4 papers · 1 filter
Neuron merging via inverse-activation regression for post-training compression of sigmoid neural networks
Ao Kuniya, Jun Ohkubo
As neural networks continue to grow in scale, model compression is becoming increasingly important for efficient inference under limited computational resources. Structured pruning…
Learning Koopman operators for coupled systems via information on governing equations of subsystems
Tatsuya Naoi, Jun Ohkubo
Nonlinear coupled systems are ubiquitous in science and engineering. The analysis and modeling of such systems are challenging due to their high dimensionality and complex interact…
Tensor-based computation of the Koopman generator via operator logarithm
Tatsuya Kishimoto, Jun Ohkubo
Identifying governing equations of nonlinear dynamical systems from data is challenging. While sparse identification of nonlinear dynamics (SINDy) and its extensions are widely use…
Neural network initialization with nonlinear characteristics and information on hierarchical features
Hikaru Homma, Jun Ohkubo
Initialization of neural network parameters, such as weights and biases, has a crucial impact on learning performance; if chosen well, we can even avoid the need for additional tra…