A comparative study of back propagation and its alternatives on multilayer perceptrons

• URL: http://arxiv.org/abs/2206.06098v1
• Date: Tue, 31 May 2022 18:44:13 GMT
• Title: A comparative study of back propagation and its alternatives on multilayer perceptrons
• Authors: John Waldo
• Abstract summary: The de facto algorithm for training the back pass of a feedforward neural network is backpropagation (BP) The use of almost-everywhere differentiable activation functions made it efficient and effective to propagate the gradient backwards through layers of deep neural networks. In this paper, we analyze the stability and similarity of predictions and neurons in convolutional neural networks (CNNs) and propose a new variation of one of the algorithms.
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: The de facto algorithm for training the back pass of a feedforward neural network is backpropagation (BP). The use of almost-everywhere differentiable activation functions made it efficient and effective to propagate the gradient backwards through layers of deep neural networks. However, in recent years, there has been much research in alternatives to backpropagation. This analysis has largely focused on reaching state-of-the-art accuracy in multilayer perceptrons (MLPs) and convolutional neural networks (CNNs). In this paper, we analyze the stability and similarity of predictions and neurons in MLPs and propose a new variation of one of the algorithms.

Related papers

• The Cascaded Forward Algorithm for Neural Network Training [61.06444586991505]
  We propose a new learning framework for neural networks, namely Cascaded Forward (CaFo) algorithm, which does not rely on BP optimization as that in FF. Unlike FF, our framework directly outputs label distributions at each cascaded block, which does not require generation of additional negative samples. In our framework each block can be trained independently, so it can be easily deployed into parallel acceleration systems.
  arXiv  Detail & Related papers  (2023-03-17T02:01:11Z)
• Implicit Stochastic Gradient Descent for Training Physics-informed Neural Networks [51.92362217307946]
  Physics-informed neural networks (PINNs) have effectively been demonstrated in solving forward and inverse differential equation problems. PINNs are trapped in training failures when the target functions to be approximated exhibit high-frequency or multi-scale features. In this paper, we propose to employ implicit gradient descent (ISGD) method to train PINNs for improving the stability of training process.
  arXiv  Detail & Related papers  (2023-03-03T08:17:47Z)
• WLD-Reg: A Data-dependent Within-layer Diversity Regularizer [98.78384185493624]
  Neural networks are composed of multiple layers arranged in a hierarchical structure jointly trained with a gradient-based optimization. We propose to complement this traditional 'between-layer' feedback with additional 'within-layer' feedback to encourage the diversity of the activations within the same layer. We present an extensive empirical study confirming that the proposed approach enhances the performance of several state-of-the-art neural network models in multiple tasks.
  arXiv  Detail & Related papers  (2023-01-03T20:57:22Z)
• Low-Variance Forward Gradients using Direct Feedback Alignment and Momentum [0.0]
  We propose an algorithm that combines Activity-Perturbed Forward Gradients with Direct Feedback Alignment and momentum. Our approach enables faster convergence and better performance when compared to other local alternatives to backpropagation.
  arXiv  Detail & Related papers  (2022-12-14T15:30:56Z)
• Including STDP to eligibility propagation in multi-layer recurrent spiking neural networks [0.0]
  Spiking neural networks (SNNs) in neuromorphic systems are more energy efficient compared to deep learning-based methods. There is no clear competitive learning algorithm for training such SNNs. E-prop offers an efficient and biologically plausible way to train competitive recurrent SNNs in low-power neuromorphic hardware.
  arXiv  Detail & Related papers  (2022-01-05T05:51:18Z)
• Target Propagation via Regularized Inversion [4.289574109162585]
  We present a simple version of target propagation based on regularized inversion of network layers, easily implementable in a differentiable programming framework. We show how our TP can be used to train recurrent neural networks with long sequences on various sequence modeling problems.
  arXiv  Detail & Related papers  (2021-12-02T17:49:25Z)
• Dynamic Neural Diversification: Path to Computationally Sustainable Neural Networks [68.8204255655161]
  Small neural networks with a constrained number of trainable parameters, can be suitable resource-efficient candidates for many simple tasks. We explore the diversity of the neurons within the hidden layer during the learning process. We analyze how the diversity of the neurons affects predictions of the model.
  arXiv  Detail & Related papers  (2021-09-20T15:12:16Z)
• Analytically Tractable Inference in Deep Neural Networks [0.0]
  Tractable Approximate Inference (TAGI) algorithm was shown to be a viable and scalable alternative to backpropagation for shallow fully-connected neural networks. We are demonstrating how TAGI matches or exceeds the performance of backpropagation, for training classic deep neural network architectures.
  arXiv  Detail & Related papers  (2021-03-09T14:51:34Z)
• LocalDrop: A Hybrid Regularization for Deep Neural Networks [98.30782118441158]
  We propose a new approach for the regularization of neural networks by the local Rademacher complexity called LocalDrop. A new regularization function for both fully-connected networks (FCNs) and convolutional neural networks (CNNs) has been developed based on the proposed upper bound of the local Rademacher complexity.
  arXiv  Detail & Related papers  (2021-03-01T03:10:11Z)
• Parallelization Techniques for Verifying Neural Networks [52.917845265248744]
  We introduce an algorithm based on the verification problem in an iterative manner and explore two partitioning strategies. We also introduce a highly parallelizable pre-processing algorithm that uses the neuron activation phases to simplify the neural network verification problems.
  arXiv  Detail & Related papers  (2020-04-17T20:21:47Z)
• Semi-Implicit Back Propagation [1.5533842336139065]
  We propose a semi-implicit back propagation method for neural network training. The difference on the neurons are propagated in a backward fashion and the parameters are updated with proximal mapping. Experiments on both MNIST and CIFAR-10 demonstrate that the proposed algorithm leads to better performance in terms of both loss decreasing and training/validation accuracy.
  arXiv  Detail & Related papers  (2020-02-10T03:26:09Z)

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.