine pitch package, SPI underprint detection, pad contamination, rework variability, thermal cycling failure, low stand-off package
Insufficient solder is the condition where a joint receives less solder volume than its design requires, producing a weak fillet with a thinner cross-section than intended…
IGBT, hybrid power device, motor drives, traction, grid power conversion
The insulated-gate bipolar transistor, abbreviated IGBT, is a power semiconductor device that merges the voltage-driven insulated gate of a MOSFET with the efficient high-power…
igbt switching loss prediction, igbt switching loss, switching loss prediction, igbt switching, switching loss, loss prediction
IGBT Switching Loss Prediction with Machine Learning Introduction & Motivation IGBT Switching Loss Prediction with Machine Learning addresses a central problem in insulated gate…
electrical insulator, dielectric, gate dielectric, silicon dioxide, high-k dielectric, breakdown field, dielectric breakdown
An insulator is a material that, under ordinary electric fields, passes almost no current because its electrons are held in filled energy states separated from the next available…
insulin pump sensor drift prediction, insulin pump sensor, pump sensor drift, sensor drift prediction, insulin pump, pump sensor, sensor drift, drift prediction
Insulin Pump Sensor Drift Prediction with Machine Learning Introduction & Motivation Insulin Pump Sensor Drift Prediction with Machine Learning addresses a central problem…
4bit, aggressive
INT4 (4-bit integer) quantization aggressively compresses model weights to 4 bits per parameter, achieving 8× memory reduction versus FP32 and enabling large models to run on…
quantization, integer
INT8 quantization represents neural network weights and activations using 8-bit integers instead of 32-bit floats, achieving 4× memory reduction and 2-4× inference speedup…
deployment
Integer-Only Inference is a deployment strategy where the entire neural network forward pass uses integer arithmetic exclusively — eliminating all floating-point operations…
integer programming branch-bound prediction, integer programming branch-bound, programming branch-bound prediction, integer programming, programming branch-bound
Integer Programming Branch-Bound Prediction with Machine Learning Introduction & Motivation Integer Programming Branch-Bound Prediction with Machine Learning addresses a central…
IC, microchip, silicon chip, Jack Kilby, Robert Noyce, planar process, Moore's law
An integrated circuit is a complete electronic circuit, with its transistors, resistors, capacitors and the wiring between them, fabricated together on a single small piece…
monolithic integrated circuit, kilby noyce integrated circuit, junction isolation integrated circuit, photolithographic interconnect
The Integrated Circuit: From Hand-Wired Germanium Bar to Photolithographically Printed Interconnect The planar process solved the junction-edge exposure problem and, as a side…
integrated clock gating cell, icg, design
An Integrated Clock Gating cell (ICG) is a specialized standard cell that combines a latch, AND gate, and clock buffer into a single optimized cell — providing glitch-free clock…
idpc, idpc-stem, integrated dpc, integrated differential phase contrast stem, light element stem imaging, idpc semiconductor interface
High-angle annular dark-field STEM makes heavy atomic columns easy to recognize because strong high-angle scattering creates intuitive bright contrast, but that same weighting can…
attribution, baseline
Integrated Gradients is the axiomatic attribution method that explains neural network predictions by summing gradients along the path from a baseline input to the actual input…
Integrated Gradients Introduction & Motivation Integrated Gradients addresses a central problem in interpretability and explanation of xai predictions: how to Produce…
explainable ai
Integrated Gradients is an attribution method that assigns importance scores to input features by accumulating gradients along a straight-line path from a baseline to the actual…
interpretability
Integrated Gradients is an attribution method that integrates input gradients along a path from baseline to actual input - It reduces gradient saturation issues and provides…
Integrated Gradients Axiomatic Neural Attribution Introduction & Motivation Integrated Gradients Axiomatic Neural Attribution addresses a central problem in explainability…
Integrated Gradients Attribution Introduction & Motivation Integrated Gradients Attribution addresses a central problem in explainability interpretation and model understanding…
Integrated Gradients (Extended Study) Introduction & Motivation Integrated Gradients (Extended Study) addresses a central problem in interpretability and explanation of xai…
Integrated Gradients (Extended Study) Introduction & Motivation Integrated Gradients (Extended Study) addresses a central problem in interpretability and explanation of xai…
Integrated Gradients (Extended Study) Introduction & Motivation Integrated Gradients (Extended Study) addresses a central problem in interpretability and explanation of xai…
explainable ai
Integrated Hessians is an attribution method that captures feature interactions by integrating second-order derivatives (the Hessian) along a path from a baseline to the input…
Integrated Hessians for Axiomatic Feature Interactions Introduction & Motivation Integrated Hessians for Axiomatic Feature Interactions addresses a central problem…
I2L, bipolar logic, merged transistor logic, current injection logic, dense bipolar
Integrated injection logic is a bipolar digital logic family developed in the early 1970s that achieved high density and low power for bipolar circuits by merging transistors…
metrology
