4 papers
Task-Aware Discretization of Differentiable Logic Gate Networks
Thore Gerlach
Differentiable logic gate networks (DLGNs) enable gradient-based training of highly efficient Boolean networks by relaxing discrete logic gates during training and discretizing the…
WARP Logic Neural Networks
Lino Gerlach, Thore Gerlach, Liv Våge +2
Fast and efficient AI inference is increasingly important, and recent models that directly learn low-level logic operations have achieved state-of-the-art performance. However, exi…
WARP-LUTs -- Walsh-Assisted Relaxation for Probabilistic Look Up Tables
Lino Gerlach, Liv Våge, Thore Gerlach +2
Fast and efficient machine learning is of growing interest to the scientific community and has spurred significant research into novel model architectures and hardware-aware design…
Quantum Boltzmann Machines for Sample-Efficient Reinforcement Learning
Thore Gerlach, Michael Schenk, Verena Kain
We introduce theoretically grounded Continuous Semi-Quantum Boltzmann Machines (CSQBMs) that supports continuous-action reinforcement learning. By combining exponential-family prio…