Reviving and Improving Recurrent Back-Propagation
In this paper, we revisit the recurrent back-propagation (RBP) algorithm, discuss the conditions under which it applies as well as how to satisfy them in deep neural networks. We show that RBP can be unstable and propose two variants based on conjugate gradient on the normal equations (CG-RBP) and Neumann series (Neumann-RBP). We further investigate the relationship between Neumann-RBP and back propagation through time (BPTT) and its truncated version (TBPTT). Our Neumann-RBP has the same time complexity as TBPTT but only requires constant memory, whereas TBPTT's memory cost scales linearly with the number of truncation steps. We examine all RBP variants along with BPTT and TBPTT in three different application domains: associative memory with continuous Hopfield networks, document classification in citation networks using graph neural networks and hyperparameter optimization for fully connected networks. All experiments demonstrate that RBPs, especially the Neumann-RBP variant, are efficient and effective for optimizing convergent recurrent neural networks. Code is released at: \url{https://github.com/lrjconan/RBP}.
Code (1)
Tasks
Document ClassificationHyperparameter OptimizationSimilar Papers 제목 키워드 기반
Equivalence of Equilibrium Propagation and Recurrent Backpropagation
Recurrent Backpropagation and Equilibrium Propagation are supervised learning algorithms for fixed point recurrent neural networks which differ in their second phase. In the first phase, both algorithms converge to a fix…
A Gentle Tutorial of Recurrent Neural Network with Error Backpropagation
We describe recurrent neural networks (RNNs), which have attracted great attention on sequential tasks, such as handwriting recognition, speech recognition and image to text. However, compared to general feedforward neur…
Handwriting RecognitionImage to textspeech-recognitionSpeech RecognitionReviving ConvNeXt for Efficient Convolutional Diffusion Models
Recent diffusion models increasingly favor Transformer backbones, motivated by the remarkable scalability of fully attentional architectures. Yet the locality bias, parameter efficiency, and hardware friendliness--the at…
A Practical Sparse Approximation for Real Time Recurrent Learning
Current methods for training recurrent neural networks are based on backpropagation through time, which requires storing a complete history of network states, and prohibits updating the weights `online' (after every time…
RNNbow: Visualizing Learning via Backpropagation Gradients in Recurrent Neural Networks
We present RNNbow, an interactive tool for visualizing the gradient flow during backpropagation training in recurrent neural networks. RNNbow is a web application that displays the relative gradient contributions from Re…