Forward-Forward Learning achieves Highly Selective Latent Representations for Out-of-Distribution Detection in Fully Spiking Neural Networks
- URL: http://arxiv.org/abs/2407.14097v2
- Date: Wed, 19 Feb 2025 12:14:17 GMT
- Title: Forward-Forward Learning achieves Highly Selective Latent Representations for Out-of-Distribution Detection in Fully Spiking Neural Networks
- Authors: Erik B. Terres-Escudero, Javier Del Ser, Aitor MartÃnez-Seras, Pablo Garcia-Bringas,
- Abstract summary: Spiking Neural Networks (SNNs), inspired by biological systems, offer a promising avenue for overcoming limitations.
In this work, we explore the potential of the spiking Forward-Forward Algorithm (FFA) to address these challenges.
We propose a novel, gradient-free attribution method to detect features that drive a sample away from class distributions.
- Score: 6.7236795813629
- License:
- Abstract: In recent years, Artificial Intelligence (AI) models have achieved remarkable success across various domains, yet challenges persist in two critical areas: ensuring robustness against uncertain inputs and drastically increasing model efficiency during training and inference. Spiking Neural Networks (SNNs), inspired by biological systems, offer a promising avenue for overcoming these limitations. By operating in an event-driven manner, SNNs achieve low energy consumption and can naturally implement biological methods known for their high noise tolerance. In this work, we explore the potential of the spiking Forward-Forward Algorithm (FFA) to address these challenges, leveraging its representational properties for both Out-of-Distribution (OoD) detection and interpretability. To achieve this, we exploit the sparse and highly specialized neural latent space of FF networks to estimate the likelihood of a sample belonging to the training distribution. Additionally, we propose a novel, gradient-free attribution method to detect features that drive a sample away from class distributions, addressing the challenges posed by the lack of gradients in most visual interpretability methods for spiking models. We evaluate our OoD detection algorithm on well-known image datasets (e.g., Omniglot, Not-MNIST, CIFAR10), outperforming previous methods proposed in the recent literature for OoD detection in spiking networks. Furthermore, our attribution method precisely identifies salient OoD features, such as artifacts or missing regions, hence providing a visual explanatory interface for the user to understand why unknown inputs are identified as such by the proposed method.
Related papers
- Investigating Application of Deep Neural Networks in Intrusion Detection System Design [0.0]
Research aims to learn how effective applications of Deep Neural Networks (DNN) can accurately detect and identify malicious network intrusion.
Test results demonstrate no support for the model to accurately and correctly distinguish the classification of network intrusion.
arXiv Detail & Related papers (2025-01-27T04:06:30Z) - Generative Edge Detection with Stable Diffusion [52.870631376660924]
Edge detection is typically viewed as a pixel-level classification problem mainly addressed by discriminative methods.
We propose a novel approach, named Generative Edge Detector (GED), by fully utilizing the potential of the pre-trained stable diffusion model.
We conduct extensive experiments on multiple datasets and achieve competitive performance.
arXiv Detail & Related papers (2024-10-04T01:52:23Z) - Manipulating Feature Visualizations with Gradient Slingshots [54.31109240020007]
We introduce a novel method for manipulating Feature Visualization (FV) without significantly impacting the model's decision-making process.
We evaluate the effectiveness of our method on several neural network models and demonstrate its capabilities to hide the functionality of arbitrarily chosen neurons.
arXiv Detail & Related papers (2024-01-11T18:57:17Z) - Small Object Detection via Coarse-to-fine Proposal Generation and
Imitation Learning [52.06176253457522]
We propose a two-stage framework tailored for small object detection based on the Coarse-to-fine pipeline and Feature Imitation learning.
CFINet achieves state-of-the-art performance on the large-scale small object detection benchmarks, SODA-D and SODA-A.
arXiv Detail & Related papers (2023-08-18T13:13:09Z) - A Compact Deep Learning Model for Face Spoofing Detection [4.250231861415827]
presentation attack detection (PAD) has received significant attention from research communities.
We address the problem via fusing both wide and deep features in a unified neural architecture.
The procedure is done on different spoofing datasets such as ROSE-Youtu, SiW and NUAA Imposter.
arXiv Detail & Related papers (2021-01-12T21:20:09Z) - Attribute-Guided Adversarial Training for Robustness to Natural
Perturbations [64.35805267250682]
We propose an adversarial training approach which learns to generate new samples so as to maximize exposure of the classifier to the attributes-space.
Our approach enables deep neural networks to be robust against a wide range of naturally occurring perturbations.
arXiv Detail & Related papers (2020-12-03T10:17:30Z) - Ramifications of Approximate Posterior Inference for Bayesian Deep
Learning in Adversarial and Out-of-Distribution Settings [7.476901945542385]
We show that Bayesian deep learning models on certain occasions marginally outperform conventional neural networks.
Preliminary investigations indicate the potential inherent role of bias due to choices of initialisation, architecture or activation functions.
arXiv Detail & Related papers (2020-09-03T16:58:15Z) - Gradients as a Measure of Uncertainty in Neural Networks [16.80077149399317]
We propose to utilize backpropagated gradients to quantify the uncertainty of trained models.
We show that our gradient-based method outperforms state-of-the-art methods by up to 4.8% of AUROC score in out-of-distribution detection.
arXiv Detail & Related papers (2020-08-18T16:58:46Z) - Open Set Recognition with Conditional Probabilistic Generative Models [51.40872765917125]
We propose Conditional Probabilistic Generative Models (CPGM) for open set recognition.
CPGM can detect unknown samples but also classify known classes by forcing different latent features to approximate conditional Gaussian distributions.
Experiment results on multiple benchmark datasets reveal that the proposed method significantly outperforms the baselines.
arXiv Detail & Related papers (2020-08-12T06:23:49Z) - SEKD: Self-Evolving Keypoint Detection and Description [42.114065439674036]
We propose a self-supervised framework to learn an advanced local feature model from unlabeled natural images.
We benchmark the proposed method on homography estimation, relative pose estimation, and structure-from-motion tasks.
We will release our code along with the trained model publicly.
arXiv Detail & Related papers (2020-06-09T06:56:50Z) - Rectified Linear Postsynaptic Potential Function for Backpropagation in
Deep Spiking Neural Networks [55.0627904986664]
Spiking Neural Networks (SNNs) usetemporal spike patterns to represent and transmit information, which is not only biologically realistic but also suitable for ultra-low-power event-driven neuromorphic implementation.
This paper investigates the contribution of spike timing dynamics to information encoding, synaptic plasticity and decision making, providing a new perspective to design of future DeepSNNs and neuromorphic hardware systems.
arXiv Detail & Related papers (2020-03-26T11:13:07Z)
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.