Summary of Relu-kan: New Kolmogorov-arnold Networks That Only Need Matrix Addition, Dot Multiplication, and Relu, by Qi Qiu et al.
ReLU-KAN: New Kolmogorov-Arnold Networks that Only Need Matrix Addition, Dot Multiplication, and ReLUby Qi Qiu,…
ReLU-KAN: New Kolmogorov-Arnold Networks that Only Need Matrix Addition, Dot Multiplication, and ReLUby Qi Qiu,…
Activation-Descent Regularization for Input Optimization of ReLU Networksby Hongzhan Yu, Sicun GaoFirst submitted to arxiv…
Optimizing cnn-Bigru performance: Mish activation and comparative analysis with Reluby Asmaa Benchama, Khalid ZebbaraFirst submitted…
Large Deviations of Gaussian Neural Networks with ReLU activationby Quirin VogelFirst submitted to arxiv on:…
Novel Kernel Models and Exact Representor Theory for Neural Networks Beyond the Over-Parameterized Regimeby Alistair…
Adversarial Training of Two-Layer Polynomial and ReLU Activation Networks via Convex Optimizationby Daniel Kuelbs, Sanjay…
Sigmoid Gating is More Sample Efficient than Softmax Gating in Mixture of Expertsby Huy Nguyen,…
Keep the Momentum: Conservation Laws beyond Euclidean Gradient Flowsby Sibylle Marcotte, Rémi Gribonval, Gabriel PeyréFirst…
A Method on Searching Better Activation Functionsby Haoyuan Sun, Zihao Wu, Bo Xia, Pu Chang,…
Using Degeneracy in the Loss Landscape for Mechanistic Interpretabilityby Lucius Bushnaq, Jake Mendel, Stefan Heimersheim,…