4 papers
Efficient Sparse Selective-Update RNNs for Long-Range Sequence Modeling
Bojian Yin, Shurong Wang, Haoyu Tan +3
Real-world sequential signals, such as audio or video, contain critical information that is often embedded within long periods of silence or noise. While recurrent neural networks…
Traces Propagation: Memory-Efficient and Scalable Forward-Only Learning in Spiking Neural Networks
Lorenzo Pes, Bojian Yin, Sander Stuijk +1
Spiking Neural Networks (SNNs) provide an efficient framework for processing dynamic spatio-temporal signals and for investigating the learning principles underlying biological neu…
Stochastic Layer-wise Learning: Scalable and Efficient Alternative to Backpropagation
Bojian Yin, Federico Corradi
Backpropagation underpins modern deep learning, yet its reliance on global gradient synchronization limits scalability and incurs high memory costs. In contrast, fully local learni…
Never Reset Again: A Mathematical Framework for Continual Inference in Recurrent Neural Networks
Bojian Yin, Federico Corradi
Recurrent Neural Networks (RNNs) are widely used for sequential processing but face fundamental limitations with continual inference due to state saturation, requiring disruptive h…