3 citations · 12 across the 6 of their papers we have counts for
7 papers
Misalignment of Low-Loss Regions Causes Grokking
Yongding Tian, Zaid Al-Ars, Maksim Kitsak +1
Grokking refers to the delayed emergence of validation-set generalization after a model has already overfit the training set. Although first observed in small algorithmic tasks tra…
Connecting Independently Trained Modes via Layer-Wise Connectivity
Yongding Tian, Zaid Al-Ars, Maksim Kitsak +1
Empirical studies have shown that continuous low-loss paths can be constructed between independently trained neural network models. This phenomenon, known as mode connectivity, ref…
Tydi-lang: A Language for Typed Streaming Hardware
Yongding Tian, Matthijs A. Reukers, Zaid Al-Ars +4
Transferring composite data structures with variable-length fields often requires designing unique protocols, causing incompatibility issues and decreased collaboration among hardw…
An Attention Module for Convolutional Neural Networks
Zhu Baozhou, Peter Hofstee, Jinho Lee +1
Attention mechanism has been regarded as an advanced technique to capture long-range feature interactions and to boost the representation capability for convolutional neural networ…
AutoReCon: Neural Architecture Search-based Reconstruction for Data-free Compression
Baozhou Zhu, Peter Hofstee, Johan Peltenburg +2
Data-free compression raises a new challenge because the original training dataset for a pre-trained model to be compressed is not available due to privacy or transmission issues.…
SoFAr: Shortcut-based Fractal Architectures for Binary Convolutional Neural Networks
Zhu Baozhou, Peter Hofstee, Jinho Lee +1
Binary Convolutional Neural Networks (BCNNs) can significantly improve the efficiency of Deep Convolutional Neural Networks (DCNNs) for their deployment on resource-constrained pla…
NASB: Neural Architecture Search for Binary Convolutional Neural Networks
Baozhou Zhu, Zaid Al-Ars, Peter Hofstee
Binary Convolutional Neural Networks (CNNs) have significantly reduced the number of arithmetic operations and the size of memory storage needed for CNNs, which makes their deploym…