Growing Cosine Unit: A Novel Oscillatory Activation Function That Can Speedup Training and Reduce Parameters in Convolutional Neural Networks

Documenti analoghi

• Biologically Inspired Oscillating Activation Functions Can Bridge the Performance Gap between Biological and Artificial Neurons
  di: Noel, Matthew Mithra, et al.
  Pubblicazione: (2021)
• A Significantly Better Class of Activation Functions Than ReLU Like Activation Functions
  di: Noel, Mathew Mithra, et al.
  Pubblicazione: (2024)
• Alternate Loss Functions for Classification and Robust Regression Can Improve the Accuracy of Artificial Neural Networks
  di: Noel, Mathew Mithra, et al.
  Pubblicazione: (2023)
• Efficient Vectorized Backpropagation Algorithms for Training Feedforward Networks Composed of Quadratic Neurons
  di: Noel, Mathew Mithra, et al.
  Pubblicazione: (2023)
• Parallel Spiking Unit for Efficient Training of Spiking Neural Networks
  di: Li, Yang, et al.
  Pubblicazione: (2024)