Category

Neural network architectures

page 1

machine-learning model architecture first developed by Google Brain

convolutional neural network

regularized type of feed-forward neural network that learns features by itself via filter (or kernel) optimization

recurrent neural network

class of artificial neural network where connections between units form a directed graph along a temporal sequence

generative adversarial network

deep learning method in which two neural networks compete with each other in a game, learning to generate new data with the same statistics as the training set

long short-term memory

artificial recurrent neural network architecture used in deep learning

Hopfield network

recurrent neural network

multilayer perceptron

type of feedforward neural network with multiple fully connected layers

thumb|upright=1.15|A schema of an autoencoder. An autoencoder has two main parts: an encoder that maps the message to a code, and a decoder that reconstructs the message from the code.

feedforward neural network

artificial neural network in which connections between the nodes do not form a cycle

Boltzmann machine

type of stochastic neural network

thumb|362x362px|AlexNet architecture and a possible modification. At the top is half of the original AlexNet, which is divided into two halves, one for each GPU. At the bottom is the same architecture, but the final "projection" layer is replaced by another that projects to fewer outputs. If one freezes the remaining model and only fine-tunes the last layer, one can obtain another vision model at a significantly lower cost than training one from scratch. thumb|245x245px|LeNet (left) and AlexNet (right) block diagram AlexNet is a convolutional neural network architecture developed for image cla

variational auto-encoder

deep learning generative model to encode data representation

U-Net is a convolutional neural network that was developed for image segmentation. The network is based on a fully convolutional neural network whose architecture was modified and extended to work with fewer training images and to yield more precise segmentation. Segmentation of a 512 × 512 image takes less than a second on a modern (2015) GPU using the U-Net architecture.

residual neural network

type of artificial neural network

vision transformer

machine learning algorithm for vision processing

restricted Boltzmann machine

Boltzmann machine whose neurons form a bipartite graph with visible and hidden neurons

spiking neural network

artificial neural network that mimics real neurons

gated recurrent unit

mechanisms in recurrent neural networks

graph neural network

specialized artificial neural networks that are designed for tasks whose inputs are graphs

radial basis function network

an artificial neural network that uses radial basis functions as activation functions

neural Turing machine

neural network with external memory

echo state network

recurrent neural network with a sparsely connected hidden layer

deep belief network

type of artificial neural network

recursive neural network

artificial neural network with connections forming a hierarchical structure, processing data recursively

time delay neural network

multilayer artificial neural network that classifies patterns with shift-invariance and models context at each layer of the network

Siamese neural network

form of neural network

bidirectional recurrent neural networks

type of artificial neural network that connects two hidden layers of opposite directions to the same output

differentiable neural computer

artificial neural network architecture

probabilistic neural network

type of artificial neural network