TopAIToolsTopAITools

Glossary

0-9
0-shot learning1-shot learning2-stage detector3D convolution4D data5G + AI6DoF pose estimation7D representation8-bit quantization9-layer network
A
AGI / Artificial General IntelligenceAlgorithmArtificial Intelligence (AI)AttentionAutoencoder
B
BackpropagationBatch NormalizationBERTBiasBoosting
C
ChatbotClassifier / ClassificationClusteringCNN / Convolutional Neural NetworkCross-Validation
D
Data AugmentationDeep LearningDeepfakeDeterministic ModelDiscriminative Model
E
EmbeddingEncoderEnsemble LearningEpochExplainable AI (XAI)
F
Feature ExtractionFine-tuningForward PropagationFoundation ModelFusion / Multimodal Fusion
G
GAN / Generative Adversarial NetworkGenerative AIGradient DescentGraph Neural Network (GNN)Grounding
H
HallucinationHeuristicHidden LayerHierarchical ModelHyperparameter
I
Imbalanced DataInstance / SampleInstruction tuningIntelligence Amplification / AugmentationInterpretability
J
JAXJitteringJoint EmbeddingJSONL / JSON-linesJuxtaposition
K
K-means ClusteringK-Shot LearningKernel TrickKL Divergence (Kullback–Leibler Divergence)Knowledge Distillation
L
Large Language Model (LLM)Latent VariableLearning RateLoss FunctionLSTM / Long Short-Term Memory
M
Machine Learning (ML)Meta-learningModelMulti-head AttentionMultimodal / Multimodality
N
Neural NetworkNLP / Natural Language ProcessingNLU / Natural Language UnderstandingNormalizationNovelty Detection / Anomaly Detection
O
Objective FunctionOne-hot EncodingOnline LearningOptimizerOverfitting
P
ParameterPolicy / Reinforcement Learning PolicyPoolingPretrainingPrompt
Q
Q-learningQuality EstimationQuantizationQueryQueue / Buffer
R
RegularizationReinforcement Learning (RL)Representation LearningRetrieval Augmented Generation (RAG)RNN / Recurrent Neural Network
S
SamplingSelf-Supervised LearningSequence ModelingSoftmaxSupervised Learning
T
TokenizerTraining DataTransfer LearningTransformerTuning / Hyperparameter Tuning
U
U-NetUncertainty EstimationUnderfittingUniversal Approximation TheoremUnsupervised Learning
V
Validation SetVanishing / Exploding GradientVariational Autoencoder (VAE)Vector EmbeddingVision Transformer (ViT)
W
Weak SupervisionWeight DecayWhitening / Whitening TransformationWord EmbeddingWorkflow
X
X-axis / feature axisXAI / Explainable AIXLMXLNetXOR problem
Y
Y-axis / feature axisY-transform / YUVYAGNI (You Aren't Gonna Need It)Yield (model yield / throughput)Yoga of AI
Z
Z-score NormalizationZero-centric / Zero-bias initializationZero-gradient phenomenonZero-shot Learning / Zero-shot inferenceZygosity in augmentation

What is CNN / Convolutional Neural Network

Convolutional Neural Networks (CNNs) are a category of deep learning models particularly effective for image recognition and processing. The fundamental idea is to mimic the human visual system by progressively extracting image features through multiple convolutional layers. CNN was first introduced by Yann LeCun in the 1980s and gained significant attention after its success in the ImageNet competition in 2012, which greatly propelled the research and application of deep learning.


CNNs typically consist of an input layer, several convolutional layers, pooling layers, fully connected layers, and an output layer. The convolutional layers extract local features through convolution operations, while the pooling layers reduce the dimensionality of the features, decreasing computational complexity while retaining essential information. After several rounds of convolution and pooling, the final features are mapped to output labels through the fully connected layers.


CNNs are widely applied in computer vision tasks such as image classification, object detection, and image segmentation. For example, Google's Inception model and Facebook's Mask R-CNN are successful implementations based on CNN. Their applications are also increasingly found in medical image analysis, autonomous driving, and video surveillance.


With the explosion of data and improvements in computational power, the application fields of CNNs will continue to expand. Emerging technologies like edge computing, augmented reality, and virtual reality will also drive further innovations in CNN. Moreover, combining CNN with Generative Adversarial Networks (GANs) may lead to new breakthroughs in generative models.


Despite their outstanding performance in handling image data, CNNs have certain limitations, such as the requirement for large-scale datasets and high computational resource consumption. Additionally, the interpretability of models remains a hot topic of research. When using CNNs, it is essential to preprocess the data adequately to improve the model's accuracy.