no code implementations • 23 Dec 2021 • Eric Binnendyk, Marco Carmosino, Antonina Kolokolova, Ramyaa Ramyaa, Manuel Sabin
- If there is a strongly useful natural property in the sense of Razborov & Rudich 1997 -- an efficient algorithm that can distinguish between random strings and strings of non-trivial circuit complexity -- then general polynomial-sized Boolean circuits are learnable over any efficiently samplable distribution in randomized polynomial time, given membership queries to the target function
1 code implementation • NeurIPS Workshop AIPLANS 2021 • Giri P Krishnan, Frederick Maier, Ramyaa Ramyaa
Differentiable methods to learn rules (logic programs) have the potential to integrate the interpretability, transferability and low data requirements of inductive logic programming with the noise tolerance of non-symbolic learning.
no code implementations • 4 May 2020 • Michael R. Smith, Nicholas T. Johnson, Joe B. Ingram, Armida J. Carbajal, Ramyaa Ramyaa, Evelyn Domschot, Christopher C. Lamb, Stephen J. Verzi, W. Philip Kegelmeyer
Specifically, current datasets and representations used by ML are not suitable for learning the behaviors of an executable and differ significantly from those used by the InfoSec community.
no code implementations • ICLR 2020 • Timothy Tadros, Giri Krishnan, Ramyaa Ramyaa, Maxim Bazhenov
In this work, we utilize a biologically inspired sleep phase in ANNs and demonstrate the benefit of sleep on defending against adversarial attacks as well as in increasing ANN classification robustness.
no code implementations • 1 Aug 2019 • Giri P. Krishnan, Timothy Tadros, Ramyaa Ramyaa, Maxim Bazhenov
First, in an incremental learning framework, sleep is able to recover older tasks that were otherwise forgotten in the ANN without sleep phase due to catastrophic forgetting.