This page links to all terms that do not have listed external references.

• Abscissa
• Abstractive sentence summarization
• AdaBoost
• Adaptive learning rate
• Additive clustering
• Affine space
• Antonym
• Attention Mechanism
• Average pooling
• Bag-of-n-grams
• Bayesian optimization
• Bayesian Probabilistic Matrix Factorization (BPMF)
• Bidirectional LSTM
• Bidirectional Recurrent Neural Network (BRNN)
• Bilingual Evaluation Understudy (BLEU)
• Black-Box optimization
• Bounding box
• Categorical mixture model
• Chinese Restaurant Process
• Chunking
• Clustering stability
• Clustering
• Co-clustering
• Codebook collapse
• Collaborative filtering
• Collaborative Topic Regression (CTR)
• Community detection
• Conditional GAN
• Conditional Markov Models (CMMs)
• Confusion matrix
• Continuous-Bag-of-Words (CBOW)
• Contractive autoencoder (CAE)
• Convex optimization
• Convolution
• Coreference resolution
• Cosine similarity
• Covariance
• Cross-Entropy loss
• Denoising autoencoder
• Differential Topic Modeling
• Dirichlet process
• doc2vec
• Early stopping
• Expectation
• Exploding gradient problem
• Face detection
• Facet (disambiguation)
• fastText
• First-order information
• Gibbs sampling
• GoogLeNet
• Gradient descent
• Gradient
• Graph
• Grid search
• Hadamard product
• Hamming distance
• Hessian matrix
• Hidden Markov Models (HMMs)
• Hierarchical Dirichlet process (HDP)
• Hierarchical Latent Dirichlet allocation (hLDA)
• Hierarchical Softmax
• Hinge loss
• Hypernym
• Hyperparameter
• Hyponym
• Identity mapping
• Importance sampling
• Inceptionism
• Independent and Identically Distributed (i.i.d)
• Jaccard index (intersection over union)
• Jacobian matrix
• K-Means clustering
• Kullback-Leibler (KL) divergence
• Language segmentation
• Laplacian matrix
• Latent Dirichlet allocation (LDA)
• Leaky ReLU
• Learning rate
• Lexeme
• Likelihood
• Linear discriminant analysis (LDA)
• Loss function
• Market basket analysis
• Markov Chain Monte Carlo (MCMC)
• Max-margin loss
• Max Pooling
• Maximum A Posteriori (MAP) Estimation
• Maximum Likelihood Estimation (MLE)
• Meronym
• Minibatch Gradient Descent
• Mini-Batching
• Minimal matching distance
• Mixed-membership model
• Mode collapse
• Model averaging
• Model compression
• Moore-Penrose Pseudoinverse
• Multi-Armed Bandit
• Multilayer LSTM
• Multinomial distribution
• Narrow convolution
• Natural Language Processing
• NCHW
• Negative Sampling
• Nested Chinese Restaurant Process
• Neural network
• NHWC
• Nonparametric clustering
• Object detection
• Object localization
• One-dimensional convolution
• Optimization
• Padding (convolution)
• Paragraph vector
• Parameter budget
• Parametric clustering
• Peephole connection
• Perplexity
• Pertainym
• Pitman-Yor Topic Modeling (PYTM)
• Point Estimator
• Pointwise Mutual Information (PMI)
• Polysemy
• Positive Pointwise Mutual Information (PPMI)
• Principal Component Analysis (PCA)
• Probabilistic Latent Semantic Indexing (PLSI)
• Probabilistic Matrix Factorization (PMF)
• Pseudo-labeling
• Q-learning
• Rand Index
• Random Forest (RF)
• Random search
• Receiver Operating Characteristic (ROC)
• Recursive Neural Network
• Regression based latent factors (RLFM)
• Regularization
• RMSProp
• Second-order information
• Singular Value Decomposition (SVD)
• Skip-Gram
• Sparse autoencoder
• Spearman's Rank Correlation Coefficient
• Stacked autoencoder
• Stationary environment
• Stochastic block model (SBM)
• Stochastic Gradient Descent (SGD)
• Stochastic Gradient Variational Bayes (SGVB)
• Stochastic Optimization
• Stride (convolution)
• Support Vector Machine (SVM)
• Synset
• Temporal classification
• Test term
• Time-delayed neural network
• Time-delayed signal
• Troponym
• Underfitting
• UNK
• Vanishing gradient problem
• Variational Autoencoder (VAE)
• Wide convolution
• Word embedding
• word2phrase
• Wronskian matrix