paper-with-me

Papers

Fixed-Weight Difference Target Propagation

2022-12-19 · Tatsukichi Shibuya, Nakamasa Inoue, Rei Kawakami, Ikuro Sato

Target Propagation (TP) is a biologically more plausible algorithm than the error backpropagation (BP) to train deep networks, and improving practicality of TP is an open issue. TP methods require the feedforward and feedback networks to form layer-wise autoencoders for propagating the target values generated at the output layer. However, this causes certain drawbacks; e.g., careful hyperparameter tuning is required to synchronize the feedforward and feedback training, and frequent updates of the feedback path are usually required than that of the feedforward path. Learning of the feedforward and feedback networks is sufficient to make TP methods capable of training, but is having these layer-wise autoencoders a necessary condition for TP to work? We answer this question by presenting Fixed-Weight Difference Target Propagation (FW-DTP) that keeps the feedback weights constant during training. We confirmed that this simple method, which naturally resolves the abovementioned problems of TP, can still deliver informative target values to hidden layers for a given task; indeed, FW-DTP consistently achieves higher test performance than a baseline, the Difference Target Propagation (DTP), on four classification datasets. We also present a novel propagation architecture that explains the exact form of the feedback function of DTP to analyze FW-DTP.

📄 PDF Abstract BibTeX arXiv:2212.10352

Code (1)

TatsukichiShibuya/Fixed-Weight-Difference-Target-Propagation 공식 구현 pytorch

Methods 이 논문이 사용한 방법론

Test 설명 없음

Similar Papers 제목 키워드 기반

Difference Target Propagation

2014-12-23 · Dong-Hyun Lee, Saizheng Zhang, Asja Fischer, Yoshua Bengio

Back-propagation has been the workhorse of recent successes of deep learning but it relies on infinitesimal effects (partial derivatives) in order to perform credit assignment. This could become a serious issue as one co…

Towards Scaling Difference Target Propagation by Learning Backprop Targets

2022-01-31 · Maxence Ernoult, Fabrice Normandin, Abhinav Moudgil, Sean Spinney 외

The development of biologically-plausible learning algorithms is important for understanding learning in the brain, but most of them fail to scale-up to real-world tasks, limiting their potential as explanations for lear…

Deriving Differential Target Propagation from Iterating Approximate Inverses

2020-07-29 · Yoshua Bengio

We show that a particular form of target propagation, i.e., relying on learned inverses of each layer, which is differential, i.e., where the target is a small perturbation of the forward propagation, gives rise to an up…

A Theoretical Framework for Target Propagation

2020-06-25 · NeurIPS 2020 12 · Alexander Meulemans, Francesco S. Carzaniga, Johan A. K. Suykens, João Sacramento 외

The success of deep learning, a brain-inspired form of AI, has sparked interest in understanding how the brain could similarly learn across multiple layers of neurons. However, the majority of biologically-plausible lear…

Probing Association Instability with Track-State Perturbations for Clip-Level Active Learning in Query-Propagation Multi-Object Tracking

2026-08-18 · Riku Inoue, Shogo Sato, Kazuhiko Murasaki, Tomoyasu Shimada 외 arxiv

Training query-propagation end-to-end multi-object tracking (MOT) models requires dense bounding-box and identity annotations across video sequences, making dataset construction expensive. Clip-level active learning redu…

Multi-Object TrackingActive Learning