paper-with-me

Papers

Wide Feedforward or Recurrent Neural Networks of Any Architecture are Gaussian Processes

2019-12-01 · NeurIPS 2019 12 · Greg Yang

Wide neural networks with random weights and biases are Gaussian processes, as observed by Neal (1995) for shallow networks, and more recently by Lee et al.~(2018) and Matthews et al.~(2018) for deep fully-connected networks, as well as by Novak et al.~(2019) and Garriga-Alonso et al.~(2019) for deep convolutional networks. We show that this Neural Network-Gaussian Process correspondence surprisingly extends to all modern feedforward or recurrent neural networks composed of multilayer perceptron, RNNs (e.g. LSTMs, GRUs), (nD or graph) convolution, pooling, skip connection, attention, batch normalization, and/or layer normalization. More generally, we introduce a language for expressing neural network computations, and our result encompasses all such expressible neural networks. This work serves as a tutorial on the \emph{tensor programs} technique formulated in Yang (2019) and elucidates the Gaussian Process results obtained there. We provide open-source implementations of the Gaussian Process kernels of simple RNN, GRU, transformer, and batchnorm+ReLU network at github.com/thegregyang/GP4A. Please see our arxiv version for the complete and up-to-date version of this paper.

📄 PDF Abstract BibTeX

Code (1)

thegregyang/GP4A 공식 구현 pytorch

Tasks

Gaussian Processes

Methods 이 논문이 사용한 방법론

GRU A Gated Recurrent Unit, or GRU, is a type of recurrent neural network. It is similar to an LSTM, but only has two gates - a reset…
Gaussian Process Gaussian Processes are non-parametric models for approximating functions. They rely upon a measure of similarity between points (the kernel function) to predict the value for…

Similar Papers 제목 키워드 기반

Tensor Programs I: Wide Feedforward or Recurrent Neural Networks of Any Architecture are Gaussian Processes

2019-10-28 · Greg Yang

Wide neural networks with random weights and biases are Gaussian processes, as originally observed by Neal (1995) and more recently by Lee et al. (2018) and Matthews et al. (2018) for deep fully-connected networks, as we…

Gaussian Processes

Gaussian Process Behaviour in Wide Deep Neural Networks

2018-04-30 · ICLR 2018 1 · Alexander G. de G. Matthews, Mark Rowland, Jiri Hron, Richard E. Turner 외

Whilst deep neural networks have shown great empirical success, there is still much work to be done to understand their theoretical properties. In this paper, we study the relationship between random, wide, fully connect…

Gaussian Processes

Scale Mixtures of Neural Network Gaussian Processes

2021-07-03 · ICLR 2022 4 · Hyungi Lee, Eunggu Yun, Hongseok Yang, Juho Lee

Recent works have revealed that infinitely-wide feed-forward or recurrent neural networks of any architecture correspond to Gaussian processes referred to as Neural Network Gaussian Processes (NNGPs). While these works h…

Gaussian Processes

Deep Predictive Coding Network for Object Recognition

2018-02-13 · ICML 2018 7 · Haiguang Wen, Kuan Han, Junxing Shi, Yizhen Zhang 외

Based on the predictive coding theory in neuroscience, we designed a bi-directional and recurrent neural net, namely deep predictive coding networks (PCN). It has feedforward, feedback, and recurrent connections. Feedbac…

image-classificationImage ClassificationObjectObject Recognition+1

Architectural Complexity Measures of Recurrent Neural Networks

2016-02-26 · NeurIPS 2016 12 · Saizheng Zhang, Yuhuai Wu, Tong Che, Zhouhan Lin 외

In this paper, we systematically analyze the connecting architectures of recurrent neural networks (RNNs). Our main contribution is twofold: first, we present a rigorous graph-theoretic framework describing the connectin…

Language Modelling