Matches in SemOpenAlex for { <https://semopenalex.org/work/W2994747787> ?p ?o ?g. }
- W2994747787 abstract "Neural Tangents is a library for working with infinite-width neural networks. It provides a high-level API for specifying complex and hierarchical neural network architectures. These networks can then be trained and evaluated either at finite-width as usual, or in their infinite-width limit. For the infinite-width networks, Neural Tangents performs exact inference either via Bayes' rule or gradient descent, and generates the corresponding Neural Network Gaussian Process and Neural Tangent kernels. Additionally, Neural Tangents provides tools to study gradient descent training dynamics of wide but finite networks. The entire library runs out-of-the-box on CPU, GPU, or TPU. All computations can be automatically distributed over multiple accelerators with near-linear scaling in the number of devices. In addition to the repository below, we provide an accompanying interactive Colab notebook at https://colab.sandbox.google.com/github/neural-tangents/neural-tangents/blob/master/notebooks/neural_tangents_cookbook.ipynb" @default.
- W2994747787 created "2019-12-26" @default.
- W2994747787 creator A5022953202 @default.
- W2994747787 creator A5059899470 @default.
- W2994747787 creator A5064407466 @default.
- W2994747787 creator A5064986566 @default.
- W2994747787 creator A5070645440 @default.
- W2994747787 creator A5081096634 @default.
- W2994747787 date "2020-04-30" @default.
- W2994747787 modified "2023-09-23" @default.
- W2994747787 title "Neural Tangents: Fast and Easy Infinite Neural Networks in Python" @default.
- W2994747787 cites W2167608136 @default.
- W2994747787 cites W2540189295 @default.
- W2994747787 cites W2766273648 @default.
- W2994747787 cites W2803268044 @default.
- W2994747787 cites W2806504075 @default.
- W2994747787 cites W2886067286 @default.
- W2994747787 cites W2891962546 @default.
- W2994747787 cites W2894604724 @default.
- W2994747787 cites W2899748887 @default.
- W2994747787 cites W2899771611 @default.
- W2994747787 cites W2910655610 @default.
- W2994747787 cites W2913473169 @default.
- W2994747787 cites W2920270464 @default.
- W2994747787 cites W2947328134 @default.
- W2994747787 cites W2952204734 @default.
- W2994747787 cites W2962685794 @default.
- W2994747787 cites W2962698540 @default.
- W2994747787 cites W2962804662 @default.
- W2994747787 cites W2962939986 @default.
- W2994747787 cites W2963063862 @default.
- W2994747787 cites W2963323437 @default.
- W2994747787 cites W2964052793 @default.
- W2994747787 cites W2964065616 @default.
- W2994747787 cites W2964088238 @default.
- W2994747787 cites W2964137095 @default.
- W2994747787 cites W2970474218 @default.
- W2994747787 cites W2971043187 @default.
- W2994747787 cites W2978031686 @default.
- W2994747787 cites W2994872659 @default.
- W2994747787 cites W3118608800 @default.
- W2994747787 hasPublicationYear "2020" @default.
- W2994747787 type Work @default.
- W2994747787 sameAs 2994747787 @default.
- W2994747787 citedByCount "57" @default.
- W2994747787 countsByYear W29947477872018 @default.
- W2994747787 countsByYear W29947477872019 @default.
- W2994747787 countsByYear W29947477872020 @default.
- W2994747787 countsByYear W29947477872021 @default.
- W2994747787 countsByYear W29947477872023 @default.
- W2994747787 crossrefType "proceedings-article" @default.
- W2994747787 hasAuthorship W2994747787A5022953202 @default.
- W2994747787 hasAuthorship W2994747787A5059899470 @default.
- W2994747787 hasAuthorship W2994747787A5064407466 @default.
- W2994747787 hasAuthorship W2994747787A5064986566 @default.
- W2994747787 hasAuthorship W2994747787A5070645440 @default.
- W2994747787 hasAuthorship W2994747787A5081096634 @default.
- W2994747787 hasConcept C11413529 @default.
- W2994747787 hasConcept C138187205 @default.
- W2994747787 hasConcept C153258448 @default.
- W2994747787 hasConcept C154945302 @default.
- W2994747787 hasConcept C199360897 @default.
- W2994747787 hasConcept C2524010 @default.
- W2994747787 hasConcept C33923547 @default.
- W2994747787 hasConcept C41008148 @default.
- W2994747787 hasConcept C50644808 @default.
- W2994747787 hasConcept C519991488 @default.
- W2994747787 hasConceptScore W2994747787C11413529 @default.
- W2994747787 hasConceptScore W2994747787C138187205 @default.
- W2994747787 hasConceptScore W2994747787C153258448 @default.
- W2994747787 hasConceptScore W2994747787C154945302 @default.
- W2994747787 hasConceptScore W2994747787C199360897 @default.
- W2994747787 hasConceptScore W2994747787C2524010 @default.
- W2994747787 hasConceptScore W2994747787C33923547 @default.
- W2994747787 hasConceptScore W2994747787C41008148 @default.
- W2994747787 hasConceptScore W2994747787C50644808 @default.
- W2994747787 hasConceptScore W2994747787C519991488 @default.
- W2994747787 hasLocation W29947477871 @default.
- W2994747787 hasOpenAccess W2994747787 @default.
- W2994747787 hasPrimaryLocation W29947477871 @default.
- W2994747787 hasRelatedWork W1567512734 @default.
- W2994747787 hasRelatedWork W2112796928 @default.
- W2994747787 hasRelatedWork W2167608136 @default.
- W2994747787 hasRelatedWork W2194775991 @default.
- W2994747787 hasRelatedWork W2809090039 @default.
- W2994747787 hasRelatedWork W2910655610 @default.
- W2994747787 hasRelatedWork W2913473169 @default.
- W2994747787 hasRelatedWork W2952204734 @default.
- W2994747787 hasRelatedWork W2962685794 @default.
- W2994747787 hasRelatedWork W2962698540 @default.
- W2994747787 hasRelatedWork W2963323437 @default.
- W2994747787 hasRelatedWork W2963518130 @default.
- W2994747787 hasRelatedWork W2964052793 @default.
- W2994747787 hasRelatedWork W2964121744 @default.
- W2994747787 hasRelatedWork W2970217468 @default.
- W2994747787 hasRelatedWork W2971043187 @default.
- W2994747787 hasRelatedWork W2994872659 @default.
- W2994747787 hasRelatedWork W3101069636 @default.
- W2994747787 hasRelatedWork W3118608800 @default.
- W2994747787 hasRelatedWork W3137695714 @default.