EXPLORE / 06
Terms index
Specialized AI and software-development terms with concise explanations
RECORDS
Entity records
3371 records · 43/85
- 1681
AMX
An Intel processor instruction set designed to accelerate deep learning matrix operations.
Website pending - 1682
Dynamic Batching
A technique that groups requests into batches based on arrival time and length to improve throughput.
Website pending - 1683
Zero-shot Classification
Ability to classify new categories without specific training data for those classes
Website pending - 1684
Inference Deployment
The process of packaging trained models as services to handle real-time data requests
Website pending - 1685
Deep Learning Container
Standardized Docker images pre-installed with deep learning frameworks and dependencies.
Website pending - 1686
Heterogeneous Hardware
A mixed system composed of computing devices with different performances and architectures.
Website pending - 1687
Pruning
Removing insignificant connections or neurons from neural networks to simplify model structure
Website pending - 1688
SQuAD
Stanford Question Answering Dataset, commonly used to evaluate machine reading comprehension
Website pending - 1689
Intelligence Processing Unit (IPU)
A processor architecture designed by Graphcore specifically for machine learning workloads
Website pending - 1690
Web Demo
A web interactive interface for visually demonstrating AI model input-output effects
Website pending - 1691
Spaces
A cloud platform for deploying and sharing machine learning demo applications.
Website pending - 1692
CLIP
A model architecture that aligns cross-modal semantics through contrastive learning on large-scale image-text pairs
Website pending - 1693
Machine Learning as Code
Treating ML workflows as software engineering, emphasizing version control and automation
Website pending - 1694
Generative Language Model
Neural networks capable of predicting and generating text sequences based on context.
Website pending - 1695
AVX512
An Intel extension supporting 512-bit wide vector operations for accelerated computing.
Website pending - 1696
VNNI
CPU instruction set extension designed to accelerate integer-quantized neural network inference
Website pending - 1697
Pretrained Model
Model pre-trained on large datasets to learn general features
Website pending - 1698
oneAPI Deep Neural Network Library
Intel's library for accelerating deep learning inference and training
Website pending - 1699
oneDNN
An open-source math kernel library provided by Intel for optimizing deep neural networks.
Website pending - 1700
EDA
Initial investigation of data characteristics via visualization and statistics
Website pending - 1701
Dataset Documentation
Standardized metadata describing a dataset's source, structure, and intended use.
Website pending - 1702
normalized Pointwise Mutual Information
A normalized statistical measure quantifying the strength of co-occurrence between two words.
Website pending - 1703
ML-Agents
An open-source toolkit from Unity for training intelligent agents.
Website pending - 1704
Latent Bottleneck
An architectural design that compresses high-dimensional inputs into a fixed-size latent representation to decouple input scale from computation cost
Website pending - 1705
Cross-Attention
An attention mechanism allowing query vectors to attend to key-value pairs from different sources
Website pending - 1706
ML Interface
Tools for rapidly building frontends to interact with and showcase ML models
Website pending - 1707
N-gram LM
A statistical language model predicting the next word based on the previous n-1 words
Website pending - 1708
WER
Metric measuring ASR accuracy by summing substitutions, insertions, and deletions
Website pending - 1709
LM-boosted decoding
Technique introducing an external language model during decoding to correct probability distributions
Website pending - 1710
Sliding Window
A strategy processing continuous data streams by moving a fixed-size window step-by-step.
Website pending - 1711
CTC
A loss function for sequence labeling that allows output length to differ from input without explicit alignment.
Website pending - 1712
Bidirectional Encoder Representations
A language model architecture that considers both left and right context simultaneously.
Website pending - 1713
Constrained Decoding
Applying rules during generation to ensure output meets specific syntactic, lexical, or semantic requirements
Website pending - 1714
Beam Search
A heuristic search algorithm that retains the top-k most probable sequences to balance efficiency and quality
Website pending - 1715
Multimodal Retrieval
Technology matching similarity across different modalities like text and images
Website pending - 1716
Semantic Segmentation
Task of classifying each pixel in an image
Website pending - 1717
Ethical AI
Ensuring AI systems are designed and used in accordance with moral standards and social values
Website pending - 1718
Offline Reinforcement Learning
Training policies using pre-collected datasets without real-time environment interaction
Website pending - 1719
AI Ethics
Study of moral principles, fairness, and social impacts in AI development and application
Website pending - 1720
Data Bias
Systematic errors or imbalances in training data that cause unfair model outputs
Website pending