Integrated metrology places measurement capability inside a process chamber, on a cluster-tool platform, or immediately adjacent to the production module so results are available…
integrated passive device tolerance drift prediction, integrated passive device, passive device tolerance, device tolerance drift, tolerance drift prediction
Integrated Passive Device Tolerance Drift Prediction with Machine Learning Introduction & Motivation Integrated Passive Device Tolerance Drift Prediction with Machine Learning…
integration-level defect and yield loss prediction, integration-level defect yield, defect yield loss, yield loss prediction, integration-level defect, defect yield, yield loss
Integration-Level Defect and Yield Loss Prediction with Machine Learning Introduction & Motivation Integration-Level Defect and Yield Loss Prediction with Machine Learning…
integrator capacitor leakage current prediction, integrator capacitor leakage, capacitor leakage current, leakage current prediction, integrator capacitor
Integrator Capacitor Leakage Current Prediction with Machine Learning Introduction & Motivation Integrator Capacitor Leakage Current Prediction with Machine Learning addresses…
integrator windup mitigation effectiveness prediction, integrator windup mitigation, windup mitigation effectiveness, mitigation effectiveness prediction, integrator windup
Integrator Windup Mitigation Effectiveness Prediction with Machine Learning Introduction & Motivation Integrator Windup Mitigation Effectiveness Prediction with Machine Learning…
Intel CPU, Intel Core, Intel Xeon, Intel Gaudi, Intel product portfolio, intel, what is intel, about intel, intel company
Intel processor. refers to Intel’s broad compute portfolio centered on x86 client and server CPUs and increasingly spanning tiled SoCs, AI accelerators, networking, FPGA products…
intel 10 nm delay, what is intel 10 nm delay
Intel’s 10 nm delay refers to slippage in its own process and product ramp schedule. The numerical node name belongs to Intel’s technology program and should not be equated…
intel 14a, what is intel 14a
An Intel development platform in the angstrom roadmap. Intel 14A is an advanced process platform that follows Intel 18A in the company’s published technology roadmap. Intel…
intel atom, what is intel atom
Intel announced the Atom brand for a low-power processor family in March 2008. The announcement targeted mobile internet devices and inexpensive internet-oriented computers. Atom…
intel core 2, what is intel core 2
Intel Core 2 is a processor family introduced in 2006 around the Intel Core microarchitecture. Intel’s July 27 announcement covered Core 2 Duo and Core 2 Extreme products.…
intel fdiv bug, what is intel fdiv bug
The Intel FDIV bug was a floating-point division defect in affected early Pentium processors. It became a major public issue in 1994. The problem concerned incorrect results…
intel inside, what is intel inside
Intel Inside is an ingredient-branding campaign launched in 1991. The idea was to make the processor supplier visible to people buying complete computers. Intel’s historical…
intel pentium, what is intel pentium
The original Intel Pentium was the P5-generation x86 processor introduced in 1993. Intel’s historical reference lists initial 60 and 66 MHz parts with 3.1 million transistors on…
intel tick-tock, what is intel tick-tock
Intel tick-tock was a technology-development cadence alternating process and microarchitecture advances. Intel’s 2007 annual report described introducing a new microarchitecture…
ip ownership, who owns the ip, ip rights, ownership
Customer owns all custom intellectual property we develop for their projects — our standard agreement grants customers full ownership of custom RTL code, verification…
ip protection, patent, trade secret, nda, confidentiality
We provide comprehensive IP protection to safeguard your intellectual property throughout our engagement — offering NDA agreements, secure facilities, access controls, IP…
I. J. Good, ultraintelligent machine, technological singularity, Vernor Vinge, Superintelligence Bostrom, Speculations Concerning the First Ultraintelligent Machine
An intelligence explosion is a hypothesized runaway process in which an artificial intelligence that is better than humans at designing intelligent systems builds a better…
rational agent, Russell and Norvig, Artificial Intelligence: A Modern Approach 1995, PEAS, sensors and actuators, agent function, llm agent
An intelligent agent is anything that perceives its environment through sensors and acts upon that environment through actuators, chosen so that its behavior achieves good…
intelligent sampling inline inspection, intelligent sampling inline, sampling inline inspection, intelligent sampling, sampling inline, inline inspection
Intelligent Sampling Inline Inspection with Machine Learning Introduction & Motivation Intelligent Sampling Inline Inspection with Machine Learning addresses a central problem…
dialogue
Intent recognition (also called intent classification or intent detection) is the NLP task of identifying the purpose or goal behind a user's message in a conversational system.…
dialogue
Intent recognition is classification of the user goal behind an utterance - Intent models map text to actionable categories that trigger suitable dialogue policies. What Is Intent…
evaluation
Inter-annotator agreement (IAA) measures how consistently multiple human evaluators assign the same labels or scores to the same data. It is a critical quality metric for any…
evaluation
Inter-Annotator Agreement is the degree to which multiple human raters provide consistent labels on the same data - It is a core method in modern AI evaluation and governance…
signal & power integrity
Inter-Pair Skew is timing mismatch among multiple related differential pairs in a bus or lane group - It affects lane alignment and deskew complexity in parallel high-speed…