International Conference on Learning Representations · 2020 · 59 citations · 24 references
ComputingComputer EngineeringComputer ScienceAlgorithmsArtificial IntelligenceMachine LearningAccelerator ArchitectureDeep LearningHardware AccelerationNeural NetworksOptimization For Machine LearningScalable Machine LearningAcceleratorsApi DesignDeep Learning AccelerationDeep Learning AcceleratorsDeep Learning On GpusGradient DescentOptimization AlgorithmsRecurrent Neural Networks
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
24
Automatic differentiation in PyTorch
Adam Paszke, Sam Gross, Soumith Chintala et al. · 2017 · 11.1K citations
Sergey Zagoruyko, Nikos Komodakis · 2016 · 6K citations
Gradient descent finds global minima of deep neural networks
Simon S. Du, Jason D. Lee, Haochuan Li et al. · 2019 · 419 citations