mlsanityData to 13 Oct 2026

Iteration over event space in time-to-first-spike spiking neural networks for Twitter bot classification

arXiv 2407.08746 ↗First posted 3 Jun 2024cs.NE cs.LGcited by 0

Not on the map. Why?

Abstract (arXiv)

This study proposes a framework that extends existing time-coding time-to-first-spike spiking neural network (SNN) models to allow processing information changing over time. We explain spike propagation through a model with multiple input and output spikes at each neuron, as well as design training rules for end-to-end backpropagation. This strategy enables us to process information changing over time. The model is trained and evaluated on a Twitter bot detection task where the time of events (tweets and retweets) is the primary carrier of information. This task was chosen to evaluate how the proposed SNN deals with spike train data composed of hundreds of events occurring at timescales differing by almost five orders of magnitude. The impact of various parameters on model properties, performance and training-time stability is analyzed.

Key facts. No citing papers in the map yet (data through 13 Oct 2026). Builds on 28 of its 49 references that are in the map. First posted on arXiv 3 Jun 2024.

Builds on

28 of 49 references.

References · 28

  1. 2019Surrogate Gradient Learning in Spiking Neural Networkscited by 617
  2. 2017Spatio-Temporal Backpropagation for Training High-performance Spiking Neural Networkscited by 403
  3. 2021Deep Residual Learning in Spiking Neural Networkscited by 329
  4. 2015Converting Static Image Datasets to Spiking Neuromorphic Datasets Using Saccadescited by 313
  5. 2020Going Deeper With Directly-Trained Larger Spiking Neural Networkscited by 275
  6. 2018SLAYER: Spike Layer Error Reassignment in Timecited by 263
  7. 2021Training Spiking Neural Networks Using Lessons From Deep Learningcited by 256
  8. 2016Training Deep Spiking Neural Networks using Backpropagationcited by 205
  9. 2017SuperSpike: Supervised learning in multi-layer spiking neural networkscited by 180
  10. 2021Accurate and efficient time-domain classification with adaptive spiking recurrent neural networkscited by 114
  11. 2020Temporal Spike Sequence Learning via Backpropagation for Deep Spiking Neural Networkscited by 100
  12. 2014The Rise of Social Botscited by 96
16 more
  1. 2016Supervised learning based on temporal coding in spiking neural networkscited by 76
  2. 2020Event-Based Backpropagation can compute Exact Gradients for Spiking Neural Networkscited by 59
  3. 2021Beyond Classification: Directly Training Spiking Neural Networks for Semantic Segmentationcited by 55
  4. 2017The paradigm-shift of social spambots: Evidence, theories, and tools for the arms racecited by 49
  5. 2019S4NN: temporal backpropagation for spiking neural networks with one spike per neuroncited by 49
  6. 2017Gradient Descent for Spiking Neural Networkscited by 48
  7. 2019Temporal-Coded Deep Spiking Neural Network with Easy Training and Robust Performancecited by 46
  8. 2016BotOrNot: A System to Evaluate Social Botscited by 41
  9. 2021Sparse Spiking Gradient Descentcited by 41
  10. 2023Joint A-SNN: Joint Training of Artificial and Spiking Neural Networks via Self-Distillation and Weight Factorizationcited by 35
  11. 2019RTbust: Exploiting Temporal Patterns for Botnet Detection on Twittercited by 27
  12. 2018Bio-inspired digit recognition using reward-modulated spike-timing-dependent plasticity in deep convolutional networkscited by 26
  13. 2019Unsupervised Visual Feature Learning with Spike-timing-dependent Plasticity: How Far are we from Traditional Feature Learning Approaches?cited by 12
  14. 2018NengoDL: Combining deep learning and neuromorphic modelling methodscited by 11
  15. 2018Retweet Us, We Will Retweet You: Spotting Collusive Retweeters Involved in Blackmarket Servicescited by 4
  16. 2022Supervised Training of Siamese Spiking Neural Networks with Earth Mover's Distancecited by 1

Built on by

Not cited yet.