paper-with-me

Papers

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 considers deeper and more non-linear functions, e.g., consider the extreme case of nonlinearity where the relation between parameters and cost is actually discrete. Inspired by the biological implausibility of back-propagation, a few approaches have been proposed in the past that could play a similar credit assignment role. In this spirit, we explore a novel approach to credit assignment in deep networks that we call target propagation. The main idea is to compute targets rather than gradients, at each layer. Like gradients, they are propagated backwards. In a way that is related but different from previously proposed proxies for back-propagation which rely on a backwards network with symmetric weights, target propagation relies on auto-encoders at each layer. Unlike back-propagation, it can be applied even when units exchange stochastic bits rather than real numbers. We show that a linear correction for the imperfectness of the auto-encoders, called difference target propagation, is very effective to make target propagation actually work, leading to results comparable to back-propagation for deep networks with discrete and continuous units and denoising auto-encoders and achieving state of the art for stochastic networks.

📄 PDF Abstract BibTeX arXiv:1412.7525

Code (1)

donghyunlee/dtp 공식 구현

Similar Papers 제목 키워드 기반

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 fee…

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…

Are skip connections necessary for biologically plausible learning rules?

2019-12-04 · NeurIPS Workshop Neuro_AI 2019 12 · Daniel Jiwoong Im, Rutuja Patil, Kristin Branson

Backpropagation is the workhorse of deep learning, however, several other biologically-motivated learning rules have been introduced, such as random feedback alignment and difference target propagation. None of these met…

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…

Biologically Motivated Algorithms for Propagating Local Target Representations

2018-05-26 · Alexander G. Ororbia, Ankur Mali

Finding biologically plausible alternatives to back-propagation of errors is a fundamentally important challenge in artificial neural network research. In this paper, we propose a learning algorithm called error-driven L…