Low-power analogue neural networks with trainable nonlinear connections for continuous control
arXiv:2606.23742v1 Announce Type: new Abstract: Physical neural networks promise low-power machine learning by computing directly with analogue device physics, but most architectures force nonlinear device responses to act as scalar weights. Inspired by Kolmogorov-Arnold networks, we place trainable nonlinear functions on the connections, making each physical connection a learnable computational element. Realising these functions as analogue band-pass filters on field-programmable analogue array
延伸阅读
- One Ruler: A Same-Hands Re-Evaluation of Bivariate Causal Direction on Tuebingen, with a Parameter-Free Compression Baseline
- Exploring Dualistic Meta-Learning to Enhance Domain Generalization in Open Set Scenarios
- Synergizing Physically Constrained MCMC and Chemical-Informed Gaussian Processes for Reaction Network Discovery
相关资讯
One Ruler: A Same-Hands Re-Evaluation of Bivariate Causal Direction on Tuebingen, with a Parameter-Free Compression Baseline
今天Exploring Dualistic Meta-Learning to Enhance Domain Generalization in Open Set Scenarios
今天Synergizing Physically Constrained MCMC and Chemical-Informed Gaussian Processes for Reaction Network Discovery
今天A Survey on Federated Causal Discovery and Inference
今天