NoProp: Training Neural Networks without Back-propagation or Forward-propagation

• URL: http://arxiv.org/abs/2503.24322v1
• Date: Mon, 31 Mar 2025 17:08:57 GMT
• Title: NoProp: Training Neural Networks without Back-propagation or Forward-propagation
• Authors: Qinyu Li, Yee Whye Teh, Razvan Pascanu,
• Abstract summary: We introduce a new learning method named NoProp, which does not rely on either forward or backwards propagation.<n>NoProp takes inspiration from diffusion and flow matching methods, where each layer independently learns to denoise a noisy target.<n>We demonstrate the effectiveness of our method on MNIST, CIFAR-10, and CIFAR-100 image classification benchmarks.
• Score: 47.978316065775246
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: The canonical deep learning approach for learning requires computing a gradient term at each layer by back-propagating the error signal from the output towards each learnable parameter. Given the stacked structure of neural networks, where each layer builds on the representation of the layer below, this approach leads to hierarchical representations. More abstract features live on the top layers of the model, while features on lower layers are expected to be less abstract. In contrast to this, we introduce a new learning method named NoProp, which does not rely on either forward or backwards propagation. Instead, NoProp takes inspiration from diffusion and flow matching methods, where each layer independently learns to denoise a noisy target. We believe this work takes a first step towards introducing a new family of gradient-free learning methods, that does not learn hierarchical representations -- at least not in the usual sense. NoProp needs to fix the representation at each layer beforehand to a noised version of the target, learning a local denoising process that can then be exploited at inference. We demonstrate the effectiveness of our method on MNIST, CIFAR-10, and CIFAR-100 image classification benchmarks. Our results show that NoProp is a viable learning algorithm which achieves superior accuracy, is easier to use and computationally more efficient compared to other existing back-propagation-free methods. By departing from the traditional gradient based learning paradigm, NoProp alters how credit assignment is done within the network, enabling more efficient distributed learning as well as potentially impacting other characteristics of the learning process.

Related papers

• Scaling Forward Gradient With Local Losses [117.22685584919756]
  Forward learning is a biologically plausible alternative to backprop for learning deep neural networks. We show that it is possible to substantially reduce the variance of the forward gradient by applying perturbations to activations rather than weights. Our approach matches backprop on MNIST and CIFAR-10 and significantly outperforms previously proposed backprop-free algorithms on ImageNet.
  arXiv  Detail & Related papers  (2022-10-07T03:52:27Z)
• Stacked unsupervised learning with a network architecture found by supervised meta-learning [4.209801809583906]
  Stacked unsupervised learning seems more biologically plausible than backpropagation. But SUL has fallen far short of backpropagation in practical applications. We show an SUL algorithm that can perform completely unsupervised clustering of MNIST digits.
  arXiv  Detail & Related papers  (2022-06-06T16:17:20Z)
• FOSTER: Feature Boosting and Compression for Class-Incremental Learning [52.603520403933985]
  Deep neural networks suffer from catastrophic forgetting when learning new categories. We propose a novel two-stage learning paradigm FOSTER, empowering the model to learn new categories adaptively.
  arXiv  Detail & Related papers  (2022-04-10T11:38:33Z)
• Forward Signal Propagation Learning [2.578242050187029]
  We propose a new learning algorithm for propagating a learning signal and updating neural network parameters via a forward pass. In biology, this explains how neurons without feedback connections can still receive a global learning signal. sigprop enables global supervised learning with only a forward path.
  arXiv  Detail & Related papers  (2022-04-04T04:41:59Z)
• Towards Disentangling Information Paths with Coded ResNeXt [11.884259630414515]
  We take a novel approach to enhance the transparency of the function of the whole network. We propose a neural network architecture for classification, in which the information that is relevant to each class flows through specific paths.
  arXiv  Detail & Related papers  (2022-02-10T21:45:49Z)
• Train your classifier first: Cascade Neural Networks Training from upper layers to lower layers [54.47911829539919]
  We develop a novel top-down training method which can be viewed as an algorithm for searching for high-quality classifiers. We tested this method on automatic speech recognition (ASR) tasks and language modelling tasks. The proposed method consistently improves recurrent neural network ASR models on Wall Street Journal, self-attention ASR models on Switchboard, and AWD-LSTM language models on WikiText-2.
  arXiv  Detail & Related papers  (2021-02-09T08:19:49Z)
• LoCo: Local Contrastive Representation Learning [93.98029899866866]
  We show that by overlapping local blocks stacking on top of each other, we effectively increase the decoder depth and allow upper blocks to implicitly send feedbacks to lower blocks. This simple design closes the performance gap between local learning and end-to-end contrastive learning algorithms for the first time.
  arXiv  Detail & Related papers  (2020-08-04T05:41:29Z)
• Eigen-CAM: Class Activation Map using Principal Components [1.2691047660244335]
  This paper builds on previous ideas to cope with the increasing demand for interpretable, robust, and transparent models. The proposed Eigen-CAM computes and visualizes the principle components of the learned features/representations from the convolutional layers.
  arXiv  Detail & Related papers  (2020-08-01T17:14:13Z)
• Attentive CutMix: An Enhanced Data Augmentation Approach for Deep Learning Based Image Classification [58.20132466198622]
  We propose Attentive CutMix, a naturally enhanced augmentation strategy based on CutMix. In each training iteration, we choose the most descriptive regions based on the intermediate attention maps from a feature extractor. Our proposed method is simple yet effective, easy to implement and can boost the baseline significantly.
  arXiv  Detail & Related papers  (2020-03-29T15:01:05Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.