Networks

aka ANN, NN

A network based on a collection of connected units called artificial neurons modeled after biological neurons.

aka AE

An unsupervised pretrained network that learns efficient codings of unlabeled data by training to ignore insignificant data and regenerate i…

A network that is a probabilistic graphical model representing variables and their conditional dependencies via a directed acyclic graph.

aka BM, Sherrington–Kirkpatrick model with external field…

A symmetrically connected network that is a type of stochastic recurrent neural network and Markov random field.

aka Incremental Learning, Life-Long Learning

A deep neural network that learns sequential tasks without forgetting knowledge from preceding tasks and without access to old task data dur…

A deep neural network self-supervised learning approach that learns to distinguish between similar and dissimilar data samples.

aka DN

A deep neural network that uses deconvolution for unsupervised construction of hierarchical image representations.

aka DeepAL

A deep neural network that combines deep learning and active learning to maximize model performance while annotating the fewest samples poss…

aka DBN

An unsupervised pretrained network composed of multiple layers of latent variables that learns to probabilistically reconstruct inputs and p…

aka DCIGN

An autoencoder network that learns interpretable disentangled image representations through convolution and de-convolution layers trained wi…

aka CNN, ConvNet…

A deep neural network specialized for analyzing visual imagery using shared-weight architecture and translation-equivariant feature maps.

aka DFF, MLP…

A deep neural network that processes information in one direction—from input nodes through hidden nodes to output nodes—without cycles or lo…

aka DNN

An artificial neural network characterized by multiple hidden layers between the input and output layers.

A deep neural network that relaxes the hypothesis that training data must be independent and identically distributed with test data to addre…

aka DAE, Denoising Autoencoder

An autoencoder network trained to reconstruct the original undistorted input from a partially corrupted input.

aka ESN

A recurrent neural network with a recurrent hidden layer and sparsely connected hidden neurons that learns output weights to produce tempora…

aka ELM

A feedback network with randomly assigned hidden nodes that are not updated during training.

A deep neural network trained across decentralized edge devices or servers holding local data samples without exchanging them.

aka FBN

An artificial neural network that refines its representations iteratively based on feedback from previous outputs.

aka GRU

A long short-term memory network that is a gating mechanism in recurrent neural networks similar to LSTMs but with fewer parameters and no o…

aka GFSL

A deep neural network that learns novel classes from few samples per class, preventing catastrophic forgetting of base classes and ensuring…

aka GAN

An unsupervised pretrained network framework where two neural networks contest in a game to generate new data with the same statistics as th…

aka GCN

A deep neural network that operates directly on graph structures utilizing structural information.

aka GPCN

A graph convolutional network that generates goal-directed graphs using reinforcement learning and optimizing for rewards and adversarial lo…

aka HN, Ising model of a neural network…

A symmetrically connected network that is a type of recurrent artificial neural network serving as a content-addressable memory system.

aka IFSL

A deep neural network trained on a base set of classes and then presented with novel classes, each with few labeled examples.

aka KN, SOFM…

A network that is an unsupervised technique producing a low-dimensional representation of high-dimensional data preserving topological struc…

aka LSM

A network that is a type of reservoir computer turning time-varying input into spatio-temporal activation patterns.

aka LSTM

A recurrent neural network with feedback connections that processes entire sequences of data.

aka MC, MP…

A network that is a stochastic model describing a sequence of possible events where the probability of each event depends only on the previo…

aka Distance Metric Learning

A deep neural network that learns a representation function mapping objects into an embedded space.

A deep neural network that processes and links information using various modalities.

aka unified encoder, vision-language model

A transformer network that processes and relates information from different modalities such as text images and audio using a shared embeddin…

A system of interconnected nodes or entities for communication, computation or data exchange.

aka NTM

A deep feedforward network that combines neural network pattern matching with the algorithmic power of programmable computers.

aka OSL

A deep neural network that classifies objects from one or only a few examples.

aka FFN, Feed-Forward Network…

An artificial neural network with a supervised learning algorithm for binary classification using a linear predictor function.

aka RBFN, RBN…

A deep feedforward network that uses radial basis functions as activation functions for pattern recognition and interpolation.

aka RN, RecNN…

A network with connections forming a directed graph along a temporal sequence enabling dynamic behavior.

aka RLM, Compositional generalization

A deep neural network that uses recursive neural network architectures like TreeLSTMs to learn syntactic composition functions improving sys…

aka RecuNN, RvNN

A deep neural network that recursively applies weights over structured input to generate structured or scalar predictions.

aka Feature Learning

A deep neural network that discovers representations required for feature detection or classification from raw data.

aka DRN, Deep Residual Network…

A deep neural network that employs skip connections to bypass layers facilitating learning of residual functions.

aka RBM

A Boltzmann machine network that learns the probability distribution of its input data.

aka SAE, Sparse AE…

An autoencoder network with more hidden units than inputs that constrains only a few hidden units to be active at once.

aka Sparse coding, Sparse dictionary Learning

A representation learning network that finds sparse representations of input data as a linear combination of basic elements and identifies t…

aka SVM, SVN…

A network with supervised learning models for classification and regression that maps training examples to points in space maximizing the ga…

aka SCN

A network that is a type of recurrent neural network where connections between units are symmetrical with equal weights in both directions.

A deep neural network that utilizes attention mechanisms to weigh the significance of input data.

aka UPN

A network that initializes a discriminative neural net from one trained using an unsupervised criterion.

aka VAE

An autoencoder network that imposes a probabilistic structure on the latent space for unsupervised learning.

aka ZSL

A deep neural network that predicts classes at test time from classes not observed during training.