paper-with-me

홈 › Papers

Target Propagation in Recurrent Neural Networks

2020-02-01 · Journal of Machine Learning Research 2020 2 · Nikolay Manchev, Michael Spratling

Recurrent Neural Networks have been widely used to process sequence data, but have long been criticized for their biological implausibility and training difficulties related to vanishing and exploding gradients. This paper presents a novel algorithm for training recurrent networks, target propagation through time (TPTT), that outperforms standard backpropagation through time (BPTT) on four out of the five problems used for testing. The proposed algorithm is initially tested and compared to BPTT on four synthetic time lag tasks, and its performance is also measured using the sequential MNIST data set. In addition, as TPTT uses target propagation, it allows for discrete nonlinearities and could potentially mitigate the credit assignment problem in more complex recurrent architectures.

📄 PDF Abstract BibTeX

Code (1)

nmanchev/tptt 공식 구현

Similar Papers 제목 키워드 기반

Training Language Models Using Target-Propagation

2017-02-15 · Sam Wiseman, Sumit Chopra, Marc'Aurelio Ranzato, Arthur Szlam 외

While Truncated Back-Propagation through Time (BPTT) is the most popular approach to training Recurrent Neural Networks (RNNs), it suffers from being inherently sequential (making parallelization difficult) and from trun…

Target Propagation via Regularized Inversion

2021-12-02 · Vincent Roulet, Zaid Harchaoui

Target Propagation (TP) algorithms compute targets instead of gradients along neural networks and propagate them backward in a way that is similar yet different than gradient back-propagation (BP). The idea was first pre…

Equivalence of Equilibrium Propagation and Recurrent Backpropagation

2017-11-22 · Benjamin Scellier, Yoshua Bengio

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…

Learning with Local Gradients at the Edge

2022-08-17 · Michael Lomnitz, Zachary Daniels, David Zhang, Michael Piacentino

To enable learning on edge devices with fast convergence and low memory, we present a novel backpropagation-free optimization algorithm dubbed Target Projection Stochastic Gradient Descent (tpSGD). tpSGD generalizes dire…

Recurrent Filter Learning for Visual Tracking

2017-08-13 · Tianyu Yang, Antoni B. Chan

Recently using convolutional neural networks (CNNs) has gained popularity in visual tracking, due to its robust feature representation of images. Recent methods perform online tracking by fine-tuning a pre-trained CNN mo…

ObjectVisual Tracking