Nothing Special   »   [go: up one dir, main page]

Grathwohl et al., 2019 - Google Patents

Scalable reversible generative models with free-form continuous dynamics

Grathwohl et al., 2019

View PDF
Document ID
15948756339021923930
Author
Grathwohl W
Chen R
Bettencourt J
Duvenaud D
Publication year
Publication venue
International Conference on Learning Representations

External Links

Snippet

A promising class of generative models maps points from a simple distribution to a complex distribution through an invertible neural network. Likelihood-based training of these models requires restricting their architectures to allow cheap computation of Jacobian determinants …
Continue reading at approximateinference.org (PDF) (other versions)

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING; COUNTING
    • G06N—COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computer systems based on biological models
    • G06N3/02—Computer systems based on biological models using neural network models
    • G06N3/08—Learning methods
    • G06N3/082—Learning methods modifying the architecture, e.g. adding or deleting nodes or connections, pruning
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING; COUNTING
    • G06N—COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computer systems based on biological models
    • G06N3/02—Computer systems based on biological models using neural network models
    • G06N3/04—Architectures, e.g. interconnection topology
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING; COUNTING
    • G06N—COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computer systems based on biological models
    • G06N3/02—Computer systems based on biological models using neural network models
    • G06N3/06—Physical realisation, i.e. hardware implementation of neural networks, neurons or parts of neurons
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING; COUNTING
    • G06F—ELECTRICAL DIGITAL DATA PROCESSING
    • G06F17/00—Digital computing or data processing equipment or methods, specially adapted for specific functions
    • G06F17/10—Complex mathematical operations
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING; COUNTING
    • G06F—ELECTRICAL DIGITAL DATA PROCESSING
    • G06F17/00—Digital computing or data processing equipment or methods, specially adapted for specific functions
    • G06F17/30—Information retrieval; Database structures therefor; File system structures therefor
    • G06F17/30286—Information retrieval; Database structures therefor; File system structures therefor in structured data stores
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING; COUNTING
    • G06F—ELECTRICAL DIGITAL DATA PROCESSING
    • G06F17/00—Digital computing or data processing equipment or methods, specially adapted for specific functions
    • G06F17/50—Computer-aided design
    • G06F17/5009—Computer-aided design using simulation
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING; COUNTING
    • G06K—RECOGNITION OF DATA; PRESENTATION OF DATA; RECORD CARRIERS; HANDLING RECORD CARRIERS
    • G06K9/00—Methods or arrangements for reading or recognising printed or written characters or for recognising patterns, e.g. fingerprints
    • G06K9/62—Methods or arrangements for recognition using electronic means
    • G06K9/6217—Design or setup of recognition systems and techniques; Extraction of features in feature space; Clustering techniques; Blind source separation
    • G06K9/6232—Extracting features by transforming the feature space, e.g. multidimensional scaling; Mappings, e.g. subspace methods
    • G06K9/6247—Extracting features by transforming the feature space, e.g. multidimensional scaling; Mappings, e.g. subspace methods based on an approximation criterion, e.g. principal component analysis
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING; COUNTING
    • G06N—COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N99/00—Subject matter not provided for in other groups of this subclass
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING; COUNTING
    • G06N—COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N5/00—Computer systems utilising knowledge based models

Similar Documents

Publication Publication Date Title
Grathwohl et al. Scalable reversible generative models with free-form continuous dynamics
Grathwohl et al. Ffjord: Free-form continuous dynamics for scalable reversible generative models
Onken et al. Ot-flow: Fast and accurate continuous normalizing flows via optimal transport
Ruthotto et al. Deep neural networks motivated by partial differential equations
Finlay et al. How to train your neural ODE: the world of Jacobian and kinetic regularization
Falorsi et al. Reparameterizing distributions on lie groups
Li et al. Scalable gradients and variational inference for stochastic differential equations
Song et al. Mintnet: Building invertible neural networks with masked convolutions
Yang et al. Feed-forward neural network training using sparse representation
Fan et al. Convergence of online gradient method for feedforward neural networks with smoothing L1/2 regularization penalty
Gabrié et al. Training Restricted Boltzmann Machine via the Thouless-Anderson-Palmer free energy
CN108764460A (en) A kind of Time Series Forecasting Methods based on time convolution sum LSTM
Chilinski et al. Neural likelihoods via cumulative distribution functions
CN114341891A (en) Neural network pruning
CN109034034A (en) A kind of vein identification method based on nitrification enhancement optimization convolutional neural networks
Sengupta et al. How robust are deep neural networks?
MacDonald et al. Enabling equivariance for arbitrary lie groups
Potapczynski et al. Invertible gaussian reparameterization: Revisiting the gumbel-softmax
CN114611384A (en) Medical knowledge graph node importance evaluation method based on graph neural network
Li et al. Calibrating multi-dimensional complex ODE from noisy data via deep neural networks
CN113298129A (en) Polarized SAR image classification method based on superpixel and graph convolution network
Tan et al. Performance comparison of three types of autoencoder neural networks
Admon et al. A new modern scheme for solving fractal–fractional differential equations based on deep feedforward neural network with multiple hidden layer
Potapczynski et al. Invertible gaussian reparameterization: Revisiting the gumbel-softmax
Xu et al. Pseudoinverse learning algorithom for fast sparse autoencoder training