no code implementations • 7 May 2024 • Mathew Mithra Noel, Yug Oswal
This paper introduces a significantly better class of activation functions than the almost universally used ReLU like and Sigmoidal class of activation functions.
no code implementations • 4 Oct 2023 • Mathew Mithra Noel, Venkataraman Muthiah-Nakarajan
Solutions to the XOR problem with a single quadratic neuron are considered.
1 code implementation • 17 Mar 2023 • Mathew Mithra Noel, Arindam Banerjee, Geraldine Bessie Amali D, Venkataraman Muthiah-Nakarajan
Two new classification loss functions that significantly improve performance on a wide variety of benchmark tasks are proposed.
no code implementations • 30 Aug 2021 • Mathew Mithra Noel, Arunkumar L, Advait Trivedi, Praneet Dutta
This ability to learn complex high-dimensional functions hierarchically can be attributed to the use of nonlinear activation functions.