The Impact of Activation Sparsity on Overfitting in Convolutional Neural Networks

• URL: http://arxiv.org/abs/2104.06153v1
• Date: Tue, 13 Apr 2021 12:55:37 GMT
• Title: The Impact of Activation Sparsity on Overfitting in Convolutional Neural Networks
• Authors: Karim Huesmann, Luis Garcia Rodriguez, Lars Linsen, and Benjamin Risse
• Abstract summary: Overfitting is one of the fundamental challenges when training convolutional neural networks. In this study we introduce a perplexity-based sparsity definition to derive and visualise layer-wise activation measures.
• Score: 1.9424280683610138
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Overfitting is one of the fundamental challenges when training convolutional neural networks and is usually identified by a diverging training and test loss. The underlying dynamics of how the flow of activations induce overfitting is however poorly understood. In this study we introduce a perplexity-based sparsity definition to derive and visualise layer-wise activation measures. These novel explainable AI strategies reveal a surprising relationship between activation sparsity and overfitting, namely an increase in sparsity in the feature extraction layers shortly before the test loss starts rising. This tendency is preserved across network architectures and reguralisation strategies so that our measures can be used as a reliable indicator for overfitting while decoupling the network's generalisation capabilities from its loss-based definition. Moreover, our differentiable sparsity formulation can be used to explicitly penalise the emergence of sparsity during training so that the impact of reduced sparsity on overfitting can be studied in real-time. Applying this penalty and analysing activation sparsity for well known regularisers and in common network architectures supports the hypothesis that reduced activation sparsity can effectively improve the generalisation and classification performance. In line with other recent work on this topic, our methods reveal novel insights into the contradicting concepts of activation sparsity and network capacity by demonstrating that dense activations can enable discriminative feature learning while efficiently exploiting the capacity of deep models without suffering from overfitting, even when trained excessively.

Related papers

• Learning Neural Networks with Sparse Activations [42.88109060676769]
  In transformer networks, the activations in the hidden layer of this block tend to be extremely sparse on any given input. Unlike traditional forms of sparsity, where there are neurons/weights which can be deleted from the network, this form of em activation sparsity appears to be harder to exploit. We present a variety of results showing that classes of functions do lead to provable computational and statistical advantages over their non-sparse counterparts.
  arXiv  Detail & Related papers  (2024-06-26T00:11:13Z)
• On the Dynamics Under the Unhinged Loss and Beyond [104.49565602940699]
  We introduce the unhinged loss, a concise loss function, that offers more mathematical opportunities to analyze closed-form dynamics. The unhinged loss allows for considering more practical techniques, such as time-vary learning rates and feature normalization.
  arXiv  Detail & Related papers  (2023-12-13T02:11:07Z)
• Towards Improving Robustness Against Common Corruptions using Mixture of Class Specific Experts [10.27974860479791]
  This paper introduces a novel paradigm known as the Mixture of Class-Specific Expert Architecture. The proposed architecture aims to mitigate vulnerabilities associated with common neural network structures.
  arXiv  Detail & Related papers  (2023-11-16T20:09:47Z)
• Learning Dynamics and Generalization in Reinforcement Learning [59.530058000689884]
  We show theoretically that temporal difference learning encourages agents to fit non-smooth components of the value function early in training. We show that neural networks trained using temporal difference algorithms on dense reward tasks exhibit weaker generalization between states than randomly networks and gradient networks trained with policy methods.
  arXiv  Detail & Related papers  (2022-06-05T08:49:16Z)
• Understanding and Preventing Capacity Loss in Reinforcement Learning [28.52122927103544]
  We identify a mechanism by which non-stationary prediction targets can prevent learning progress in deep RL agents. Capacity loss occurs in a range of RL agents and environments, and is particularly damaging to performance in sparse-reward tasks.
  arXiv  Detail & Related papers  (2022-04-20T15:55:15Z)
• Clustering-Based Interpretation of Deep ReLU Network [17.234442722611803]
  We recognize that the non-linear behavior of the ReLU function gives rise to a natural clustering. We propose a method to increase the level of interpretability of a fully connected feedforward ReLU neural network.
  arXiv  Detail & Related papers  (2021-10-13T09:24:11Z)
• Residual Error: a New Performance Measure for Adversarial Robustness [85.0371352689919]
  A major challenge that limits the wide-spread adoption of deep learning has been their fragility to adversarial attacks. This study presents the concept of residual error, a new performance measure for assessing the adversarial robustness of a deep neural network. Experimental results using the case of image classification demonstrate the effectiveness and efficacy of the proposed residual error metric.
  arXiv  Detail & Related papers  (2021-06-18T16:34:23Z)
• Sparsity in Deep Learning: Pruning and growth for efficient inference and training in neural networks [78.47459801017959]
  Sparsity can reduce the memory footprint of regular networks to fit mobile devices. We describe approaches to remove and add elements of neural networks, different training strategies to achieve model sparsity, and mechanisms to exploit sparsity in practice.
  arXiv  Detail & Related papers  (2021-01-31T22:48:50Z)
• Gradient Starvation: A Learning Proclivity in Neural Networks [97.02382916372594]
  Gradient Starvation arises when cross-entropy loss is minimized by capturing only a subset of features relevant for the task. This work provides a theoretical explanation for the emergence of such feature imbalance in neural networks.
  arXiv  Detail & Related papers  (2020-11-18T18:52:08Z)
• Untangling tradeoffs between recurrence and self-attention in neural networks [81.30894993852813]
  We present a formal analysis of how self-attention affects gradient propagation in recurrent networks. We prove that it mitigates the problem of vanishing gradients when trying to capture long-term dependencies. We propose a relevancy screening mechanism that allows for a scalable use of sparse self-attention with recurrence.
  arXiv  Detail & Related papers  (2020-06-16T19:24:25Z)
• Exploiting the Full Capacity of Deep Neural Networks while Avoiding Overfitting by Targeted Sparsity Regularization [1.3764085113103217]
  Overfitting is one of the most common problems when training deep neural networks on comparatively small datasets. We propose novel targeted sparsity visualization and regularization strategies to counteract overfitting.
  arXiv  Detail & Related papers  (2020-02-21T11:38:17Z)

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.