5 papers
Fitting Multilinear Polynomials for Logic Gate Networks
Youngsung Kim
We study learnable logic gate networks that stack layers of 2-input Boolean gates to build combinational circuits. Every 2-input gate has a unique multilinear polynomial with 4 coe…
Align Forward, Adapt Backward: Closing the Discretization Gap in Logic Gate Networks
Youngsung Kim
In neural network models, soft mixtures of fixed candidate components (e.g., logic gates and sub-networks) are often used during training for stable optimization, while hard select…
Standard Neural Computation Alone Is Insufficient for Logical Intelligence
Youngsung Kim
Neural networks, as currently designed, fall short of achieving true logical intelligence. Modern AI models rely on standard neural computation-inner-product-based transformations…
Towards Narrowing the Generalization Gap in Deep Boolean Networks
Youngsung Kim
The rapid growth of the size and complexity in deep neural networks has sharply increased computational demands, challenging their efficient deployment in real-world scenarios. Boo…
ProtoFL: Unsupervised Federated Learning via Prototypical Distillation
Hansol Kim, Youngjun Kwak, Minyoung Jung +3
Federated learning (FL) is a promising approach for enhancing data privacy preservation, particularly for authentication systems. However, limited round communications, scarce repr…