2 papers
cs.LG2025
Categorical Distributions are Effective Neural Network Outputs for Event Prediction
Kevin Doran, Tom Baden
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…
q-bio.NC2023
Spike distance function as a learning objective for spike prediction
Kevin Doran, Marvin Seifert, Carola A. M. Yovanovich +1
Approaches to predicting neuronal spike responses commonly use a Poisson learning objective. This objective quantizes responses into spike counts within a fixed summation interval,…