Iteration over event space in time-to-first-spike spiking neural networks for Twitter bot classification
Fuente:
arXiv
Salvato in:
| Autori principali: | , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2024
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866917719957307392 |
|---|---|
| author | Pabian, Mateusz Rzepka, Dominik Pawlak, Mirosław |
| author_facet | Pabian, Mateusz Rzepka, Dominik Pawlak, Mirosław |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2407_08746 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Iteration over event space in time-to-first-spike spiking neural networks for Twitter bot classification Pabian, Mateusz Rzepka, Dominik Pawlak, Mirosław Neural and Evolutionary Computing Machine Learning 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. |
| title | Iteration over event space in time-to-first-spike spiking neural networks for Twitter bot classification |
| topic | Neural and Evolutionary Computing Machine Learning |
| url | https://arxiv.org/abs/2407.08746 |