Saved in:
| Main Authors: | , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2507.21616 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866914274176139264 |
|---|---|
| author | Doran, Kevin Baden, Tom |
| author_facet | Doran, Kevin Baden, Tom |
| contents | We demonstrate the effectiveness of the categorical distribution as a neural network output for next event prediction. This is done for both discrete-time and continuous-time event sequences. To model continuous-time processes, the categorical distribution is interpreted as a piecewise-constant density function and is shown to be competitive across a range of datasets. We then argue for the importance of studying discrete-time processes by introducing a neuronal spike prediction task motivated by retinal prosthetics, where discretization of event times is consequent on the task description. Separately, we show evidence that commonly used datasets favour smaller models. Finally, we introduce new synthetic datasets for testing larger models, as well as synthetic datasets with discrete event times. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2507_21616 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Categorical Distributions are Effective Neural Network Outputs for Event Prediction Doran, Kevin Baden, Tom Machine Learning We demonstrate the effectiveness of the categorical distribution as a neural network output for next event prediction. This is done for both discrete-time and continuous-time event sequences. To model continuous-time processes, the categorical distribution is interpreted as a piecewise-constant density function and is shown to be competitive across a range of datasets. We then argue for the importance of studying discrete-time processes by introducing a neuronal spike prediction task motivated by retinal prosthetics, where discretization of event times is consequent on the task description. Separately, we show evidence that commonly used datasets favour smaller models. Finally, we introduce new synthetic datasets for testing larger models, as well as synthetic datasets with discrete event times. |
| title | Categorical Distributions are Effective Neural Network Outputs for Event Prediction |
| topic | Machine Learning |
| url | https://arxiv.org/abs/2507.21616 |